pith. sign in

arxiv: 2605.12451 · v2 · pith:NNRPEF6Inew · submitted 2026-05-12 · 💻 cs.CV

FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation

Nicholas Ikechukwu , Keanu Nichols , Deepti Ghadiyaram , Bryan A. Plummer This is my paper

Pith reviewed 2026-05-20 22:16 UTC · model grok-4.3

classification 💻 cs.CV
keywords continual panoptic segmentationcontrastive learningfuture class discoverybackground repulsionrepresentation restructuringpanoptic quality
0
0 comments X

The pith

FuTCR improves new-class panoptic quality by up to 28% in continual segmentation by discovering future-like regions and repelling background features from known prototypes.

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

Continual panoptic segmentation requires models to learn new object categories from images that contain both labeled and unlabeled objects. Existing methods treat all unlabeled pixels as one background class, which discards distinctions that later become important when those objects receive labels. The paper claims that identifying regions the current model treats inconsistently as background yet shows non-background signals, then contrasting pixels within those regions while pushing background features away from known-class prototypes, restructures the representation space ahead of time. If this holds, the model can incorporate new categories with less interference from prior training. A sympathetic reader would care because the same images used for current classes now also prepare the system for categories that appear later.

Core claim

FuTCR discovers confident future-like regions by grouping model-predicted masks whose pixels are consistently classified as background but exhibit non-background logits. It then applies pixel-to-region contrast to build coherent prototypes from these unlabeled regions, while simultaneously repelling background features away from known-class prototypes to explicitly reserve representational space for future categories.

What carries the argument

Discovery of confident future-like regions followed by pixel-to-region contrast and repulsion of background features from known-class prototypes.

Load-bearing premise

Model-predicted masks whose pixels are consistently classified as background but exhibit non-background logits reliably correspond to regions belonging to future categories that will be introduced later.

What would settle it

If the discovered regions fail to match the actual new classes when those classes are added, or if ablating the future-targeted contrast and repulsion steps removes the reported gains on new-class panoptic quality, the mechanism would not hold.

Figures

Figures reproduced from arXiv: 2605.12451 by Bryan A. Plummer, Deepti Ghadiyaram, Keanu Nichols, Nicholas Ikechukwu.

Figure 1
Figure 1. Figure 1: From background noise to structured supervision. (a) Prior continual panoptic methods treat background regions as non-informative [21, 23, 29, 30], allowing future-class evidence to be absorbed into existing decision regions in feature space over time. (b) Our framework instead converts background activations into future-aware structural cues that organize scene composition before new labels arrive, reduci… view at source ↗
Figure 2
Figure 2. Figure 2: Overview of FuTCR, a query-based continual panoptic model produces dense region features and mask predictions. Our future-targeted module leverages unlabeled regions together with ground-truth labeled regions to perform unlabeled region discovery Sec. 3.1, region-level contrastive learning Sec. 3.2, and known-class repulsion Sec. 3.3, encouraging structured rep￾resentations for future categories. The final… view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative comparison of segmentation produced by FuTCR and SimCIS [ [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 5
Figure 5. Figure 5: Future-aware error dynamics. FuTCR reduces the fraction of future-class pixels that are misclassified as base classes across incremental steps compared to Sim￾CIS [23], indicating less future–old class con￾fusion at the base step. 2 4 6 8 10 Incremental Step 10 20 30 40 50 60 SemSeg mIoU 2 4 6 8 10 Incremental Step 10 20 30 40 Panoptic PQ Ours (FuTCR) SimCIS Old Classes New Classes All Classes 2 3 4 5 6 7 … view at source ↗
Figure 6
Figure 6. Figure 6: Left/middle: FuTCR consistently outperforms SimCIS [23] in mIoU and PQ on ADE20K 100–5, with especially pronounced gains on newly introduced classes and improved performance on previously learned classes. Right: cross-step prototype similarity for old classes, where FuTCR permits moderate drift (down to ≈ 0.89) instead of the baseline’s near-rigid prototypes (> 0.97), and this adaptive evolution coincides … view at source ↗
Figure 7
Figure 7. Figure 7: Stability–plasticity trajectory of FuTCR versus SimCIS on ADE20K 100–5 (steps 2–11). [PITH_FULL_IMAGE:figures/full_fig_p014_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Additional qualitative comparisons between FuTCR and SimCIS [ [PITH_FULL_IMAGE:figures/full_fig_p016_8.png] view at source ↗
read the original abstract

