SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
SkyPart uses learnable prototypes for patch grouping, altitude modulation only in training, graph-attention readout, and Kendall-weighted loss to set new state-of-the-art single-pass performance on SUES-200, Universit...
-
Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
SkyPart achieves state-of-the-art single-pass cross-view geo-localization on SUES-200, University-1652, and DenseUAV by using prototype-based part discovery, altitude-conditioned modulation, and Kendall-weighted loss,...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.