CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift

Amrita Singh; Rishabh Jha

arxiv: 2606.23487 · v1 · pith:TWPZ323Enew · submitted 2026-06-22 · 💻 cs.AI

CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift

Amrita Singh , Rishabh Jha This is my paper

Pith reviewed 2026-06-26 08:37 UTC · model grok-4.3

classification 💻 cs.AI

keywords continual learningmedical vision-language modelsparameter-efficient adaptationcatastrophic forgettingelastic weight consolidationLoRAcross-modality adaptationbackward transfer

0 comments

The pith

CADRE adapts medical vision-language models across modalities while reducing forgetting sevenfold and achieving positive backward transfer by training 0.23 percent of parameters.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents CADRE as a parameter-efficient method for continual adaptation of medical vision-language models that prioritizes stability over raw accuracy. It freezes the backbone and adds low-rank adaptation together with an online self-scaling similarity-aware elastic weight consolidation term and an anchor-to-prior penalty. These components are designed to bound competence loss on prior modalities and keep embeddings from drifting away from the pretrained prior. Two short guarantees on total consolidation mass and scale invariance are shown to remove order fragility that affects standard elastic weight consolidation. In controlled tests on breast cancer imaging across histopathology, ultrasound, and chest radiography using multiple seeds and orders, CADRE records the lowest forgetting and the only positive backward transfer among compared methods.

Core claim

CADRE is a frozen-backbone framework that pairs low-rank adaptation with an online, self-scaling, similarity-aware elastic weight consolidation term bounding retained-competence loss and an anchor-to-prior penalty bounding embedding drift from the frozen prior. The two guarantees (bound on total consolidation mass and scale-invariance) eliminate scale-related order fragility of vanilla EWC. Under a multi-seed, multi-order protocol with paired significance testing on three maximally dissimilar modalities, CADRE attains the highest accuracy, SPQ, and backward transfer and the lowest forgetting (0.011 versus 0.075 for the strongest baseline, paired p=0.023) while training approximately 0.23 per

What carries the argument

The online, self-scaling, similarity-aware elastic weight consolidation term together with the anchor-to-prior penalty, which together bound retained-competence loss and embedding drift while supplying the mass and scale-invariance guarantees that remove order fragility.

If this is right

CADRE records the lowest forgetting and the only positive backward transfer among the adapting methods tested.
Forgetting is reduced roughly sevenfold relative to the strongest regularized baseline under the same protocol.
The mass bound and scale-invariance guarantees remove the scale-related sources of order fragility present in vanilla EWC.
Only approximately 0.23 percent of parameters are trained, keeping the backbone frozen.
The resulting stability properties are framed as aligned with clinical-safety desiderata rather than a deployment guarantee.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same regularization structure could be applied to continual adaptation of other large vision-language models outside medicine to limit drift from a trusted prior.
The cross-modality stress test on three dissimilar breast-cancer modalities indicates the method may extend to other multi-modal medical tasks where order of arrival is uncontrolled.
Because the guarantees are independent of post-hoc thresholds, the approach might reduce the need for validation-set tuning when models are updated incrementally in practice.

Load-bearing premise

That the online self-scaling similarity-aware elastic weight consolidation term and the anchor-to-prior penalty actually bound retained-competence loss and embedding drift in the claimed way and that the two short guarantees eliminate order fragility without post-hoc scaling or similarity threshold choices.

What would settle it

A replication of the multi-seed multi-order cross-modality protocol in which CADRE's forgetting measure exceeds 0.011, backward transfer turns negative, or paired significance testing no longer shows it outperforming the strongest regularized baseline.

Figures

Figures reproduced from arXiv: 2606.23487 by Amrita Singh, Rishabh Jha.