Continual Panoptic Segmentation (CPS) requires methods that can quickly adapt to new categories over time. The nature of this dense prediction task means that training images may contain a mix of labeled and unlabeled objects. As nothing is known about these unlabeled objects a priori, existing methods often simply group any unlabeled pixel into a single "background" class during training. In effect, during training, they repeatedly tell the model that all the different background categories are the same (even when they aren't). This makes learning to identify different background categories as they are added challenging since these new categories may require using information the model was previously told was unimportant and ignored. Thus, we propose a Future-Targeted Contrastive and Repulsive (FuTCR) framework that addresses this limitation by restructuring representations before new classes are introduced. FuTCR first discovers confident future-like regions by grouping model-predicted masks whose pixels are consistently classified as background but exhibit non-background logits. Next, FuTCR applies pixel-to-region contrast to build coherent prototypes from these unlabeled regions, while simultaneously repelling background features away from known-class prototypes to explicitly reserve representational space for future categories. Experiments across six CPS settings and a range of dataset sizes show FuTCR improves relative new-class panoptic quality over the state-of-the-art by up to 28%, while preserving or improving base-class performance with gains up to 4%.

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.

Referee Report

1 major / 3 minor

Summary. The manuscript proposes the FuTCR framework for continual panoptic segmentation. It identifies confident future-like regions by grouping pixels predicted as background but with non-background logits, then uses pixel-to-region contrast to build prototypes from these regions and repels background features from known-class prototypes to reserve space for future categories. Across six experimental settings, it claims relative improvements in new-class panoptic quality of up to 28% over prior state-of-the-art while maintaining or enhancing base-class performance by up to 4%.

Significance. If the discovery step reliably isolates future-class regions rather than uncertainties, FuTCR would provide a concrete mechanism for proactively structuring representations in CPS to accommodate unlabeled objects that later become new classes. The multi-setting experiments and reported relative gains suggest the approach could improve adaptability in dense prediction tasks, with the explicit repulsion term offering a clear way to reserve representational capacity.

major comments (1)
  1. [Abstract and §3.2] Abstract (discovery step) and §3.2: The central claim attributes up to 28% relative new-class PQ gains to the future-targeting effect of grouping background-classified pixels that exhibit non-background logits. This step assumes such regions predominantly contain pixels from classes that will be introduced later, yet the same logit pattern arises from epistemic uncertainty at base-class boundaries, rare intra-class variants, or non-future unlabeled objects. No quantitative validation (e.g., overlap statistics with held-out future ground truth or ablation that disables the discovery module) is provided, so the performance attribution remains unconfirmed.
minor comments (3)
  1. [§3.3] §3.3: The pixel-to-region contrast and repulsion losses are described at a high level but lack explicit equations or hyperparameter schedules, making exact reproduction difficult.
  2. [§4] §4: Tables reporting PQ metrics should include standard deviations over multiple runs and p-values for the claimed improvements to establish statistical reliability.
  3. [Figure 2] Figure 2: The visualization of discovered regions would benefit from side-by-side ground-truth overlays to illustrate the composition of the selected pixels.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback and positive assessment of the work's potential impact. We address the major comment point by point below and commit to revisions that directly strengthen the validation of the discovery mechanism.

read point-by-point responses

  1. Referee: [Abstract and §3.2] Abstract (discovery step) and §3.2: The central claim attributes up to 28% relative new-class PQ gains to the future-targeting effect of grouping background-classified pixels that exhibit non-background logits. This step assumes such regions predominantly contain pixels from classes that will be introduced later, yet the same logit pattern arises from epistemic uncertainty at base-class boundaries, rare intra-class variants, or non-future unlabeled objects. No quantitative validation (e.g., overlap statistics with held-out future ground truth or ablation that disables the discovery module) is provided, so the performance attribution remains unconfirmed.

