SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation

Huaishao Luo, Junwei Bao, Youzheng Wu, Xiaodong He, Tianrui Li
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23033-23044, 2023.

Abstract

Recently, the contrastive language-image pre-training, e.g., CLIP, has demonstrated promising results on various downstream tasks. The pre-trained model can capture enriched visual concepts for images by learning from a large scale of text-image data. However, transferring the learned visual knowledge to open-vocabulary semantic segmentation is still under-explored. In this paper, we propose a CLIP-based model named SegCLIP for the topic of open-vocabulary segmentation in an annotation-free manner. The SegCLIP achieves segmentation based on ViT and the main idea is to gather patches with learnable centers to semantic regions through training on text-image pairs. The gathering operation can dynamically capture the semantic groups, which can be used to generate the final segmentation results. We further propose a reconstruction loss on masked patches and a superpixel-based KL loss with pseudo-labels to enhance the visual representation. Experimental results show that our model achieves comparable or superior segmentation accuracy on the PASCAL VOC 2012 (+0.3% mIoU), PASCAL Context (+2.3% mIoU), and COCO (+2.2% mIoU) compared with baselines. We release the code at https://github.com/ArrowLuo/SegCLIP.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-luo23a, title = {{S}eg{CLIP}: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation}, author = {Luo, Huaishao and Bao, Junwei and Wu, Youzheng and He, Xiaodong and Li, Tianrui}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {23033--23044}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/luo23a/luo23a.pdf}, url = {https://proceedings.mlr.press/v202/luo23a.html}, abstract = {Recently, the contrastive language-image pre-training, e.g., CLIP, has demonstrated promising results on various downstream tasks. The pre-trained model can capture enriched visual concepts for images by learning from a large scale of text-image data. However, transferring the learned visual knowledge to open-vocabulary semantic segmentation is still under-explored. In this paper, we propose a CLIP-based model named SegCLIP for the topic of open-vocabulary segmentation in an annotation-free manner. The SegCLIP achieves segmentation based on ViT and the main idea is to gather patches with learnable centers to semantic regions through training on text-image pairs. The gathering operation can dynamically capture the semantic groups, which can be used to generate the final segmentation results. We further propose a reconstruction loss on masked patches and a superpixel-based KL loss with pseudo-labels to enhance the visual representation. Experimental results show that our model achieves comparable or superior segmentation accuracy on the PASCAL VOC 2012 (+0.3% mIoU), PASCAL Context (+2.3% mIoU), and COCO (+2.2% mIoU) compared with baselines. We release the code at https://github.com/ArrowLuo/SegCLIP.} }
Endnote
%0 Conference Paper %T SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation %A Huaishao Luo %A Junwei Bao %A Youzheng Wu %A Xiaodong He %A Tianrui Li %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-luo23a %I PMLR %P 23033--23044 %U https://proceedings.mlr.press/v202/luo23a.html %V 202 %X Recently, the contrastive language-image pre-training, e.g., CLIP, has demonstrated promising results on various downstream tasks. The pre-trained model can capture enriched visual concepts for images by learning from a large scale of text-image data. However, transferring the learned visual knowledge to open-vocabulary semantic segmentation is still under-explored. In this paper, we propose a CLIP-based model named SegCLIP for the topic of open-vocabulary segmentation in an annotation-free manner. The SegCLIP achieves segmentation based on ViT and the main idea is to gather patches with learnable centers to semantic regions through training on text-image pairs. The gathering operation can dynamically capture the semantic groups, which can be used to generate the final segmentation results. We further propose a reconstruction loss on masked patches and a superpixel-based KL loss with pseudo-labels to enhance the visual representation. Experimental results show that our model achieves comparable or superior segmentation accuracy on the PASCAL VOC 2012 (+0.3% mIoU), PASCAL Context (+2.3% mIoU), and COCO (+2.2% mIoU) compared with baselines. We release the code at https://github.com/ArrowLuo/SegCLIP.
APA
Luo, H., Bao, J., Wu, Y., He, X. & Li, T.. (2023). SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:23033-23044 Available from https://proceedings.mlr.press/v202/luo23a.html.

Related Material