pith. sign in

arxiv: 2606.20924 · v1 · pith:KRSYR2ESnew · submitted 2026-06-18 · 💻 cs.CV

ELDiff: When Evidential Learning Meets Text-to-Image Diffusion

Qingtao Pan , Kai Ye , Zhihao Dou , Bing Ji , Shuo Li This is my paper

Pith reviewed 2026-06-26 17:38 UTC · model grok-4.3

classification 💻 cs.CV
keywords evidential learningtext-to-image diffusionsemantic consistencymulti-object generationsegmentation biastoken conflictStable Diffusion
0
0 comments X

The pith

ELDiff adds evidential learning to text-to-image diffusion to reduce segmentation bias and semantic conflicts in multi-object scenes.

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

The paper tries to establish that evidential learning can strengthen object-wise consistency in multi-object T2I diffusion by using uncertainty to tolerate unreliable segmentation maps and by detecting conflicts between object tokens. A sympathetic reader would care because current diffusion models often produce images that miss or mix up elements when prompts describe several objects at once. ELDiff introduces a pixel evidence loss to regularize overconfidence in bad labels and a token conflict loss to weaken semantic contradictions during training. If the approach works, it delivers better prompt adherence on existing diffusion backbones without any changes at inference time.

Core claim

ELDiff is a new evidential learning-supervised T2I diffusion model that leverages uncertainty metrics and conflict detection to enhance fault tolerance of unreliable segmentation maps and suppress semantic conflicts, strengthening object-wise consistency learning through a pixel evidence loss that restrains overconfidence via evidential regularization and a token conflict loss that optimizes a measured conflict factor.

What carries the argument

Pixel evidence loss and token conflict loss, which apply evidential regularization to unreliable segmentation labels and optimize a conflict factor between object tokens.

If this is right

  • ELDiff outperforms existing training-based and train-free T2I diffusion models on SD v1.4, SD v2.1, SDXL, SD v3.5, and Qwen-Image.
  • Gains are achieved without requiring additional inference-time manipulations.
  • ELDiff integrates directly into the existing training pipeline of T2I diffusion models.

Where Pith is reading between the lines

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

  • Similar uncertainty handling could be tested in video or 3D generation where element consistency across frames or views is required.
  • The method may allow training on automatically generated or lower-quality segmentation data instead of clean manual maps.
  • Extending the conflict loss to other modalities such as text-to-video or image-to-text could address overlapping concepts in those settings.

Load-bearing premise

The pixel evidence loss and token conflict loss can reliably reduce segmentation map bias and semantic overlap conflict without creating new training instabilities or degrading single-object performance.

What would settle it

A controlled test on a multi-object prompt set with deliberately noisy or overlapping segmentation maps where ELDiff produces more missing objects, attribute errors, or lower human preference scores than standard token-supervised training.

Figures

Figures reproduced from arXiv: 2606.20924 by Bing Ji, Kai Ye, Qingtao Pan, Shuo Li, Zhihao Dou.

Figure 1
Figure 1. Figure 1: Overview of ELDiff. The main components include: (1) The pixel evidence loss drives reliable consistency constraint between the text prompts and the image contents through pixel-level uncertainty estimation; (2) The token conflict loss weakens the contradiction between semantics. 3.1 Problem setup Segmentation map bias. While consistency constraint based T2I diffusion methods have shown great success [67,7… view at source ↗
Figure 2
Figure 2. Figure 2: Detailed diagram of pixel evidence loss and token conflict loss. [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Ablation visualization demonstrates that finetuning the Stable Diffusion with only LLDM does not clearly identify the target objects. By introducing LP ixEvi and LT okCon, the model shows substantial improvement in text-object correspondence. 4.6 Comparison with Stronger T2I Backbone [PITH_FULL_IMAGE:figures/full_fig_p012_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative comparison between our ELDiff and the other T2I models. 4.7 User Study We also conducted user studies on SD v2.1 and SD v3.5. This study involves 11 volunteers with expertise in image processing. Participants were asked to select the best image based on realism, compositionality, and overall quality. We use 1,000 prompts from DSG1K [8] for evaluation. Vot￾ing results are shown in [PITH_FULL_IM… view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative comparison of finetuning methods based on SD v3.5 Medium [PITH_FULL_IMAGE:figures/full_fig_p024_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Qualitative comparison of finetuning methods based on Stable Diffusion v2.1 [PITH_FULL_IMAGE:figures/full_fig_p025_6.png] view at source ↗
read the original abstract