    Authors: We agree that explicit quantitative validation of the discovered regions would provide stronger confirmation that the performance gains stem specifically from future-targeting rather than other factors such as uncertainty reduction. In the standard CPS protocol, future-class labels are unavailable during training, which precludes direct overlap statistics with held-out ground truth without altering the evaluation protocol. The manuscript instead relies on consistent relative gains of up to 28% across six diverse settings, together with the design of the contrast and repulsion terms, as indirect support. To address the concern directly, we will add (i) an ablation that disables the discovery module entirely (treating all background pixels uniformly) and reports the resulting drop in new-class PQ, and (ii) additional analysis of logit distributions and qualitative examples to characterize the discovered regions relative to boundary uncertainty. These revisions will be incorporated in the next version. revision: yes

Circularity Check

0 steps flagged

No significant circularity in FuTCR method derivation

full rationale

The paper presents FuTCR as an empirical framework that first identifies candidate future-like regions via a heuristic on current model outputs (background-classified pixels with non-background logits), then applies pixel-to-region contrast and prototype repulsion. No equations, fitted parameters renamed as predictions, or self-citation chains are shown that would make the reported PQ gains equivalent to the inputs by construction. The central claims rest on experimental results across multiple CPS settings rather than a closed logical loop, rendering the derivation self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Based solely on the abstract, the approach rests on domain assumptions about the informativeness of model logits in background regions rather than introducing explicit free parameters or new entities; full paper may reveal additional details.

axioms (1)
  • domain assumption Pixels consistently predicted as background but showing non-background logits form coherent regions that correspond to future object categories.
    This assumption underpins the discovery of future-like regions described in the abstract.

pith-pipeline@v0.9.0 · 5794 in / 1376 out tokens · 40836 ms · 2026-05-20T22:16:33.485218+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

62 extracted references · 62 canonical work pages

  1. [1]

    Ferret: An efficient online continual learning framework under varying memory constraints

    Yuhao Zhou, Yuxin Tian, Jindi Lv, Mingjia Shi, Yuanxi Li, Qing Ye, Shuhao Zhang, and Jiancheng Lv. Ferret: An efficient online continual learning framework under varying memory constraints. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 4850–4861, 2025

    work page 2025

  2. [2]

    Do your best and get enough rest for continual learning

    Hankyul Kang, Gregor Seifer, Donghyun Lee, and Jongbin Ryu. Do your best and get enough rest for continual learning. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 10077–10086, 2025

    work page 2025

  3. [3]

    End-to-end incremental learning

    Francisco M Castro, Manuel J Marín-Jiménez, Nicolás Guil, Cordelia Schmid, and Karteek Alahari. End-to-end incremental learning. InProceedings of the European conference on computer vision (ECCV), pages 233–248, 2018

    work page 2018

  4. [4]

    icarl: Incremental classifier and representation learning

    Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H Lampert. icarl: Incremental classifier and representation learning. InProceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 2001–2010, 2017

    work page 2001

  5. [5]

    Riemannian walk for incremental learning: Understanding forgetting and intransigence

    Arslan Chaudhry, Puneet K Dokania, Thalaiyasingam Ajanthan, and Philip HS Torr. Riemannian walk for incremental learning: Understanding forgetting and intransigence. InProceedings of the European conference on computer vision (ECCV), pages 532–547, 2018

    work page 2018

  6. [6]

    Continual learning with deep generative replay.Advances in neural information processing systems, 30, 2017

    Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. Continual learning with deep generative replay.Advances in neural information processing systems, 30, 2017

    work page 2017

  7. [7]

    Der: Dynamically expandable representation for class incremental learning

    Shipeng Yan, Jiangwei Xie, and Xuming He. Der: Dynamically expandable representation for class incremental learning. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 3014–3023, 2021

    work page 2021

  8. [8]

    Few-shot class-incremental learning

    Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, and Yihong Gong. Few-shot class-incremental learning. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12183–12192, 2020

    work page 2020

  9. [9]

    Vector quantization prompting for continual learning

    Li Jiao, Qiuxia Lai, Yu Li, and Qiang Xu. Vector quantization prompting for continual learning. Advances in Neural Information Processing Systems, 37:34056–34076, 2024

    work page 2024

  10. [10]

    Ordisco: Effective and efficient usage of incremental unlabeled data for semi-supervised continual learning

    Liyuan Wang, Kuo Yang, Chongxuan Li, Lanqing Hong, Zhenguo Li, and Jun Zhu. Ordisco: Effective and efficient usage of incremental unlabeled data for semi-supervised continual learning. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5383–5392, 2021

    work page 2021

  11. [11]

