Elamur Research⌕
☰
home / papers / 2023 / T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation

T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation

Paper · 2023 · Kaiyi Huang, Chengqi Duan, Kaiyue Sun et al.

Summary

Text-to-image models produce convincing pictures but often fail when a prompt combines several objects with distinct attributes, relations, or counts. Earlier benchmarks each addressed a narrow slice of this problem, usually color binding, and relied on CLIPScore- or BLIP-style similarity, which judges compositional correctness poorly. The authors build T2I-CompBench++, a set of 8,000 prompts organized into four groups: tying attributes to the right objects, depicting how objects relate to one another, generating the correct number of objects, and handling complex compositions. These split into eight sub-categories. The work extends an earlier conference version with numeracy and 3D-spatial relations.

They pair each category with a suited metric:

  • Disentangled BLIP-VQA for attributes.
  • A UniDet detector, combined with depth estimation, for 2D/3D layout and counting.
  • MLLM judges (ShareGPT4V, GPT-4V) for non-spatial and complex prompts.

They also introduce GORS, which fine-tunes Stable Diffusion v2 on its own well-aligned samples, weighting the loss by an alignment reward. The metrics agree with human ratings, and GORS beats its baselines. Across 11 tested models, compositional prompts remain hard even for leading systems, which gives a common yardstick for future work.

Key points

  • Prompt split: 3,000 attribute binding (color/shape/texture), 3,000 relationships (2D-spatial, 3D-spatial, non-spatial), 1,000 numeracy (quantities 1–8), and 1,000 complex prompts.
  • Vocabulary: 2,470 nouns, 33 colors, 32 shapes, 23 textures, 7 2D-spatial, 3 3D-spatial, and 875 non-spatial relation types. This is broader than CC-500, ABC-6K, Attn-Exct, and HRS-comp.
  • Benchmarked models: 11 in total, including FLUX.1, SD3, DALLE-3, Pixart-α, and SD-XL. The authors also check how stable MLLM-based scoring is across repeated runs.
  • GORS (Generative mOdel finetuning with Reward-driven Sample selection) needs no repeated generate-and-select rounds, unlike RAFT. It still handles long prompts well after fine-tuning.
  • Prompt detail did not fix the failures: GPT-4 rewrites that lengthened prompts from about 8.21 to 24.00 words did not noticeably reduce compositional errors.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of Hong KongPok Fu Lam · China127 works · 13,824 citations🏢Huawei Technologies (Canada)Markham · Canada4 works · 307 citations

 Fields, topics and concepts

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 19,503 worksComputer Vision and Pattern Recognition · 3,621 works

🧭 Topics 2Research subjects and languages the work is about.Evaluation & benchmarks · 1,394 worksVision & language · 827 works

Cite

Cite as Kaiyi Huang, Chengqi Duan, Kaiyue Sun, Enze Xie, Zhenguo Li and Xihui Liu. 2023. T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation. arXiv:2307.06350.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2307.06350 · arXiv 2307.06350

@misc{huang2023t2i,
  title = {{T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation}},
  author = {Kaiyi Huang, Chengqi Duan, Kaiyue Sun, Enze Xie, Zhenguo Li and Xihui Liu},
  year = {2023},
  doi = {10.48550/arxiv.2307.06350},
  eprint = {2307.06350},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2307.06350}
}