In multi-object text-to-image (T2I) diffusion, ensuring semantic consistency between textual prompts and generated visual content is crucial for image synthesis. However, such consistency constraint is often underemphasized in the denoising process of diffusion models. Although token supervised diffusion models can mitigate this issue by learning object-wise consistency between the image content and object segmentation maps, it tends to suffer from the problems of segmentation map bias and semantic overlap conflict, especially when involving multiple objects. In this paper, we propose ELDiff, a new evidential learning-supervised T2I diffusion model, which leverages the advantages of uncertainty metric and conflict detection to enhance the fault tolerance of unreliable segmentation maps and suppress semantic conflicts, strengthening object-wise consistency learning. Specifically, a pixel evidence loss is proposed to restrain overconfidence in unreliable labels through evidential regularization, and a token conflict loss is designed to weaken the contradiction between semantics through optimizing a measured conflict factor. Extensive experiments show that our ELDiff outperforms existing training based and train-free based T2I diffusion models on SD v1.4, SD v2.1, SDXL, SD v3.5, and Qwen-Image, without requiring additional inference-time manipulations. Notably, ELDiff can be seamlessly extended to the existing training pipeline of T2I diffusion models. Code can be found at https://github.com/QingtaoPan/ELDiff.

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 / 1 minor

Summary. The paper proposes ELDiff, a text-to-image diffusion model that augments standard training with evidential learning. It introduces a pixel evidence loss to regularize overconfidence on unreliable segmentation maps and a token conflict loss to reduce semantic contradictions between tokens. The central claim is that these additions improve object-wise consistency in multi-object generation, yielding better performance than both training-based and train-free baselines across SD v1.4, v2.1, SDXL, SD v3.5, and Qwen-Image, while requiring no inference-time changes and integrating seamlessly into existing diffusion training pipelines.

Significance. If the empirical claims are substantiated, ELDiff would demonstrate a practical training-time route to better semantic alignment in diffusion models by exploiting uncertainty quantification and conflict measurement, without the overhead of test-time interventions. The public code release at the cited GitHub repository is a clear strength for reproducibility. The significance remains conditional on verification that the added losses preserve training stability and do not trade off single-object fidelity.

major comments (1)
  1. [Experiments] The central claim that the pixel evidence loss and token conflict loss improve multi-object consistency without introducing training instabilities or degrading single-object performance is load-bearing, yet the manuscript provides no loss curves, divergence statistics, or single-object metrics to support it (Experiments section). Without these, the reported gains on SD v1.4–v3.5 and Qwen-Image cannot be assessed for robustness.
minor comments (1)
  1. Notation for the conflict factor and evidence parameters should be defined explicitly at first use to avoid ambiguity when the losses are combined with the standard diffusion objective.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive comment on the need for explicit validation of training stability and single-object performance. We address this below.

read point-by-point responses

  1. Referee: [Experiments] The central claim that the pixel evidence loss and token conflict loss improve multi-object consistency without introducing training instabilities or degrading single-object performance is load-bearing, yet the manuscript provides no loss curves, divergence statistics, or single-object metrics to support it (Experiments section). Without these, the reported gains on SD v1.4–v3.5 and Qwen-Image cannot be assessed for robustness.