    PAC-bayes bounds for cumulative loss in continual learning

    Lior Friedman and Ron Meir. PAC-bayes bounds for cumulative loss in continual learning. In The Fourteenth International Conference on Learning Representations, 2026. URL https: //openreview.net/forum?id=hWw269fPov

    work page 2026

  12. [12]

    Bors, Jingling Sun, Rongyao Hu, and Shijie Zhou

    Fei Ye, Yulong Zhao, Qihe Liu, Junlin Chen, Adrian G. Bors, Jingling Sun, Rongyao Hu, and Shijie Zhou. Dynamic siamese expansion framework for improving robustness in online continual learning. InAdvances in Neural Information Processing Systems, 2025

    work page 2025

  13. [13]

    Exploiting task relationships in continual learning via transferability-aware task embeddings

    Yanru Wu, Jianning Wang, Xiangyu Chen, Enming Zhang, Yang Tan, Hanbing Liu, and Yang Li. Exploiting task relationships in continual learning via transferability-aware task embeddings. InAdvances in Neural Information Processing Systems, 2025. URL https: //openreview.net/forum?id=V8FnYzDX35

    work page 2025

  14. [14]

    Anacp: Toward upper-bound continual learning via analytic contrastive projection

    Saleh Momeni, Changnan Xiao, and Bing Liu. Anacp: Toward upper-bound continual learning via analytic contrastive projection. InAdvances in Neural Information Processing Systems,

    work page

  15. [15]

    URLhttps://openreview.net/forum?id=qQbvLU34F1

    work page

  16. [16]

    Hippotune: A hippocampal associative loop–inspired fine-tuning method for continual learning

    chenyanxi, Xiuxing Li, Han Yuyang, Zhuo Wang, Qing Li, Ziyu Li, Xiang Li, Chen Wei, and Xia Wu. Hippotune: A hippocampal associative loop–inspired fine-tuning method for continual learning. InThe Fourteenth International Conference on Learning Representations, 2026. URL https://openreview.net/forum?id=MtDiLnnYgm. 10

    work page 2026

  17. [17]

    ADAPT: Attentive self- distillation and dual-decoder prediction fusion for continual panoptic segmentation

    Ze Yang, Shichao Dong, Ruibo Li, Nan Song, and Guosheng Lin. ADAPT: Attentive self- distillation and dual-decoder prediction fusion for continual panoptic segmentation. InThe Thirteenth International Conference on Learning Representations, 2025. URL https:// openreview.net/forum?id=HF1UmIVv6a

    work page 2025

  18. [18]

    Beyond background shift: Rethinking instance replay in continual semantic segmentation

    Hongmei Yin, Tingliang Feng, Fan Lyu, Fanhua Shang, Hongying Liu, Wei Feng, and Liang Wan. Beyond background shift: Rethinking instance replay in continual semantic segmentation. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 9839–9848, 2025

    work page 2025

  19. [19]

    Falcon: Fairness learning via contrastive attention approach to continual semantic scene understanding

    Thanh-Dat Truong, Utsav Prabhu, Bhiksha Raj, Jackson Cothren, and Khoa Luu. Falcon: Fairness learning via contrastive attention approach to continual semantic scene understanding. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 15065– 15075, 2025

    work page 2025

  20. [20]

    Continual gaussian mixture distribution modeling for class incremental semantic segmentation

    Guilin Zhu, Runmin Wang, Yuanjie Shao, Wei dong Yang, Nong Sang, and Changxin Gao. Continual gaussian mixture distribution modeling for class incremental semantic segmentation. InThe Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. URL https://openreview.net/forum?id=dtYKDOBkc7

    work page 2025

  21. [21]

    Parameter release and knowledge reuse for class-incremental semantic segmentation, 2025

    Xinyue Zhang, Xu Zou, Liqun Chen, Jiahuan Zhou, Guodong Wang, Sheng Zhong, and Luxin Yan. Parameter release and knowledge reuse for class-incremental semantic segmentation, 2025. URLhttps://openreview.net/forum?id=9qbKOaF8YJ

    work page 2025

  22. [22]

    Combo: Conflict mitigation via branched optimization for class incremental segmentation

