Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Open-vocabulary semantic segmentation aims to segment an image into semantic regions according to text descriptions, which may not have been seen during training. Recent two-stage methods first generate class-agnostic mask proposals and then leverage pre-trained vision-language models, e.g., CLIP, to classify masked regions. We identify the performance bottleneck of this paradigm to be the pre-trained CLIP model, since it does not perform well on masked images. To address this, we propose to finetune CLIP on a collection of masked image regions and their corresponding text descriptions. We collect training data by mining an existing image-caption dataset (e.g., COCO Captions), using CLIP to match masked image regions to nouns in the image captions. Compared with the more precise and manually annotated segmentation labels with fixed classes (e.g., COCO-Stuff), we find our noisy but diverse dataset can better retain CLIP's generalization ability. Along with finetuning the entire model, we utilize the “blank” areas in masked images using a method we dub mask prompt tuning. Experiments demonstrate mask prompt tuning brings significant improvement without modifying any weights of CLIP, and it can further improve a fully finetuned model. In particular, when trained on COCO and evaluated on ADE20K-150, our best model achieves 29.6% mIoU, which is +8.5% higher than the previous state-of-the-art. For the first time, open-vocabulary generalist models match the performance of supervised specialist models in 2017 without dataset specific adaptations.
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
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
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
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · arXiv · doi:10.48550/arxiv.1802.02611 · Cited by 20,063
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_49 · Cited by 20,054
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · cited 6×
“Thus, we test our model on challenging ADE20K [43], Pascal VOC [15] and Pascal Context [33] datasets.”
MethodInfluentialZhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.660 · Cited by 16,438
Cited by
Vision-Language Models for Vision Tasks: A Survey
Zhang, J., Huang, J., Jin, S., & Lu, S. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3369699 · Cited by 1,051
“OVSeg [190] [code] Adapt CLIP with the region-word pairs generated by the modified MaskFormer.”
MethodLISA: Reasoning Segmentation via Large Language Model
Lai, X., Tian, Z., Chen, Y., Li, Y., Yuan, Y., Liu, S., & Jia, J. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00915 · Cited by 466
OpenScene: 3D Scene Understanding with Open Vocabularies
Peng, S., Genova, K., Jiang, C., Tagliasacchi, A., Pollefeys, M., & Funkhouser, T. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00085 · Cited by 395
Chen, K., Liu, C., Chen, H., Zhang, H., Li, W., Zou, Z., & Shi, Z. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3356074 · Cited by 383
Self-citationLERF: Language Embedded Radiance Fields
Kerr, J., Kim, C. M., Goldberg, K., Kanazawa, A., & Tancik, M. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01807 · Cited by 370
Side Adapter Network for Open-Vocabulary Semantic Segmentation
Xu, M., Zhang, Z., Wei, F., Hu, H., & Bai, X. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00288 · Cited by 316
LangSplat: 3D Language Gaussian Splatting
Qin, M., Li, W., Zhou, J., Wang, H., & Pfister, H. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01895 · Cited by 268
ConceptFusion: Open-set Multimodal 3D Mapping
Jatavallabhula, K. M., Kuwajerwala, A., Gu, Q., Omama, M., Chen, T., Maalouf, A., Li, S., Iyer, G., Saryazdi, S., Keetha, N., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.07241 · Cited by 228
ConceptFusion: Open-set multimodal 3D mapping
Jatavallabhula, K., Kuwajerwala, A., Gu, Q., Omama, M., Iyer, G., Saryazdi, S., Chen, T., Maalouf, A., Li, S., Keetha, N., et al. (2023) · Robotics: Science and Systems XIX · doi:10.15607/rss.2023.xix.066 · Cited by 228
Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation
Werby, A., Huang, C., Büchner, M., Valada, A., & Burgard, W. (2024) · Robotics: Science and Systems XX · doi:10.15607/rss.2024.xx.077 · Cited by 124
“Previous work [48] proposed to use the CLIP feature of the masked image without background, while others [13] approach this by combining the CLIP features of the whole image and the target mask’s crop including background.”
MethodCLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP
Zhang, J., Dong, R., & Ma, K. (2023) · 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw60793.2023.00219 · Cited by 62
Expediting Large-Scale Vision Transformer for Dense Prediction Without Fine-Tuning
Yuan, Y., Liang, W., Ding, H., Liang, Z., Zhang, C., & Hu, H. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3327511 · Cited by 14
Metadata
- Authors
- Liang, F., Wu, B., Dai, X., Li, K., Zhao, Y., Zhang, H., Zhang, P., Vajda, P., & Marculescu, D.
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 7061-7070
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386075561
- Cited by
- 464
- References
- 41
- FWCI
- 52.76
- 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.