    Authors: We agree that the manuscript lacks direct evidence such as loss curves, divergence statistics, or single-object metrics to substantiate the claims of no training instabilities or degradation in single-object fidelity. While the reported gains across multiple base models are consistent, this does not constitute explicit verification. In the revised version we will add training loss curves (comparing standard diffusion loss with the added pixel evidence and token conflict losses), divergence statistics between evidential and standard predictions, and single-object metrics (FID and CLIP score on single-object prompts) to directly support the robustness claims. revision: yes

Circularity Check

0 steps flagged

No circularity in derivation chain

full rationale

The paper derives pixel evidence loss (via evidential regularization to restrain overconfidence) and token conflict loss (via measured conflict factor to weaken semantic contradictions) from standard evidential learning theory applied to existing diffusion objectives. These are presented as new supervisory terms that extend the training pipeline without any reduction to fitted parameters, self-referential definitions, or load-bearing self-citations. No equations or claims in the abstract or described method equate outputs to inputs by construction; the central claims rest on independent evidential metrics rather than renaming or refitting the target consistency metrics themselves. The approach is self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available, so free parameters, axioms, and invented entities cannot be identified from the provided information.

pith-pipeline@v0.9.1-grok · 5785 in / 1015 out tokens · 34877 ms · 2026-06-26T17:38:19.812994+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

77 extracted references · 10 canonical work pages · 5 internal anchors

  1. [1]

    Advances in neural information processing systems33, 14927–14937 (2020)

    Amini, A., Schwarting, W., Soleimany, A., Rus, D.: Deep evidential regression. Advances in neural information processing systems33, 14927–14937 (2020)

    2020

  2. [2]

    Qwen3-VL Technical Report

    Bai, S., Cai, Y., Chen, R., Chen, K., Chen, X., Cheng, Z., Deng, L., Ding, W., Gao, C., Ge, C., et al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  3. [3]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Bao, W., Yu, Q., Kong, Y.: Evidential deep learning for open set action recognition. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 13349–13358 (2021)

    2021

  4. [4]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Blattmann, A., Rombach, R., Ling, H., Dockhorn, T., Kim, S.W., Fidler, S., Kreis, K.: Align your latents: High-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 22563–22575 (2023)

    2023

  5. [5]

    ACM transactions on Graphics (TOG)42(4), 1–10 (2023)

    Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. ACM transactions on Graphics (TOG)42(4), 1–10 (2023)

    2023

  6. [6]

    In: The Twelfth International Conference on Learning Representations

    Chen, J., Jincheng, Y., Chongjian, G., Yao, L., Xie, E., Wang, Z., Kwok, J., Luo, P., Lu, H., Li, Z.: Pixart-α: Fast training of diffusion transformer for photorealistic text-to-image synthesis. In: The Twelfth International Conference on Learning Representations

  7. [7]

    In: Pro- ceedings of the IEEE/CVF winter conference on applications of computer vision

    Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance. In: Pro- ceedings of the IEEE/CVF winter conference on applications of computer vision. pp. 5343–5353 (2024)

    2024

  8. [8]

    arXiv preprint arXiv:2310.18235 (2023)

    Cho,J.,Hu,Y.,Garg,R.,Anderson,P.,Krishna,R.,Baldridge,J.,Bansal,M.,Pont-Tuset,J.,Wang,S.: Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image generation. arXiv preprint arXiv:2310.18235 (2023)

    work page arXiv 2023

  9. [9]

    In: Classic works of the Dempster-Shafer theory of belief functions, pp

    Dempster, A.P.: Upper and lower probabilities induced by a multivalued mapping. In: Classic works of the Dempster-Shafer theory of belief functions, pp. 57–72 (2008)

    2008

  10. [10]

    Advances in Neural Information Processing Systems36, 58648–58669 (2023)

    Du, C., Li, Y., Qiu, Z., Xu, C.: Stable diffusion is unstable. Advances in Neural Information Processing Systems36, 58648–58669 (2023)

    2023

  11. [11]

    In: Forty-first international conference on machine learning (2024)

    Esser, P., Kulal, S., Blattmann, A., Entezari, R., Müller, J., Saini, H., Levi, Y., Lorenz, D., Sauer, A., Boesel, F., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-first international conference on machine learning (2024)

    2024

  12. [12]

    In: The Eleventh International Conference on Learning Representations

    Feng, W., He, X., Fu, T.J., Jampani, V., Akula, A.R., Narayana, P., Basu, S., Wang, X.E., Wang, W.Y.: Training-free structured diffusion guidance for compositional text-to-image synthesis. In: The Eleventh International Conference on Learning Representations