References

90 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, “High-resolution image synthesis with latent diffusion models,” in CVPR, 2022.
  2. J. Ho, C. Saharia, W. Chan, D. J. Fleet, M. Norouzi, and T. Salimans, “Cascaded diffusion models for high fidelity image generation,” The Journal of Machine Learning Research, 2022. find
  3. C. Saharia, W. Chan, S. Saxena, L. Li, J. Whang, E. L. Denton, K. Ghasemipour, R. Gontijo Lopes, B. Karagol Ayan, T. Salimans et al., “Photorealistic text-to-image diffusion models with deep language understanding,” in NeurIPS, 2022.
  4. P. Dhariwal and A. Nichol, “Diffusion models beat gans on image synthesis,” in NeurIPS, 2021. find
  5. A. Q. Nichol and P. Dhariwal, “Improved denoising diffusion probabilistic models,” ICLR, 2021. find
  6. H. Chang, H. Zhang, J. Barber, A. Maschinot, J. Lezama, L. Jiang, M.-H. Yang, K. Murphy, W. T. Freeman, M. Rubinstein et al., “Muse: Text-to-image generation via masked generative transformers,” arXiv preprint arXiv:2301.00704, 2023. — [arXiv:2301.00704](https://arxiv.org/abs/2301.00704) find
  7. N. Liu, S. Li, Y. Du, A. Torralba, and J. B. Tenenbaum, “Compositional visual generation with composable diffusion models,” in ECCV, 2022. find
  8. W. Feng, X. He, T.-J. Fu, V. Jampani, A. Akula, P. Narayana, S. Basu, X. E. Wang, and W. Y. Wang, “Training-free structured diffusion guidance for compositional text-to-image synthesis,” in ICLR, 2023. find
  9. H. Chefer, Y. Alaluf, Y. Vinker, L. Wolf, and D. Cohen-Or, “Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models,” in ACM Trans. Graph., 2023. TABLE XIX: Ablation studies on fine-tuning strategy and threshold. Metric FT U-Net only FT CLIP only B-VQA 0.6216 0.5507 A… find
  10. Q. Wu, Y. Liu, H. Zhao, T. Bui, Z. Lin, Y. Zhang, and S. Chang, “Harnessing the spatial-temporal attention of diffusion models for high-fidelity text-to-image synthesis,” in ICCV, 2023. find
  11. A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark et al., “Learning transferable visual models from natural language supervision,” in ICML, 2021.
  12. J. Hessel, A. Holtzman, M. Forbes, R. L. Bras, and Y. Choi, “Clipscore: A reference-free evaluation metric for image captioning,” arXiv preprint arXiv:2104.08718, 2021.
  13. J. Li, D. Li, C. Xiong, and S. Hoi, “Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation,” in ICML, 2022.
  14. J. Li, D. Li, S. Savarese, and S. Hoi, “Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,” arXiv preprint arXiv:2301.12597, 2023.
  15. L. Chen, J. Li, X. Dong, P. Zhang, C. He, J. Wang, F. Zhao, and D. Lin, “Sharegpt4v: Improving large multi-modal models with better captions,” arXiv preprint arXiv:2311.12793, 2023.
  16. Z. Yang, L. Li, K. Lin, J. Wang, C.-C. Lin, Z. Liu, and L. Wang, “The dawn of lmms: Preliminary explorations with gpt-4v (ision),” arXiv preprint arXiv:2309.17421, vol. 9, no. 1, p. 1, 2023.
  17. B. F. Labs, https://github.com/black-forest-labs/flux, 2024. ↗
  18. P. Esser, S. Kulal, A. Blattmann, R. Entezari, J. Müller, H. Saini, Y. Levi, D. Lorenz, A. Sauer, F. Boesel, D. Podell, T. Dockhorn, Z. English, K. Lacey, A. Goodwin, Y. Marek, and R. Rombach, “Scaling rectified flow transformers for high-resolution image synthesis,” 2024. find