**Figure 1.** Figure 1: Overview of CADRE. A frozen BiomedCLIP (ViT-B/16) encoder is adapted sequentially over dissimilar modalities (histopathology → ultrasound → · · · → radiography) via visual-encoder LoRA (≈0.23% of parameters) and a linear head, regularized by three stability mechanisms: (1) online self-scaling EWC over a sum-normalised running Fisher; (2) similarity-aware retention relaxing consolidation for dissimilar mo… view at source ↗

read the original abstract

Medical vision-language models (VLMs) such as BiomedCLIP generalize broadly, but adapting them to a clinical service is as much a safety problem as an accuracy one. Updating a deployed model for a new imaging modality can fail silently in two ways that harm patients: it can forget modalities it already handled (catastrophic forgetting), and it can drift from its trustworthy pretrained prior toward modality-specific shortcuts. We study parameter-efficient continual adaptation through these two properties rather than leaderboard accuracy, presenting CADRE: a frozen-backbone framework combining low-rank adaptation (LoRA) with an online, self-scaling, similarity-aware elastic weight consolidation term that bounds retained-competence loss, and an anchor-to-prior penalty bounding embedding drift from the frozen prior. Two short guarantees, a bound on total consolidation mass and a scale-invariance property, remove the scale-related sources of vanilla EWC's order fragility. Using breast cancer across three maximally dissimilar modalities (histopathology, ultrasound, chest radiography) as a controlled cross-modality stress test, under a multi-seed, multi-order protocol with paired significance testing and training approximately 0.23% of parameters, CADRE attains the highest accuracy, SPQ, and backward transfer and the lowest forgetting among adapting methods, reducing forgetting roughly sevenfold versus the strongest regularized baseline (0.075 to 0.011; paired p=0.023) and achieving positive backward transfer where every baseline is negative. We frame these as stability properties aligned with clinical-safety desiderata, not a deployment guarantee; robustness to distribution shift and adversarial inputs is out of scope.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

CADRE gives a concrete recipe for low-forgetting adaptation of medical VLMs via modified EWC plus anchor term, with decent controls on a narrow test set.

read the letter

CADRE combines LoRA with an online self-scaling similarity-aware EWC term and an anchor-to-prior penalty to limit both forgetting and drift from the pretrained prior during cross-modality adaptation. The two short guarantees on total consolidation mass and scale invariance are meant to remove the usual order fragility of vanilla EWC.

The experiments use a controlled stress test on breast cancer across histopathology, ultrasound, and chest radiography. They run multi-seed multi-order protocols with paired significance tests, train roughly 0.23 percent of parameters, and report CADRE cutting forgetting from 0.075 to 0.011 (p=0.023) while achieving positive backward transfer where baselines stay negative. That focus on stability metrics rather than leaderboard accuracy is the clearest practical angle.

The empirical protocol looks careful for what it covers. The soft spots are the narrow scope—all results stay inside one disease area—and the fact that the guarantees are described as short, so it is not yet obvious whether they hold without depending on the very scaling and similarity choices the method introduces. Generalization beyond these three modalities is not shown.

This is for people working on safe continual deployment of medical imaging models who already care about forgetting and prior drift. A reader who needs a ready-to-try stability recipe with some theory backing will get value from it. The work is coherent enough on its own terms to deserve a serious referee, even if revisions will likely be needed on scope and derivation details.

I would send it to peer review.

Referee Report

2 major / 1 minor

Summary. The manuscript introduces CADRE, a frozen-backbone parameter-efficient continual adaptation framework for medical vision-language models. It augments LoRA with an online self-scaling similarity-aware elastic weight consolidation (EWC) term claimed to bound retained-competence loss and an anchor-to-prior penalty claimed to bound embedding drift. Two short guarantees (bound on total consolidation mass; scale-invariance) are asserted to remove order fragility from vanilla EWC. In a multi-seed, multi-order protocol on cross-modality breast cancer imaging (histopathology, ultrasound, chest radiography), CADRE reports the highest accuracy, SPQ, and backward transfer, the lowest forgetting (sevenfold reduction vs. strongest baseline: 0.075 to 0.011, paired p=0.023), and positive backward transfer while training ~0.23% of parameters.

Significance. If the two guarantees are shown to be independent of the self-scaling factor and similarity threshold, and if the empirical protocol is fully reproducible with error bars, the work would be significant for clinical-safety-oriented continual learning: it supplies a concrete, low-parameter mechanism that demonstrably reduces forgetting and yields positive backward transfer where baselines fail, directly addressing silent failure modes (catastrophic forgetting and prior drift) in deployed medical VLMs.

major comments (2)