  13. [13]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Feng, Z., Zhang, Z., Yu, X., Fang, Y., Li, L., Chen, X., Lu, Y., Liu, J., Yin, W., Feng, S., et al.: Ernie-vilg 2.0: Improving text-to-image diffusion model with knowledge-enhanced mixture-of-denoising-experts. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 10135– 10145 (2023)

    2023

  14. [14]

    In: International conference on medical image computing and computer- assisted intervention

    Fu, W., Chen, Y., Liu, W., Yue, X., Ma, C.: Evidence reconciled neural network for out-of-distribution detection in medical images. In: International conference on medical image computing and computer- assisted intervention. pp. 305–315 (2023)

    2023

  15. [15]

    Advances in Neural Information Processing Systems36, 52132–52152 (2023)

    Ghosh, D., Hajishirzi, H., Schmidt, L.: Geneval: An object-focused framework for evaluating text-to- image alignment. Advances in Neural Information Processing Systems36, 52132–52152 (2023)

    2023

  16. [16]

    arXiv preprint arXiv:2212.10015 (2022)

    Gokhale, T., Palangi, H., Nushi, B., Vineet, V., Horvitz, E., Kamar, E., Baral, C., Yang, Y.: Bench- marking spatial relationships in text-to-image generation. arXiv preprint arXiv:2212.10015 (2022)

    work page arXiv 2022

  17. [17]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Guo, X., Liu, J., Cui, M., Li, J., Yang, H., Huang, D.: Initno: Boosting text-to-image diffusion models via initial noise optimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 9380–9389 (2024)

    2024

  18. [18]

    Advances in Neural Information Processing Systems36, 66923–66939 (2023)

    Hao, Y., Chi, Z., Dong, L., Wei, F.: Optimizing prompts for text-to-image generation. Advances in Neural Information Processing Systems36, 66923–66939 (2023)

    2023

  19. [19]

    Advances in neural information processing systems 30(2017) ELDiff 15

    Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30(2017) ELDiff 15

    2017

  20. [20]

    IEEE Transactions on Pattern Analysis and Machine Intelligence47(5), 3563–3579 (2025)

    Huang, K., Duan, C., Sun, K., Xie, E., Li, Z., Liu, X.: T2i-compbench++: An enhanced and compre- hensive benchmark for compositional text-to-image generation. IEEE Transactions on Pattern Analysis and Machine Intelligence47(5), 3563–3579 (2025)

    2025

  21. [21]

    Advances in Neural Information Processing Systems36, 78723–78747 (2023)

    Huang, K., Sun, K., Xie, E., Li, Z., Liu, X.: T2i-compbench: A comprehensive benchmark for open- world compositional text-to-image generation. Advances in Neural Information Processing Systems36, 78723–78747 (2023)

    2023

  22. [22]

    Machine Intelligence Research21(4), 617–630 (2024)

    Ji, W., Li, J., Bi, Q., Liu, T., Li, W., Cheng, L.: Segment anything is not always perfect: An investigation of sam on different real-world applications. Machine Intelligence Research21(4), 617–630 (2024)

    2024

  23. [23]

    Advances in Neural Information Processing Systems37, 76177–76209 (2024)

    Jiang, D., Song, G., Wu, X., Zhang, R., Shen, D., Zong, Z., Liu, Y., Li, H.: Comat: Aligning text-to- image diffusion model with image-to-text concept matching. Advances in Neural Information Processing Systems37, 76177–76209 (2024)

    2024

  24. [24]

    In: 2012 15th International Conference on Information Fusion

    Jøsang, A., Hankin, R.: Interpretation and fusion of hyper opinions in subjective logic. In: 2012 15th International Conference on Information Fusion. pp. 1225–1232 (2012)

    2012

  25. [25]

    Jsang,A.:SubjectiveLogic:Aformalismforreasoningunderuncertainty.SpringerPublishingCompany, Incorporated (2018)

    2018

  26. [26]

    arXiv preprint arXiv:2512.16853 , year=

    Kamath, A., Chang, K.W., Krishna, R., Zettlemoyer, L., Hu, Y., Ghazvininejad, M.: Geneval 2: Ad- dressing benchmark drift in text-to-image evaluation. arXiv preprint arXiv:2512.16853 (2025)

    work page arXiv 2025

  27. [27]