  19. J. Betker, G. Goh, L. Jing, T. Brooks, J. Wang, L. Li, L. Ouyang, J. Zhuang, J. Lee, Y. Guo et al., “Improving image generation with better captions,” Computer Science. https://cdn.openai. com/papers/dall-e-3. pdf, vol. 2, no. 3, p. 8, 2023. ↗
  20. J. Chen, J. Yu, C. Ge, L. Yao, E. Xie, Y. Wu, Z. Wang, J. Kwok, P. Luo, H. Lu et al., “Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis,” in ICLR, 2024. — PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
  21. D. Podell, Z. English, K. Lacey, A. Blattmann, T. Dockhorn, J. Müller, J. Penna, and R. Rombach, “Sdxl: Improving latent diffusion models for high-resolution image synthesis,” arXiv preprint arXiv:2307.01952, 2023.
  22. K. Huang, K. Sun, E. Xie, Z. Li, and X. Liu, “T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation,” NeurIPS, 2024. Half threshold 0 threshold GORS (ours) 0.6570 0.6157 0.6130 A round muffin and a square napkin GORS (ours) FT U-Net only FT CLIP only Half thr… find
  23. E. M. Bakr, P. Sun, X. Shen, F. F. Khan, L. E. Li, and M. Elhoseiny, “Hrs-bench: Holistic, reliable and scalable benchmark for text-to-image models,” in ICCV, 2023. find
  24. S. Reed, Z. Akata, X. Yan, L. Logeswaran, B. Schiele, and H. Lee, “Generative adversarial text to image synthesis,” in ICML, 2016. find
  25. S. E. Reed, Z. Akata, S. Mohan, S. Tenka, B. Schiele, and H. Lee, “Learning what and where to draw,” in NeurIPS, 2016. find
  26. H. Zhang, T. Xu, H. Li, S. Zhang, X. Huang, X. Wang, and D. Metaxas, “Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks,” in ICCV, 2017. find
  27. T. Xu, P. Zhang, Q. Huang, H. Zhang, Z. Gan, X. Huang, and X. He, “Attngan: Fine-grained text to image generation with attentional generative adversarial networks,” in CVPR, 2018. find
  28. M. Zhu, P. Pan, W. Chen, and Y. Yang, “Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis,” in CVPR, 2019. find
  29. H. Zhang, J. Y. Koh, J. Baldridge, H. Lee, and Y. Yang, “Cross-modal contrastive learning for text-to-image generation,” in CVPR, 2021. find
  30. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” in NeurIPS, 2014.
  31. A. Ramesh, P. Dhariwal, A. Nichol, C. Chu, and M. Chen, “Hierarchical text-conditional image generation with clip latents,” arXiv preprint arXiv:2204.06125, 2022.
  32. A. Nichol, P. Dhariwal, A. Ramesh, P. Shyam, P. Mishkin, B. McGrew, I. Sutskever, and M. Chen, “Glide: Towards photorealistic image generation and editing with text-guided diffusion models,” in ICML, 2022. find
  33. C. Saharia, W. Chan, S. Saxena, L. Li, J. Whang, E. L. Denton, K. Ghasemipour, R. Gontijo Lopes, B. Karagol Ayan, T. Salimans et al., “Photorealistic text-to-image diffusion models with deep language understanding,” in NeurIPS, 2022.
  34. O. Gafni, A. Polyak, O. Ashual, S. Sheynin, D. Parikh, and Y. Taigman, “Make-a-scene: Scene-based text-to-image generation with human priors,” in ECCV, 2022. find
  35. J. Gu, S. Zhai, Y. Zhang, J. M. Susskind, and N. Jaitly, “Matryoshka diffusion models,” 2023. find
  36. A. Ramesh, M. Pavlov, G. Goh, S. Gray, C. Voss, A. Radford, M. Chen, and I. Sutskever, “Zero-shot text-to-image generation,” in ICML, 2021.
  37. S. Zhang, X. Yang, Y. Feng, C. Qin, C.-C. Chen, N. Yu, Z. Chen, H. Wang, S. Savarese, S. Ermon et al., “Hive: Harnessing human feedback for instructional visual editing,” arXiv preprint arXiv:2303.09618, 2023. find
