Unleashing Text-to-Image Diffusion Models for Visual Perception
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
Diffusion models (DMs) have become the new trend of generative models and have demonstrated a powerful ability of conditional synthesis. Among those, text-to-image diffusion models pre-trained on large-scale image-text pairs are highly controllable by customizable prompts. Unlike the unconditional generative models that focus on low-level attributes and details, text-to-image diffusion models contain more high-level knowledge thanks to the vision-language pre-training. In this paper, we propose VPD (Visual Perception with pre-trained Diffusion models), a new framework that exploits the semantic information of a pre-trained text-to-image diffusion model in visual perception tasks. Instead of using the pre-trained denoising autoencoder in a diffusion-based pipeline, we simply use it as a backbone and aim to study how to take full advantage of the learned knowledge. Specifically, we prompt the denoising decoder with proper textual inputs and refine the text features with an adapter, leading to a better alignment to the pre-trained stage and making the visual contents interact with the text prompts. We also propose to utilize the cross-attention maps between the visual features and the text features to provide explicit guidance. Compared with other pre-training methods, we show that vision-language pre-trained diffusion models can be faster adapted to downstream visual perception tasks using the proposed VPD. Extensive experiments on semantic segmentation, referring image segmentation, and depth estimation demonstrate the effectiveness of our method. Notably, VPD attains 0.254 RMSE on NYUv2 depth estimation and 73.3% oIoU on RefCOCO-val referring image segmentation, establishing new records on these two benchmarks. Code is available at https://github.com/wl-zhao/VPD.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Self-citationHigh-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00371 · Cited by 11,953
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489
Indoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · cited 2×
“Besides, self-supervised learning such as contrastive learning [7, 18] and masked image modeling [40, 17] have also proved to be able to learn transferrable representations.”
BackgroundMethodLearning to Prompt for Vision-Language Models
Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01653-1 · Cited by 3,304 · cited 1×
“However, the domain gap is usually witnessed when transferring the text encoder to downstream tasks [61, 15].”
BackgroundSelf-citationSwin Transformer V2: Scaling Up Capacity and Resolution
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.09883 · Cited by 2,679
Self-citationDeep Unsupervised Learning using Nonequilibrium Thermodynamics
Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015) · arXiv · doi:10.48550/arxiv.1503.03585 · Cited by 2,637 · cited 2×
“To begin with, we will provide a brief overview of the diffusion models [50, 20, 22].”
BackgroundPhotorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, S. K. S., Ayan, B. K., Mahdavi, S. S., Lopes, R. G., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.11487 · Cited by 2,528 · cited 1×
“We also believe that text-guided generative models other than diffusion models[47, 42, 8] can also fit in VPD, which we leave to future work.”
BackgroundHierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511 · cited 2×
“We also believe that text-guided generative models other than diffusion models[47, 42, 8] can also fit in VPD, which we leave to future work.”
BackgroundDenoising Diffusion Implicit Models
Song, J., Meng, C., & Ermon, S. (2020) · arXiv · doi:10.48550/arxiv.2010.02502 · Cited by 2,507
Vision Transformers for Dense Prediction
Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01196 · Cited by 2,373 · cited 1×
“The compared methods include self-supervised pre-training (MAE [17]) and supervised pre-training (Swin [30] and ConvNeXt [31]).”
MethodUnified Perceptual Parsing for Scene Understanding
Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_26 · Cited by 2,201
Score-Based Generative Modeling through Stochastic Differential Equations
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2020) · arXiv · doi:10.48550/arxiv.2011.13456 · Cited by 1,953 · cited 2×
“The sampling of diffusion models is achieved by discretizing the diffusion SDE or ODE [52] thus requires multiple model evaluations at different timesteps.”
BackgroundMethodInstructpix2pix: Learning to follow image editing instructions
Brooks, T., Holynski, A., & Efros, A. A. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01764 · Cited by 1,466 · cited 1×
“verse and high-fidelity images with high customizability [43, 19, 36, 6], attracting growing attention from both the research community and the public eye.”
Background(2016) · doi:10.1007/978-3-319-46475-6_5 · Cited by 1,081
LAION-5B: An open large-scale dataset for training next generation image-text models
Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.08402 · Cited by 1,022
Li, J., Li, D., Savarese, S., & Hoi, S. (2023) · arXiv · doi:10.48550/arxiv.2301.12597 · Cited by 908 · cited 2×
“5 [45] SAM [25] BLIP [27] RMSE ( ↓ ) 0.254 0.317 0.368 affect the performance of our VPD.”
BackgroundMethodInfluentialHigh-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021) · arXiv · doi:10.48550/arxiv.2112.10752 · Cited by 737
DiffusionDet: Diffusion Model for Object Detection
Chen, S., Sun, P., Song, Y., & Luo, P. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01816 · Cited by 657 · cited 1×
“Different from previous diffusion-based framework [9, 1] that reformulate the visual perception task as progressive denoising, we employ the denoising autoencoder pre-trained on the text-to-image generation as a backbone and study how to make full use of the learned highlevel and low-level knowledge, which only requir…”
MethodFrom Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
Lee, J. H., Han, M.-K., Ko, D. W., & Suh, I. H. (2019) · arXiv · doi:10.48550/arxiv.1907.10326 · Cited by 507
Kingma, D. P., Salimans, T., Poole, B., & Ho, J. (2021) · arXiv · doi:10.48550/arxiv.2107.00630 · Cited by 374
ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
Bhat, S. F., Birkl, R., Wofk, D., Wonka, P., & Müller, M. (2023) · arXiv · doi:10.48550/arxiv.2302.12288 · Cited by 242 · cited 4×
“For example, training a ConvNeXt-XL requires 47h (160K iters) while our VPD trained for only 26h (80K iters) still performs better.”
MethodInfluentialSegDiff: Image Segmentation with Diffusion Probabilistic Models
Amit, T., Shaharbany, T., Nachmani, E., & Wolf, L. (2021) · arXiv · doi:10.48550/arxiv.2112.00390 · Cited by 179
Muse: Text-To-Image Generation via Masked Generative Transformers
Chang, H., Zhang, H., Barber, J., Maschinot, A., Lezama, J., Jiang, L., Yang, M.-H., Murphy, K., Freeman, W. T., Rubinstein, M., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.00704 · Cited by 157
Cited by
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., & Zhao, H. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00987 · Cited by 1,296
“As shown in Table 3 of NYUv2 [54], our model outperforms the previous best method VPD [86] remarkably, improving the δ 1 ( ↑ ) from 0.964 → 0.984 and AbsRel ( ↓ ) from 0.069 to 0.056.”
MethodInfluentialRepurposing Diffusion-Based Image Generators for Monocular Depth Estimation
Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R. C., & Schindler, K. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00907 · Cited by 412
Diffusion Model as Representation Learner
Yang, X., & Wang, X. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01736 · Cited by 58
Probing the 3D Awareness of Visual Foundation Models
Banani, M. E., Raj, A., Maninis, K.-K., Kar, A., Li, Y., Rubinstein, M., Sun, D., Guibas, L., Johnson, J., & Jampani, V. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02059 · Cited by 52
Metadata
- Authors
- Zhao, W., Rao, Y., Liu, Z., Liu, B., Zhou, J., & Lu, J.
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 5706-5716
- OpenAlex
- W4390873429
- Cited by
- 175
- References
- 31
- FWCI
- 19.90
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.