    In: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

    Kang, W., Galim, K., Koo, H.I., Cho, N.I.: Counting guidance for high fidelity text-to-image synthesis. In: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). pp. 899–908. IEEE (2025)

    2025

  28. [28]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Ke, L., Tai, Y.W., Tang, C.K.: Deep occlusion-aware instance segmentation with overlapping bilayers. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 4019– 4028 (2021)

    2021

  29. [29]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Kim, J., Esmaeili, E., Qiu, Q.: Text embedding is not all you need: Attention control for text-to-image semantic alignment with text self-attention maps. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 8031–8040 (2025)

    2025

  30. [30]

    Auto-Encoding Variational Bayes

    Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)

    work page internal anchor Pith review Pith/arXiv arXiv 2013

  31. [31]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et al.: Segment anything. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 4015–4026 (2023)

    2023

  32. [32]

    Kopetzki, A.K., Charpentier, B., Zügner, D., Giri, S., Günnemann, S.: Evaluating robustness of pre- dictive uncertainty estimation: Are dirichlet-based models reliable? In: International Conference on Machine Learning. pp. 5707–5718 (2021)

    2021

  33. [33]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recogni- tion

    Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to- image diffusion. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recogni- tion. pp. 1931–1941 (2023)

    1931

  34. [34]

    arXiv preprint arXiv:2210.16056 (2022)

    Liew, J.H., Yan, H., Zhou, D., Feng, J.: Magicmix: Semantic mixing with diffusion models. arXiv preprint arXiv:2210.16056 (2022)

    work page arXiv 2022

  35. [35]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Lin, C.H., Gao, J., Tang, L., Takikawa, T., Zeng, X., Huang, X., Kreis, K., Fidler, S., Liu, M.Y., Lin, T.Y.: Magic3d: High-resolution text-to-3d content creation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 300–309 (2023)

    2023

  36. [36]

    In: European conference on computer vision

    Lin,T.Y.,Maire,M.,Belongie,S.,Hays,J.,Perona,P.,Ramanan,D.,Dollár,P.,Zitnick,C.L.:Microsoft coco: Common objects in context. In: European conference on computer vision. pp. 740–755 (2014)

    2014

  37. [37]

    Transactions of the Association for Compu- tational Linguistics11, 635–651 (2023)

    Liu, F., Emerson, G., Collier, N.: Visual spatial reasoning. Transactions of the Association for Compu- tational Linguistics11, 635–651 (2023)

    2023

  38. [38]

    In: European conference on computer vision

    Liu,N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: European conference on computer vision. pp. 423–439 (2022)

    2022

  39. [39]

    In: European conference on computer vision

    Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Jiang, Q., Li, C., Yang, J., Su, H., et al.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In: European conference on computer vision. pp. 38–55 (2024) 16 Q. Pan et al

    2024

  40. [40]

    In: European conference on computer vision

    Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Jiang, Q., Li, C., Yang, J., Su, H., et al.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In: European conference on computer vision. pp. 38–55. Springer (2024)

    2024

  41. [41]

    Loshchilov,I.,Hutter,F.:Decoupledweightdecayregularization.In:InternationalConferenceonLearn- ing Representations

  42. [42]

    In: Proceedings of the AAAI conference on artificial intelligence

    Ma, W.D.K., Lahiri, A., Lewis, J.P., Leung, T., Kleijn, W.B.: Directed diffusion: Direct control of object placement through attention guidance. In: Proceedings of the AAAI conference on artificial intelligence. vol. 38, pp. 4098–4106 (2024)

    2024

  43. [43]

    Advances in neural infor- mation processing systems31(2018)

    Malinin, A., Gales, M.: Predictive uncertainty estimation via prior networks. Advances in neural infor- mation processing systems31(2018)

    2018

  44. [44]

    Advances in Neural Information Processing Systems36, 72983–73007 (2023)