  38. K. Lee, H. Liu, M. Ryu, O. Watkins, Y. Du, C. Boutilier, P. Abbeel, M. Ghavamzadeh, and S. S. Gu, “Aligning text-to-image models using human feedback,” arXiv preprint arXiv:2302.12192, 2023. — [arXiv:2302.12192](https://arxiv.org/abs/2302.12192) find
  39. H. Dong, W. Xiong, D. Goyal, R. Pan, S. Diao, J. Zhang, K. Shum, and T. Zhang, “Raft: Reward ranked finetuning for generative foundation model alignment,” arXiv preprint arXiv:2304.06767, 2023.
  40. Z. Li, M. R. Min, K. Li, and C. Xu, “Stylet2i: Toward compositional and high-fidelity text-to-image synthesis,” in CVPR, 2022. find
  41. M. Patel, C. Kim, S. Cheng, C. Baral, and Y. Yang, “Eclipse: A resource-efficient text-to-image prior for image generations,” arXiv preprint arXiv:2312.04655, 2023. — [arXiv:2312.04655](https://arxiv.org/abs/2312.04655) find
  42. X. Liu, T. Hu, W. Wang, K. Kawaguchi, and Y. Yao, “Referee can play: An alternative approach to conditional generation via model inversion,” arXiv preprint arXiv:2402.16305, 2024. — [arXiv:2402.16305](https://arxiv.org/abs/2402.16305) find
  43. D. H. Park, S. Azadi, X. Liu, T. Darrell, and A. Rohrbach, “Benchmark for compositional text-to-image synthesis,” in NeurIPS, 2021. find
  44. L. Lian, B. Li, A. Yala, and T. Darrell, “Llm-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models,” arXiv preprint arXiv:2305.13655, 2023. find
  45. M. Chen, I. Laina, and A. Vedaldi, “Training-free layout control with cross-attention guidance,” in WACV, 2024. find
  46. R. Wang, Z. Chen, C. Chen, J. Ma, H. Lu, and X. Lin, “Compositional text-to-image synthesis with attention map control of diffusion models,” arXiv preprint arXiv:2305.13921, 2023. — [arXiv:2305.13921](https://arxiv.org/abs/2305.13921) find
  47. T. H. S. Meral, E. Simsar, F. Tombari, and P. Yanardag, “Conform: Contrast is all you need for high-fidelity text-to-image diffusion models,” arXiv preprint arXiv:2312.06059, 2023. — [arXiv:2312.06059](https://arxiv.org/abs/2312.06059) find
  48. Y. Kim, J. Lee, J.-H. Kim, J.-W. Ha, and J.-Y. Zhu, “Dense text-to-image generation with attention modulation,” 2023. find
  49. R. Rassin, E. Hirsch, D. Glickman, S. Ravfogel, Y. Goldberg, and G. Chechik, “Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment,” NeurIPS, 2024. find
  50. H. Gani, S. F. Bhat, M. Naseer, S. Khan, and P. Wonka, “Llm blueprint: Enabling text-to-image generation with complex and detailed prompts,” arXiv preprint arXiv:2310.10640, 2023. — [arXiv:2310.10640](https://arxiv.org/abs/2310.10640) find
  51. Y. Li, H. Liu, Q. Wu, F. Mu, J. Yang, J. Gao, C. Li, and Y. J. Lee, “Gligen: Open-set grounded text-to-image generation,” in ICCV, 2023. find
  52. A. Taghipour, M. Ghahremani, M. Bennamoun, A. M. Rekavandi, H. Laga, and F. Boussaid, “Box it to bind it: Unified layout control and attribute binding in t2i diffusion models,” arXiv preprint arXiv:2402.17910, 2024. — [arXiv:2402.17910](https://arxiv.org/abs/2402.17910) find
  53. Z. Wang, E. Xie, A. Li, Z. Wang, X. Liu, and Z. Li, “Divide and conquer: Language models can plan and self-correct for compositional text-to-image generation,” arXiv preprint arXiv:2401.15688, 2024. — [arXiv:2401.15688](https://arxiv.org/abs/2401.15688) find