    Kai Fang, Anqi Zhang, Guangyu Gao, Jianbo Jiao, Chi Harold Liu, and Yunchao Wei. Combo: Conflict mitigation via branched optimization for class incremental segmentation. InPro- ceedings of the Computer Vision and Pattern Recognition Conference, pages 25667–25676, 2025

    work page 2025

  23. [23]

    Continual semantic segmentation with automatic memory sample selection

    Lanyun Zhu, Tianrun Chen, Jianxiong Yin, Simon See, and Jun Liu. Continual semantic segmentation with automatic memory sample selection. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3082–3092, 2023

    work page 2023

  24. [24]

    Rethinking query-based transformer for continual image segmentation

    Yuchen Zhu, Cheng Shi, Dingyou Wang, Jiajin Tang, Zhengxuan Wei, Yu Wu, Guanbin Li, and Sibei Yang. Rethinking query-based transformer for continual image segmentation. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 4595–4606, 2025

    work page 2025

  25. [25]

    Contrastive grouping with transformer for referring image segmentation

    Jiajin Tang, Ge Zheng, Cheng Shi, and Sibei Yang. Contrastive grouping with transformer for referring image segmentation. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 23570–23580, 2023

    work page 2023

  26. [26]

    The devil is in the object boundary: Towards annotation-free instance segmentation using foundation models.arXiv preprint arXiv:2404.11957, 2024

    Cheng Shi and Sibei Yang. The devil is in the object boundary: Towards annotation-free instance segmentation using foundation models.arXiv preprint arXiv:2404.11957, 2024

    work page arXiv 2024

  27. [27]

    Coinseg: Contrast inter-and intra-class representations for incremental segmentation

    Zekang Zhang, Guangyu Gao, Jianbo Jiao, Chi Harold Liu, and Yunchao Wei. Coinseg: Contrast inter-and intra-class representations for incremental segmentation. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 843–853, 2023

    work page 2023

  28. [28]

    Towards continual universal segmentation

    Zihan Lin, Zilei Wang, and Xu Wang. Towards continual universal segmentation. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 29417–29427, June 2025

    work page 2025

  29. [29]

    Eclipse: Efficient continual learning in panoptic segmentation with visual prompt tuning

    Beomyoung Kim, Joonsang Yu, and Sung Ju Hwang. Eclipse: Efficient continual learning in panoptic segmentation with visual prompt tuning. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3346–3356, 2024

    work page 2024

  30. [30]

    Comformer: Continual learning in semantic and panoptic segmentation

    Fabio Cermelli, Matthieu Cord, and Arthur Douillard. Comformer: Continual learning in semantic and panoptic segmentation. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3010–3020, 2023

    work page 2023

  31. [31]

    Strike a balance in continual panoptic segmentation

    Jinpeng Chen, Runmin Cong, Yuxuan Luo, Horace Ho Shing Ip, and Sam Kwong. Strike a balance in continual panoptic segmentation. InEuropean Conference on Computer Vision, pages 126–142. Springer, 2024. 11

    work page 2024

  32. [32]

    Fixmatch: Simplifying semi- supervised learning with consistency and confidence.Advances in neural information processing systems, 33:596–608, 2020

    Kihyuk Sohn, David Berthelot, Nicholas Carlini, Zizhao Zhang, Han Zhang, Colin A Raf- fel, Ekin Dogus Cubuk, Alexey Kurakin, and Chun-Liang Li. Fixmatch: Simplifying semi- supervised learning with consistency and confidence.Advances in neural information processing systems, 33:596–608, 2020

    work page 2020

  33. [33]

    A simple framework for contrastive learning of visual representations

    Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. A simple framework for contrastive learning of visual representations. InInternational conference on machine learning, pages 1597–1607. PmLR, 2020

    work page 2020

  34. [34]

    Momentum contrast for unsupervised visual representation learning

    Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. Momentum contrast for unsupervised visual representation learning. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9729–9738, 2020

    work page 2020

  35. [35]

    Classmix: Segmentation-based data augmentation for semi-supervised learning

    Viktor Olsson, Wilhelm Tranheden, Juliano Pinto, and Lennart Svensson. Classmix: Segmentation-based data augmentation for semi-supervised learning. InProceedings of the IEEE/CVF winter conference on applications of computer vision, pages 1369–1378, 2021

    work page 2021

  36. [36]