    Minderer, M., Gritsenko, A., Houlsby, N.: Scaling open-vocabulary object detection. Advances in Neural Information Processing Systems36, 72983–73007 (2023)

    2023

  45. [45]

    IEEE Transactions on Medical Imaging45(4), 1369–1382 (2025)

    Pan, Q., Li, Z., Yang, G., Yang, Q., Ji, B.: Evivlm: When evidential learning meets vision language model for medical image segmentation. IEEE Transactions on Medical Imaging45(4), 1369–1382 (2025)

    2025

  46. [46]

    In: Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Pandey, D.S., Yu, Q.: Multidimensional belief quantification for label-efficient meta-learning. In: Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 14391–14400 (2022)

    2022

  47. [47]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Pandey, D.S., Yu, Q.: Evidential conditional neural processes. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 37, pp. 9389–9397 (2023)

    2023

  48. [48]

    In: International Conference on Learning Representations

    Park, D., Kim, S., Moon, T., Kim, M., Lee, K., Cho, J.: Rare-to-frequent: Unlocking compositional generation power of diffusion models on rare concepts with llm guidance. In: International Conference on Learning Representations

  49. [49]

    In: Proceedings of the IEEE international conference on computer vision

    Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k en- tities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE international conference on computer vision. pp. 2641–2649 (2015)

    2015

  50. [50]

    In: The Twelfth Interna- tional Conference on Learning Representations

    Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., Müller, J., Penna, J., Rombach, R.: Sdxl: Improving latent diffusion models for high-resolution image synthesis. In: The Twelfth Interna- tional Conference on Learning Representations

  51. [51]

    SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

    Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., Müller, J., Penna, J., Rom- bach, R.: Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  52. [52]

    In: The Eleventh International Conference on Learning Representations

    Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: Text-to-3d using 2d diffusion. In: The Eleventh International Conference on Learning Representations

  53. [53]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Qiu,W.,Wang,J.,Tang,M.:Self-crossdiffusionguidancefortext-to-imagesynthesisofsimilarsubjects. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 23528–23538 (2025)

    2025

  54. [54]

    In: Inter- national conference on machine learning

    Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.: Learning transferable visual models from natural language supervision. In: Inter- national conference on machine learning. pp. 8748–8763 (2021)

    2021

  55. [55]

    Hierarchical Text-Conditional Image Generation with CLIP Latents

    Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  56. [57]

    Advances in Neural Information Processing Systems36, 3536–3559 (2023)

    Rassin, R., Hirsch, E., Glickman, D., Ravfogel, S., Goldberg, Y., Chechik, G.: Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment. Advances in Neural Information Processing Systems36, 3536–3559 (2023)

    2023

  57. [58]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 10684–10695 (2022)

    2022

  58. [59]

    In: International Conference on Medical image computing and computer-assisted intervention

    Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmen- tation. In: International Conference on Medical image computing and computer-assisted intervention. pp. 234–241 (2015) ELDiff 17

    2015

  59. [60]

    Advances in neural information processing systems35, 36479–36494 (2022)

    Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems35, 36479–36494 (2022)

    2022

  60. [61]

    Advances in neural information processing systems31(2018)

    Sensoy, M., Kaplan, L., Kandemir, M.: Evidential deep learning to quantify classification uncertainty. Advances in neural information processing systems31(2018)

    2018

  61. [62]

    Sentz, K., Ferson, S.: Combination of evidence in dempster-shafer theory (2002)

    2002

  62. [63]

    Advances in neural information processing systems33, 17247–17257 (2020)

    Shi,W.,Zhao,X.,Chen,F.,Yu,Q.:Multifaceteduncertaintyestimationforlabel-efficientdeeplearning. Advances in neural information processing systems33, 17247–17257 (2020)

    2020

  63. [64]

    In: The Eleventh International Conference on Learning Representations

    Singer, U., Polyak, A., Hayes, T., Yin, X., An, J., Zhang, S., Hu, Q., Yang, H., Ashual, O., Gafni, O., et al.: Make-a-video: Text-to-video generation without text-video data. In: The Eleventh International Conference on Learning Representations

  64. [65]

    arXiv preprint arXiv:2311.17946 (2023)