[Abstract] Abstract: the central empirical claims (sevenfold forgetting reduction 0.075 o0.011, paired p=0.023, positive backward transfer, highest SPQ) rest on a multi-seed multi-order protocol whose data splits, exact task ordering, statistical test details, and error bars are not visible; without these the numerical superiority cannot be assessed as load-bearing evidence.
[Abstract] Abstract: the two short guarantees (bound on total consolidation mass; scale-invariance) are asserted to eliminate order fragility of the self-scaling similarity-aware EWC term, yet the abstract supplies neither the equations nor the derivation; it is therefore impossible to verify whether the bounds are independent of the free parameters listed in the axiom ledger or reduce by construction to quantities already defined by the method.

minor comments (1)

[Abstract] Abstract: the framing that results are "stability properties aligned with clinical-safety desiderata, not a deployment guarantee" is appropriately cautious and should be retained.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed report. The comments highlight important aspects of clarity and verifiability in the abstract. We address each major comment point-by-point below and agree to revisions that improve accessibility of the protocol details and guarantees while preserving the manuscript's focus.

read point-by-point responses

Referee: [Abstract] Abstract: the central empirical claims (sevenfold forgetting reduction 0.075 to 0.011, paired p=0.023, positive backward transfer, highest SPQ) rest on a multi-seed multi-order protocol whose data splits, exact task ordering, statistical test details, and error bars are not visible; without these the numerical superiority cannot be assessed as load-bearing evidence.

Authors: We agree that space constraints in the abstract prevent inclusion of the full protocol specification. The multi-seed, multi-order protocol, data splits, exact task orderings, paired statistical tests (including p=0.023), and error bars (standard deviations across seeds) are fully detailed in Section 4 and the appendix. To address the concern, we will revise the abstract to briefly reference the protocol, note the use of paired significance testing, and direct readers to Section 4 for complete reproducibility information. This makes the evidence more readily assessable without altering the reported results. revision: yes
Referee: [Abstract] Abstract: the two short guarantees (bound on total consolidation mass; scale-invariance) are asserted to eliminate order fragility of the self-scaling similarity-aware EWC term, yet the abstract supplies neither the equations nor the derivation; it is therefore impossible to verify whether the bounds are independent of the free parameters listed in the axiom ledger or reduce by construction to quantities already defined by the method.

Authors: The two guarantees and their derivations, including proofs of independence from the self-scaling factor and similarity threshold (as well as confirmation that they do not reduce to prior quantities), appear in full in Section 3.2. The abstract summarizes their role in removing order fragility but omits equations due to length limits. We will revise the abstract to include a concise statement of the guarantees and their independence properties, with explicit reference to Section 3.2 for the derivations. This directly enables verification as requested. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected from available text

full rationale

The abstract and provided context describe CADRE's components (LoRA + self-scaling similarity-aware EWC + anchor-to-prior penalty) and assert two guarantees (bound on total consolidation mass; scale-invariance) that purportedly eliminate order fragility. No equations, derivation steps, or self-citations are quoted or visible in the supplied material. Without manuscript equations to inspect, no step can be exhibited that reduces by construction to a fitted parameter, self-definition, or load-bearing self-citation. The reported empirical results (accuracy, forgetting metrics, p-values) are framed as experimental outcomes under a multi-seed protocol rather than tautological predictions. Per the rules, absence of quotable reductions means the finding is no significant circularity.

Axiom & Free-Parameter Ledger

2 free parameters · 2 axioms · 0 invented entities

Abstract-only review prevents exhaustive enumeration; the ledger below records only the elements explicitly invoked in the abstract. Full paper would be needed to list all free parameters and background assumptions.

free parameters (2)

self-scaling factor in EWC term
Invoked to achieve scale-invariance but value and fitting procedure not stated in abstract.
similarity threshold or weighting in EWC
Used to make consolidation similarity-aware; no numerical value or selection method given.

axioms (2)

ad hoc to paper The bound on total consolidation mass and the scale-invariance property remove order fragility of vanilla EWC
Stated as two short guarantees that underwrite the method's stability claims.
domain assumption The three chosen modalities (histopathology, ultrasound, chest radiography) constitute a maximally dissimilar cross-modality stress test
Used to justify the experimental design as a controlled test of forgetting.

pith-pipeline@v0.9.1-grok · 5828 in / 1534 out tokens · 20220 ms · 2026-06-26T08:37:21.916632+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

33 extracted references · 7 canonical work pages · 2 internal anchors

[1]

BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs

Zhang, S., Xu, Y., Usuyama, N., Bagga, J., Tinn, R., Preston, S., Rao, R., Wei, M., Valluri, N., Wong, C., Lungren, M.P., Naumann, T., Poon, H.: BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million image– text pairs. arXiv:2303.00915 (2023)

work page internal anchor Pith review Pith/arXiv arXiv 2023
[2]

In: Bower, G.H

McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Bower, G.H. (ed.) Psychology of Learning and Motivation, vol. 24, pp. 109–165. Academic Press (1989)

1989
[3]

Proceedings of the National Academy of Sciences114(13), 3521–3526 (2017)

Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A.A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., Hassabis, D., Clopath, C., Kumaran, D., Hadsell, R.: Overcoming catastrophic forgetting in neu- ral networks. Proceedings of the National Academy of Sciences114(13), 3521–3526 (2017)

2017
[4]

In: Proceedings of the 35th International Conference on Machine Learn- ing (ICML), pp

Schwarz, J., Czarnecki, W., Luketina, J., Grabska-Barwinska, A., Teh, Y.W., Pas- canu, R., Hadsell, R.: Progress & Compress: a scalable framework for continual learning. In: Proceedings of the 35th International Conference on Machine Learn- ing (ICML), pp. 4528–4537 (2018)

2018
[5]

LoRA: Low-Rank Adaptation of Large Language Models

Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (ICLR) (2022). arXiv:2106.09685

work page internal anchor Pith review Pith/arXiv arXiv 2022
[6]

IEEE Transactions on Pattern Analysis and Machine Intelligence40(12), 2935–2947 (2017)

Li, Z., Hoiem, D.: Learning without forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence40(12), 2935–2947 (2017)

2017
[7]

In: Advances in Neural Information Processing Systems 30 (NeurIPS), pp

Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. In: Advances in Neural Information Processing Systems 30 (NeurIPS), pp. 6467–6476 (2017)

2017
[8]

In: Proceedings of the IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR), pp

Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classi- fier and representation learning. In: Proceedings of the IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR), pp. 2001–2010 (2017)

2001
[9]

In: Proceedings of the 2022 Conference on Em- pirical Methods in Natural Language Processing (EMNLP), pp

Wang, Z., Wu, Z., Agarwal, D., Sun, J.: MedCLIP: contrastive learning from un- paired medical images and text. In: Proceedings of the 2022 Conference on Em- pirical Methods in Natural Language Processing (EMNLP), pp. 3894–3905 (2022). arXiv:2210.10163

work page arXiv 2022
[10]

Nature Medicine29, 2304–2316 (2023)

Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T.J., Zou, J.: A visual–language foundation model for pathology image analysis using medical Twitter. Nature Medicine29, 2304–2316 (2023)

2023
[11]

Neural Networks113, 54–71 (2019)

Parisi, G.I., Kemker, R., Part, J.L., Kanan, C., Wermter, S.: Continual lifelong learning with neural networks: a review. Neural Networks113, 54–71 (2019)

2019
[12]

IEEE Transactions on Pattern Analysis and Machine Intelli- gence44(7), 3366–3385 (2022)

De Lange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., Tuytelaars, T.: A continual learning survey: defying forgetting in classification tasks. IEEE Transactions on Pattern Analysis and Machine Intelli- gence44(7), 3366–3385 (2022)

2022
[13]

In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp

Zenke, F., Poole, B., Ganguli, S.: Continual learning through synaptic intelligence. In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp. 3987–3995 (2017)

2017
[14]

In: Proceedings of the European Conference on Computer Vision (ECCV), pp

Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to forget. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 144–160 (2018)

2018
[15]

Neural Computation4(3), 448–472 (1992) 10 Amrita Singh and Rishabh Jha

MacKay, D.J.C.: A practical Bayesian framework for backpropagation networks. Neural Computation4(3), 448–472 (1992) 10 Amrita Singh and Rishabh Jha

1992
[16]

In: Interna- tional Conference on Learning Representations (ICLR) (2020)

Titsias, M.K., Schwarz, J., Matthews, A.G.G., Pascanu, R., Teh, Y.W.: Func- tional regularisation for continual learning with Gaussian processes. In: Interna- tional Conference on Learning Representations (ICLR) (2020)

2020
[17]

In: Proceedings of the 36th International Conference on Machine Learning (ICML), pp

Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., de Laroussilhe, Q., Ges- mundo, A., Attariyan, M., Gelly, S.: Parameter-efficient transfer learning for NLP. In: Proceedings of the 36th International Conference on Machine Learning (ICML), pp. 2790–2799 (2019)

2019
[18]

In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp

Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neu- ral networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp. 1321–1330 (2017)

2017
[19]

In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), pp

Naeini,M.P.,Cooper,G.F.,Hauskrecht,M.:Obtainingwellcalibratedprobabilities using Bayesian binning. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), pp. 2901–2907 (2015)

2015
[20]

In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the Incep- tion architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826 (2016)

2016
[21]

4694–4703 (2019)

Müller, R., Kornblith, S., Hinton, G.: When does label smoothing help? In: Ad- vances in Neural Information Processing Systems 32 (NeurIPS), pp. 4694–4703 (2019)

2019
[22]

In: Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI), pp

Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. In: Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI), pp. 876– 885 (2018)

2018
[23]

In: Advances in Neural Information Processing Systems 30 (NeurIPS), pp

Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems 30 (NeurIPS), pp. 1195–1204 (2017)

2017
[24]

In: Proceedings of the Third Conference on Medical Imaging with Deep Learning (MIDL), PMLR 121, pp

Lenga, M., Schulz, H., Saalbach, A.: Continual learning for domain adapta- tion in chest X-ray classification. In: Proceedings of the Third Conference on Medical Imaging with Deep Learning (MIDL), PMLR 121, pp. 413–423 (2020). arXiv:2001.05922

work page arXiv 2020
[25]

Nature Communications12, 5678 (2021)

Perkonigg, M., Hofmanninger, J., Herold, C.J., Brink, J.A., Pianykh, O.S., Prosch, H., Langs, G.: Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging. Nature Communications12, 5678 (2021)

2021
[26]

arXiv:2405.13482 (2024)

Qazi, M.A., Nawaz, M., Naseer, M., Khan, S., Khan, F.S.: Continual learning in medical imaging: a survey and practical analysis. arXiv:2405.13482 (2024)

work page arXiv 2024
[27]

arXiv:2511.20732 (2025)

Gao, Z., Morel, P.: Prompt-aware adaptive elastic weight consolidation for contin- ual learning in medical vision–language models. arXiv:2511.20732 (2025)

work page arXiv 2025
[28]

IEEE Transactions on Biomedical Engineer- ing63(7), 1455–1462 (2016)

Spanhol, F.A., Oliveira, L.S., Petitjean, C., Heutte, L.: A dataset for breast cancer histopathological image classification. IEEE Transactions on Biomedical Engineer- ing63(7), 1455–1462 (2016)

2016
[29]

In: Proceedings of the European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science 13686, pp

Jia, M., Tang, L., Chen, B.C., Cardie, C., Belongie, S., Hariharan, B., Lim, S.N.: Visual prompt tuning. In: Proceedings of the European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science 13686, pp. 709–727 (2022)

2022
[30]

In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp

Wang, Z., Zhang, Z., Lee, C.Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J., Pfister, T.: Learning to prompt for continual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13949–13958 (2022)

2022
[31]

In: Proceedings of the European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science 13686, pp

Wang, Z., Zhang, Z., Ebrahimi, S., Sun, R., Zhang, H., Lee, C.Y., Ren, X., Su, G., Perot, V., Dy, J., Pfister, T.: DualPrompt: complementary prompting for rehearsal- free continual learning. In: Proceedings of the European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science 13686, pp. 13746–13756 (2022) CADRE: Stable, Parameter-Efficie...

2022
[32]

In: Findings of the Asso- ciation for Computational Linguistics: EMNLP 2023, pp

Wang, X., Chen, T., Ge, Y., Zhou, J., Zhao, H.: Orthogonal subspace learn- ing for language model continual learning (O-LoRA). In: Findings of the Asso- ciation for Computational Linguistics: EMNLP 2023, pp. 11123–11137 (2023). arXiv:2310.14152

work page arXiv 2023
[33]

In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp

Liang, Y.S., Li, W.J.: InfLoRA: interference-free low-rank adaptation for continual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28672–28681 (2024)

2024

[1] [1]

BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs

Zhang, S., Xu, Y., Usuyama, N., Bagga, J., Tinn, R., Preston, S., Rao, R., Wei, M., Valluri, N., Wong, C., Lungren, M.P., Naumann, T., Poon, H.: BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million image– text pairs. arXiv:2303.00915 (2023)

work page internal anchor Pith review Pith/arXiv arXiv 2023

[2] [2]

In: Bower, G.H

McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Bower, G.H. (ed.) Psychology of Learning and Motivation, vol. 24, pp. 109–165. Academic Press (1989)

1989

[3] [3]

Proceedings of the National Academy of Sciences114(13), 3521–3526 (2017)

Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A.A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., Hassabis, D., Clopath, C., Kumaran, D., Hadsell, R.: Overcoming catastrophic forgetting in neu- ral networks. Proceedings of the National Academy of Sciences114(13), 3521–3526 (2017)

2017

[4] [4]

In: Proceedings of the 35th International Conference on Machine Learn- ing (ICML), pp

Schwarz, J., Czarnecki, W., Luketina, J., Grabska-Barwinska, A., Teh, Y.W., Pas- canu, R., Hadsell, R.: Progress & Compress: a scalable framework for continual learning. In: Proceedings of the 35th International Conference on Machine Learn- ing (ICML), pp. 4528–4537 (2018)

2018

[5] [5]

LoRA: Low-Rank Adaptation of Large Language Models

Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (ICLR) (2022). arXiv:2106.09685

work page internal anchor Pith review Pith/arXiv arXiv 2022

[6] [6]

IEEE Transactions on Pattern Analysis and Machine Intelligence40(12), 2935–2947 (2017)

Li, Z., Hoiem, D.: Learning without forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence40(12), 2935–2947 (2017)

2017

[7] [7]

In: Advances in Neural Information Processing Systems 30 (NeurIPS), pp

Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. In: Advances in Neural Information Processing Systems 30 (NeurIPS), pp. 6467–6476 (2017)

2017

[8] [8]

In: Proceedings of the IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR), pp

Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classi- fier and representation learning. In: Proceedings of the IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR), pp. 2001–2010 (2017)

2001

[9] [9]

In: Proceedings of the 2022 Conference on Em- pirical Methods in Natural Language Processing (EMNLP), pp

Wang, Z., Wu, Z., Agarwal, D., Sun, J.: MedCLIP: contrastive learning from un- paired medical images and text. In: Proceedings of the 2022 Conference on Em- pirical Methods in Natural Language Processing (EMNLP), pp. 3894–3905 (2022). arXiv:2210.10163

work page arXiv 2022

[10] [10]

Nature Medicine29, 2304–2316 (2023)

Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T.J., Zou, J.: A visual–language foundation model for pathology image analysis using medical Twitter. Nature Medicine29, 2304–2316 (2023)

2023

[11] [11]

Neural Networks113, 54–71 (2019)

Parisi, G.I., Kemker, R., Part, J.L., Kanan, C., Wermter, S.: Continual lifelong learning with neural networks: a review. Neural Networks113, 54–71 (2019)

2019

[12] [12]

IEEE Transactions on Pattern Analysis and Machine Intelli- gence44(7), 3366–3385 (2022)

De Lange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., Tuytelaars, T.: A continual learning survey: defying forgetting in classification tasks. IEEE Transactions on Pattern Analysis and Machine Intelli- gence44(7), 3366–3385 (2022)

2022

[13] [13]

In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp

Zenke, F., Poole, B., Ganguli, S.: Continual learning through synaptic intelligence. In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp. 3987–3995 (2017)

2017

[14] [14]

In: Proceedings of the European Conference on Computer Vision (ECCV), pp

Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to forget. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 144–160 (2018)

2018

[15] [15]

Neural Computation4(3), 448–472 (1992) 10 Amrita Singh and Rishabh Jha

MacKay, D.J.C.: A practical Bayesian framework for backpropagation networks. Neural Computation4(3), 448–472 (1992) 10 Amrita Singh and Rishabh Jha

1992

[16] [16]

In: Interna- tional Conference on Learning Representations (ICLR) (2020)

Titsias, M.K., Schwarz, J., Matthews, A.G.G., Pascanu, R., Teh, Y.W.: Func- tional regularisation for continual learning with Gaussian processes. In: Interna- tional Conference on Learning Representations (ICLR) (2020)

2020

[17] [17]

In: Proceedings of the 36th International Conference on Machine Learning (ICML), pp

Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., de Laroussilhe, Q., Ges- mundo, A., Attariyan, M., Gelly, S.: Parameter-efficient transfer learning for NLP. In: Proceedings of the 36th International Conference on Machine Learning (ICML), pp. 2790–2799 (2019)

2019

[18] [18]

In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp

Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neu- ral networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp. 1321–1330 (2017)

2017

[19] [19]

In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), pp

Naeini,M.P.,Cooper,G.F.,Hauskrecht,M.:Obtainingwellcalibratedprobabilities using Bayesian binning. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), pp. 2901–2907 (2015)

2015

[20] [20]

In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the Incep- tion architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826 (2016)

2016

[21] [21]

4694–4703 (2019)

Müller, R., Kornblith, S., Hinton, G.: When does label smoothing help? In: Ad- vances in Neural Information Processing Systems 32 (NeurIPS), pp. 4694–4703 (2019)

2019

[22] [22]

In: Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI), pp

Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. In: Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI), pp. 876– 885 (2018)

2018

[23] [23]

In: Advances in Neural Information Processing Systems 30 (NeurIPS), pp

Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems 30 (NeurIPS), pp. 1195–1204 (2017)

2017

[24] [24]

In: Proceedings of the Third Conference on Medical Imaging with Deep Learning (MIDL), PMLR 121, pp

Lenga, M., Schulz, H., Saalbach, A.: Continual learning for domain adapta- tion in chest X-ray classification. In: Proceedings of the Third Conference on Medical Imaging with Deep Learning (MIDL), PMLR 121, pp. 413–423 (2020). arXiv:2001.05922

work page arXiv 2020

[25] [25]

Nature Communications12, 5678 (2021)

Perkonigg, M., Hofmanninger, J., Herold, C.J., Brink, J.A., Pianykh, O.S., Prosch, H., Langs, G.: Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging. Nature Communications12, 5678 (2021)

2021

[26] [26]

arXiv:2405.13482 (2024)

Qazi, M.A., Nawaz, M., Naseer, M., Khan, S., Khan, F.S.: Continual learning in medical imaging: a survey and practical analysis. arXiv:2405.13482 (2024)

work page arXiv 2024

[27] [27]

arXiv:2511.20732 (2025)

Gao, Z., Morel, P.: Prompt-aware adaptive elastic weight consolidation for contin- ual learning in medical vision–language models. arXiv:2511.20732 (2025)

work page arXiv 2025

[28] [28]

IEEE Transactions on Biomedical Engineer- ing63(7), 1455–1462 (2016)

Spanhol, F.A., Oliveira, L.S., Petitjean, C., Heutte, L.: A dataset for breast cancer histopathological image classification. IEEE Transactions on Biomedical Engineer- ing63(7), 1455–1462 (2016)

2016

[29] [29]

In: Proceedings of the European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science 13686, pp

Jia, M., Tang, L., Chen, B.C., Cardie, C., Belongie, S., Hariharan, B., Lim, S.N.: Visual prompt tuning. In: Proceedings of the European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science 13686, pp. 709–727 (2022)

2022

[30] [30]

In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp

Wang, Z., Zhang, Z., Lee, C.Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J., Pfister, T.: Learning to prompt for continual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13949–13958 (2022)

2022

[31] [31]

In: Proceedings of the European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science 13686, pp

Wang, Z., Zhang, Z., Ebrahimi, S., Sun, R., Zhang, H., Lee, C.Y., Ren, X., Su, G., Perot, V., Dy, J., Pfister, T.: DualPrompt: complementary prompting for rehearsal- free continual learning. In: Proceedings of the European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science 13686, pp. 13746–13756 (2022) CADRE: Stable, Parameter-Efficie...

2022

[32] [32]

In: Findings of the Asso- ciation for Computational Linguistics: EMNLP 2023, pp

Wang, X., Chen, T., Ge, Y., Zhou, J., Zhao, H.: Orthogonal subspace learn- ing for language model continual learning (O-LoRA). In: Findings of the Asso- ciation for Computational Linguistics: EMNLP 2023, pp. 11123–11137 (2023). arXiv:2310.14152

work page arXiv 2023

[33] [33]

In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp

Liang, Y.S., Li, W.J.: InfLoRA: interference-free low-rank adaptation for continual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28672–28681 (2024)

2024