    Preparing the future for continual semantic segmenta- tion

    Zihan Lin, Zilei Wang, and Yixin Zhang. Preparing the future for continual semantic segmenta- tion. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 11910–11920, 2023

    work page 2023

  37. [37]

    Continual panoptic perception: Towards multi-modal incremental interpretation of remote sensing images

    Bo Yuan, Danpei Zhao, Zhuoran Liu, Wentao Li, and Tian Li. Continual panoptic perception: Towards multi-modal incremental interpretation of remote sensing images. InProceedings of the 32nd ACM International Conference on Multimedia, pages 2117–2126, 2024

    work page 2024

  38. [38]

    Ssul: Semantic segmentation with unknown label for exemplar-based class-incremental learning.Advances in neural information processing systems, 34:10919–10930, 2021

    Sungmin Cha, YoungJoon Yoo, Taesup Moon, et al. Ssul: Semantic segmentation with unknown label for exemplar-based class-incremental learning.Advances in neural information processing systems, 34:10919–10930, 2021

    work page 2021

  39. [39]

    Vista-clip: Visual incre- mental self-tuned adaptation for efficient continual panoptic segmentation

    D Manjunath, Shrikar Madhu, Aniruddh Sikdar, and Suresh Sundaram. Vista-clip: Visual incre- mental self-tuned adaptation for efficient continual panoptic segmentation. In2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 6557–

    work page

  40. [40]

    Catastrophic forgetting in connectionist networks.Trends in cognitive sciences, 3(4):128–135, 1999

    Robert M French. Catastrophic forgetting in connectionist networks.Trends in cognitive sciences, 3(4):128–135, 1999

    work page 1999

  41. [41]

    Catastrophic forgetting, rehearsal and pseudorehearsal.Connection Science, 7 (2):123–146, 1995

    Anthony Robins. Catastrophic forgetting, rehearsal and pseudorehearsal.Connection Science, 7 (2):123–146, 1995

    work page 1995

  42. [42]

    Lifelong learning algorithms

    Sebastian Thrun. Lifelong learning algorithms. InLearning to learn, pages 181–209. Springer, 1998

    work page 1998

  43. [43]

    A survey on continual semantic segmentation: Theory, challenge, method and application.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024

    Bo Yuan and Danpei Zhao. A survey on continual semantic segmentation: Theory, challenge, method and application.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024

    work page 2024

  44. [44]

    Mitigating background shift in class-incremental semantic segmentation

    Gilhan Park, WonJun Moon, SuBeen Lee, Tae-Young Kim, and Jae-Pil Heo. Mitigating background shift in class-incremental semantic segmentation. InEuropean Conference on Computer Vision, pages 71–88. Springer, 2024

    work page 2024

  45. [45]

    Modeling the background for incremental learning in semantic segmentation

    Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulo, Elisa Ricci, and Barbara Caputo. Modeling the background for incremental learning in semantic segmentation. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9233–9242, 2020

    work page 2020

  46. [46]

    KIT Scientific Publishing, 2024

    Tobias Michael Kalb.Principles of Catastrophic Forgetting for Continual Semantic Segmenta- tion in Automated Driving. KIT Scientific Publishing, 2024

    work page 2024

  47. [47]

    Continual semantic segmentation via structure preserving and projected feature alignment

    Zihan Lin, Zilei Wang, and Yixin Zhang. Continual semantic segmentation via structure preserving and projected feature alignment. InEuropean Conference on Computer Vision, pages 345–361. Springer, 2022

    work page 2022

  48. [48]

    Scale-hybrid group distillation with knowl- edge disentangling for continual semantic segmentation.Sensors, 23(18):7820, 2023

    Zichen Song, Xiaoliang Zhang, and Zhaofeng Shi. Scale-hybrid group distillation with knowl- edge disentangling for continual semantic segmentation.Sensors, 23(18):7820, 2023. 12

    work page 2023

  49. [49]

    Bacs: Background aware continual semantic segmentation.arXiv preprint arXiv:2404.13148, 2024

    Mostafa ElAraby, Ali Harakeh, and Liam Paull. Bacs: Background aware continual semantic segmentation.arXiv preprint arXiv:2404.13148, 2024

    work page arXiv 2024

  50. [50]