    Sun, J., Fu, D., Hu, Y., Wang, S., Rassin, R., Juan, D.C., Alon, D., Herrmann, C., Van Steenkiste, S., Krishna, R., et al.: Dreamsync: Aligning text-to-image generation with image understanding feedback. arXiv preprint arXiv:2311.17946 (2023)

    work page arXiv 2023

  65. [66]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Tomani, C., Buettner, F.: Towards trustworthy predictions from deep neural networks with fast ad- versarial calibration. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 35, pp. 9886–9896 (2021)

    2021

  66. [67]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Wang, Z., Sha, Z., Ding, Z., Wang, Y., Tu, Z.: Tokencompose: Text-to-image diffusion with token- level supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 8553–8564 (2024)

    2024

  67. [68]

    Qwen-Image Technical Report

    Wu, C., Li, J., Zhou, J., Lin, J., Gao, K., Yan, K., Yin, S.m., Bai, S., Xu, X., Chen, Y., et al.: Qwen- image technical report. arXiv preprint arXiv:2508.02324 (2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  68. [69]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Wu, T.H., Lian, L., Gonzalez, J.E., Li, B., Darrell, T.: Self-correcting llm-controlled diffusion models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6327–6336 (2024)

    2024

  69. [70]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Xu, Y., Zhao, Y., Xiao, Z., Hou, T.: Ufogen: You forward once large scale text-to-image generation via diffusion gans. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 8196–8206 (2024)

    2024

  70. [71]

    Advances in Neural Information Processing Systems36, 41693–41706 (2023)

    Xue, Z., Song, G., Guo, Q., Liu, B., Zong, Z., Liu, Y., Luo, P.: Raphael: Text-to-image generation via large mixture of diffusion paths. Advances in Neural Information Processing Systems36, 41693–41706 (2023)

    2023

  71. [72]

    Advances in Neural Information Processing Systems36, 37636–37656 (2023)

    Yang, L., Liu, J., Hong, S., Zhang, Z., Huang, Z., Cai, Z., Zhang, W., Cui, B.: Improving diffusion- based image synthesis with context prediction. Advances in Neural Information Processing Systems36, 37636–37656 (2023)

    2023

  72. [73]

    In: International Conference on Learning Representations

    Zhang, X., Yang, L., Li, G., Cai, Y., Xie, J., Tang, Y., Yang, Y., Wang, M., Cui, B.: Itercomp: Iterative composition-aware feedback learning from model gallery for text-to-image generation. In: International Conference on Learning Representations. pp. 8608–8628 (2025)

    2025

  73. [74]

    Advances in Neural Information Processing Systems36, 30641–30661 (2023)

    Zhang, Y., Xing, J., Lo, E., Jia, J.: Real-world image variation by aligning diffusion inversion chain. Advances in Neural Information Processing Systems36, 30641–30661 (2023)

    2023

  74. [75]

    Advances in neural information processing systems33, 12827–12836 (2020)

    Zhao, X., Chen, F., Hu, S., Cho, J.H.: Uncertainty aware semi-supervised learning on graph data. Advances in neural information processing systems33, 12827–12836 (2020)

    2020

  75. [76]

    Neurocomputing p

    Zhong, J., Pan, Q., Zhou, X., Lin, J., Zhuang, X.: Evidential learning driven breast tumor segmentation with stage-divided vision-language interaction. Neurocomputing p. 132411 (2025)

    2025

  76. [77]

    <A><R><B>,

    Zhou, Y., Zhou, D., Wang, Y., Feng, J., Hou, Q.: Maskdiffusion: Boosting text-to-image consistency with conditional mask. International Journal of Computer Vision133(5), 2805–2824 (2025) 18 Q. Pan et al. Appendix This supplementary material contains several sections that provide additional details related to our work on ELDiff. Specifically, it will cover...

    2025

  77. [78]

    is used to assess the quality of the generated images from two datasets: i) 25014 image-caption pairs sampled from the COCO instance validation set; ii) 5000 image-caption pairs sampled from the Flickr30K instance validation set [49].4) CLIP Score[33] is utilized to evaluate realism, which reflects the degree of match between generated images and text pro...