  54. X. Chen, Y. Liu, Y. Yang, J. Yuan, Q. You, L.-P. Liu, and H. Yang, “Reason out your layout: Evoking the layout master from large language models for text-to-image synthesis,” arXiv preprint arXiv:2311.17126, 2023. — [arXiv:2311.17126](https://arxiv.org/abs/2311.17126) find
  55. L. Yang, Z. Yu, C. Meng, M. Xu, S. Ermon, and B. Cui, “Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal llms,” arXiv preprint arXiv:2401.11708, 2024. find
  56. X. Zhang, L. Yang, Y. Cai, Z. Yu, J. Xie, Y. Tian, M. Xu, Y. Tang, Y. Yang, and B. Cui, “Realcompo: Dynamic equilibrium between realism and compositionality improves text-to-image diffusion models,” arXiv preprint arXiv:2402.12908, 2024. — [arXiv:2402.12908](https://arxiv.org/abs/2402.12908) find
  57. C. Wah, S. Branson, P. Welinder, P. Perona, and S. Belongie, “The caltech-ucsd birds-200-2011 dataset,” 2011. find
  58. M.-E. Nilsback and A. Zisserman, “Automated flower classification over a large number of classes,” in ICVGIP, 2008. find
  59. T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft coco: Common objects in context,” in ECCV, 2014.
  60. J. Cho, A. Zala, and M. Bansal, “Dall-eval: Probing the reasoning skills and social biases of text-to-image generation models,” in ICCV, 2023. find
  61. V. Petsiuk, A. E. Siemenn, S. Surbehera, Z. Chin, K. Tyser, G. Hunter, A. Raghavan, Y. Hicke, B. A. Plummer, O. Kerret et al., “Human evaluation of text-to-image models on a multi-task benchmark,” arXiv preprint arXiv:2211.12112, 2022. — [arXiv:2211.12112](https://arxiv.org/abs/2211.12112) find
  62. T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, “Improved techniques for training gans,” in NeurIPS, 2016.
  63. M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, “Gans trained by a two time-scale update rule converge to a local nash equilibrium,” in NeurIPS, 2017. find
  64. Y. Lu, X. Yang, X. Li, X. E. Wang, and W. Y. Wang, “Llmscore: Unveiling the power of large language models in text-to-image synthesis evaluation,” arXiv preprint arXiv:2305.11116, 2023. — [arXiv:2305.11116](https://arxiv.org/abs/2305.11116) find
  65. Y. Chen, “X-iqe: explainable image quality evaluation for text-to-image generation with visual large language models,” arXiv preprint arXiv:2305.10843, 2023. — [arXiv:2305.10843](https://arxiv.org/abs/2305.10843) find
  66. S. Wen, G. Fang, R. Zhang, P. Gao, H. Dong, and D. Metaxas, “Improving compositional text-to-image generation with large vision-language models,” arXiv preprint arXiv:2310.06311, 2023. — [arXiv:2310.06311](https://arxiv.org/abs/2310.06311) find
  67. J. Xu, X. Liu, Y. Wu, Y. Tong, Q. Li, M. Ding, J. Tang, and Y. Dong, “Imagereward: Learning and evaluating human preferences for text-to-image generation,” 2023. find
  68. J. Sun, D. Fu, Y. Hu, S. Wang, R. Rassin, D.-C. Juan, D. Alon, C. Herrmann, S. van Steenkiste, R. Krishna et al., “Dreamsync: Aligning text-to-image generation with image understanding feedback,” arXiv preprint arXiv:2311.17946, 2023. find
  69. Y. Kirstain, A. Polyak, U. Singer, S. Matiana, J. Penna, and O. Levy, “Pick-a-pic: An open dataset of user preferences for text-to-image generation,” NeurIPS, 2024. find
  70. X. Wu, K. Sun, F. Zhu, R. Zhao, and H. Li, “Better aligning text-to-image models with human preference,” 2023. find
  71. X. Wu, Y. Hao, K. Sun, Y. Chen, F. Zhu, R. Zhao, and H. Li, “Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis,” arXiv preprint arXiv:2306.09341, 2023. — [arXiv:2306.09341](https://arxiv.org/abs/2306.09341) find