    Trace back and go ahead: Completing partial annotation for continual semantic segmentation.Pattern Recognition, 165:111613, 2025

    Yuxuan Luo, Jinpeng Chen, Runmin Cong, Horace Ho Shing Ip, and Sam Kwong. Trace back and go ahead: Completing partial annotation for continual semantic segmentation.Pattern Recognition, 165:111613, 2025

    work page 2025

  51. [51]

    Exemplar-based open- set panoptic segmentation network

    Jaedong Hwang, Seoung Wug Oh, Joon-Young Lee, and Bohyung Han. Exemplar-based open- set panoptic segmentation network. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1175–1184, 2021

    work page 2021

  52. [52]

    Revis- iting open-set panoptic segmentation

    Yufei Yin, Hao Chen, Wengang Zhou, Jiajun Deng, Haiming Xu, and Houqiang Li. Revis- iting open-set panoptic segmentation. InProceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 6747–6754, 2024

    work page 2024

  53. [53]

    Region-aware metric learning for open world semantic segmentation via meta-channel aggrega- tion.arXiv preprint arXiv:2205.08083, 2022

    Hexin Dong, Zifan Chen, Mingze Yuan, Yutong Xie, Jie Zhao, Fei Yu, Bin Dong, and Li Zhang. Region-aware metric learning for open world semantic segmentation via meta-channel aggrega- tion.arXiv preprint arXiv:2205.08083, 2022

    work page arXiv 2022

  54. [54]

    Dual decision improves open-set panoptic segmentation.arXiv preprint arXiv:2207.02504, 2022

    Hai-Ming Xu, Hao Chen, Lingqiao Liu, and Yufei Yin. Dual decision improves open-set panoptic segmentation.arXiv preprint arXiv:2207.02504, 2022

    work page arXiv 2022

  55. [55]

    Panoptic segmentation

    Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, and Piotr Dollár. Panoptic segmentation. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9404–9413, 2019

    work page 2019

  56. [56]

    Contrastive attraction and contrastive repulsion for representation learning.arXiv preprint arXiv:2105.03746, 2021

    Huangjie Zheng, Xu Chen, Jiangchao Yao, Hongxia Yang, Chunyuan Li, Ya Zhang, Hao Zhang, Ivor Tsang, Jingren Zhou, and Mingyuan Zhou. Contrastive attraction and contrastive repulsion for representation learning.arXiv preprint arXiv:2105.03746, 2021

    work page arXiv 2021

  57. [57]

    Attraction-repulsion spectrum in neighbor embeddings.Journal of Machine Learning Research, 23(95):1–32, 2022

    Jan Niklas Böhm, Philipp Berens, and Dmitry Kobak. Attraction-repulsion spectrum in neighbor embeddings.Journal of Machine Learning Research, 23(95):1–32, 2022

    work page 2022

  58. [58]

    Yu and Jianbo Shi

    Stella X. Yu and Jianbo Shi. Segmentation with pairwise attraction and repulsion. InProceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, volume 1, pages 52–58. IEEE, 2001

    work page 2001

  59. [59]

    Scene parsing through ade20k dataset

    Bolei Zhou, Hang Zhao, Xavier Puig, Sanja Fidler, Adela Barriuso, and Antonio Torralba. Scene parsing through ade20k dataset. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017

    work page 2017

  60. [60]

    Masked-attention mask transformer for universal image segmentation

    Bowen Cheng, Ishan Misra, Alexander G Schwing, Alexander Kirillov, and Rohit Girdhar. Masked-attention mask transformer for universal image segmentation. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1290–1299, 2022

    work page 2022

  61. [61]

    Deep residual learning for image recognition

    Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. 13 A Additional Analysis A.1 Stability–plasticity Trajectory Fig. 7 summarizes the stability–plasticity behavior of FuTCR and SimCIS on ADE20K 100–5. Each...

    work page 2016

  62. [62]

    Aux. cls

    The two panels depict diverse scenes where FuTCR recovers more accurate panoptic masks, particularly on newly introduced classes. and a balance term: Laux = 1 |Rfut| X r CE(gr, ℓr) +λ bal KL ¯p∥u ,(5) where ¯p is the mean predicted distribution over clusters and u is the uniform distribution. This head is intended to encourage diverse usage of latent slot...

    work page