  72. Y. Liang, J. He, G. Li, P. Li, A. Klimovskiy, N. Carolan, J. Sun, J. Pont-Tuset, S. Young, F. Yang et al., “Rich human feedback for text-to-image generation,” arXiv preprint arXiv:2312.10240, 2023. — [arXiv:2312.10240](https://arxiv.org/abs/2312.10240) find
  73. M. Ku, T. Li, K. Zhang, Y. Lu, X. Fu, W. Zhuang, and W. Chen, “Imagenhub: Standardizing the evaluation of conditional image generation models,” arXiv preprint arXiv:2310.01596, 2023. — [arXiv:2310.01596](https://arxiv.org/abs/2310.01596) find
  74. M. Ku, D. Jiang, C. Wei, X. Yue, and W. Chen, “Viescore: Towards explainable metrics for conditional image synthesis evaluation,” arXiv preprint arXiv:2312.14867, 2023.
  75. T. Lee, M. Yasunaga, C. Meng, Y. Mai, J. S. Park, A. Gupta, Y. Zhang, D. Narayanan, H. Teufel, M. Bellagente et al., “Holistic evaluation of text-to-image models,” NeurIPS, 2024. find
  76. OpenAI, https://openai.com/blog/chatgpt/, 2023. ↗
  77. D. Zhu, J. Chen, X. Shen, X. Li, and M. Elhoseiny, “Minigpt-4: Enhancing vision-language understanding with advanced large language models,” arXiv preprint arXiv:2304.10592, 2023.
  78. J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V. Le, D. Zhou et al., “Chain-of-thought prompting elicits reasoning in large language models,” in NeurIPS, 2022.
  79. X. Zhou, V. Koltun, and P. Krähenbühl, “Simple multi-dataset detection,” in CVPR, 2022. find
  80. R. Ranftl, A. Bochkovskiy, and V. Koltun, “Vision transformers for dense prediction,” in ICCV, 2021. find
  81. J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat et al., “Gpt-4 technical report,” arXiv preprint arXiv:2303.08774, 2023.
  82. E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen, “Lora: Low-rank adaptation of large language models,” arXiv preprint arXiv:2106.09685, 2021.
  83. D. Teney, E. Abbasnejad, K. Kafle, R. Shrestha, C. Kanan, and A. Van Den Hengel, “On the value of out-of-distribution testing: An example of goodhart’s law,” Advances in neural information processing systems, vol. 33, pp. 407–417, 2020. find
  84. S. Liu, Z. Zeng, T. Ren, F. Li, H. Zhang, J. Yang, C. Li, J. Yang, H. Su, J. Zhu, and L. Zhang, “Grounding dino: Marrying dino with grounded pre-training for open-set object detection,” arXiv preprint arXiv:2303.05499, 2023.
  85. L. H. Li, P. Zhang, H. Zhang, J. Yang, C. Li, Y. Zhong, L. Wang, L. Yuan, L. Zhang, J.-N. Hwang et al., “Grounded language-image pre-training,” in CVPR, 2022. find
  86. S. Shao, Z. Li, T. Zhang, C. Peng, G. Yu, X. Zhang, J. Li, and J. Sun, “Objects365: A large-scale, high-quality dataset for object detection,” in ICCV, 2019. find
  87. A. Kuznetsova, H. Rom, N. Alldrin, J. Uijlings, I. Krasin, J. Pont-Tuset, S. Kamali, S. Popov, M. Malloci, A. Kolesnikov et al., “The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale,” in IJCV, 2020. find
  88. G. Neuhold, T. Ollmann, S. Rota Bulo, and P. Kontschieder, “The mapillary vistas dataset for semantic understanding of street scenes,” in ICCV, 2017. find
  89. https://github.com/huggingface/diffusers/blob/main/examples/text to image. ↗
  90. I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” in ICLR, 2018. A PPENDIX find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/huang-2023-t2i-compbench-enhanced-comprehensive-benchmark/