Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP

• URL: http://arxiv.org/abs/2412.19650v1
• Date: Fri, 27 Dec 2024 13:55:11 GMT
• Title: Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP
• Authors: Zhongxing Xu, Feilong Tang, Zhe Chen, Yingxue Su, Zhiyi Zhao, Ge Zhang, Jionglong Su, Zongyuan Ge,
• Abstract summary: We propose a framework to learn class-specific vision prototypes in vision space with the help of text prototypes. We also propose a regional semantic contrast module that contrasts regions embedding with corresponding prototypes. Our proposed framework achieves state-of-the-art performance on two benchmark datasets.
• Score: 19.697857943845012
• License:
• Abstract: The application of Contrastive Language-Image Pre-training (CLIP) in Weakly Supervised Semantic Segmentation (WSSS) research powerful cross-modal semantic understanding capabilities. Existing methods attempt to optimize input text prompts for improved alignment of images and text, by finely adjusting text prototypes to facilitate semantic matching. Nevertheless, given the modality gap between text and vision spaces, the text prototypes employed by these methods have not effectively established a close correspondence with pixel-level vision features. In this work, our theoretical analysis indicates that the inherent modality gap results in misalignment of text and region features, and that this gap cannot be sufficiently reduced by minimizing contrast loss in CLIP. To mitigate the impact of the modality gap, we propose a Vision Prototype Learning (VPL) framework, by introducing more representative vision prototypes. The core of this framework is to learn class-specific vision prototypes in vision space with the help of text prototypes, for capturing high-quality localization maps. Moreover, we propose a regional semantic contrast module that contrasts regions embedding with corresponding prototypes, leading to more comprehensive and robust feature learning. Experimental results show that our proposed framework achieves state-of-the-art performance on two benchmark datasets.

Related papers

• Dual-Modal Prototype Joint Learning for Compositional Zero-Shot Learning [15.183106475115583]
  Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions of attributes and objects by leveraging knowledge learned from seen compositions. We propose a novel Dual-Modal Prototype Joint Learning framework for the CZSL task.
  arXiv  Detail & Related papers  (2025-01-23T17:30:27Z)
• Multi-Grained Cross-modal Alignment for Learning Open-vocabulary Semantic Segmentation from Text Supervision [23.931443799102663]
  We introduce a Multi-Grained Cross-modal Alignment (MGCA) framework to bridge the granularity gap without any dense annotations. Specifically, MGCA constructs pseudo multi-granular semantic correspondences upon image-text pairs. Our method achieves significant advancements over state-of-the-art methods, demonstrating its effectiveness and efficiency.
  arXiv  Detail & Related papers  (2024-03-06T13:43:36Z)
• Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation [100.81837601210597]
  We propose Concept Curation (CoCu) to bridge the gap between visual and textual semantics in pre-training data. CoCu achieves superb zero-shot transfer performance and greatly boosts language-supervised segmentation baseline by a large margin.
  arXiv  Detail & Related papers  (2023-09-24T00:05:39Z)
• Fine-Grained Semantically Aligned Vision-Language Pre-Training [151.7372197904064]
  Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks. Existing methods mainly model the cross-modal alignment by the similarity of the global representations of images and texts. We introduce LO, a fine-grained semantically aLigned visiOn-langUage PrE-training framework, which learns fine-grained semantic alignment from the novel perspective of game-theoretic interactions.
  arXiv  Detail & Related papers  (2022-08-04T07:51:48Z)
• Vision-Language Pre-Training for Boosting Scene Text Detectors [57.08046351495244]
  We specifically adapt vision-language joint learning for scene text detection. We propose to learn contextualized, joint representations through vision-language pre-training. The pre-trained model is able to produce more informative representations with richer semantics.
  arXiv  Detail & Related papers  (2022-04-29T03:53:54Z)
• CRIS: CLIP-Driven Referring Image Segmentation [71.56466057776086]
  We propose an end-to-end CLIP-Driven Referring Image framework (CRIS) CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. Our proposed framework significantly outperforms the state-of-the-art performance without any post-processing.
  arXiv  Detail & Related papers  (2021-11-30T07:29:08Z)
• ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration [48.01536973731182]
  We introduce a new vision-and-language pretraining method called ROSITA. It integrates the cross- and intra-modal knowledge in a unified scene graph to enhance the semantic alignments. ROSITA significantly outperforms existing state-of-the-art methods on three typical vision-and-language tasks over six benchmark datasets.
  arXiv  Detail & Related papers  (2021-08-16T13:16:58Z)
• MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding [74.33171794972688]
  We present algorithms to model phrase-object relevance by leveraging fine-grained visual representations and visually-aware language representations. Experiments conducted on the widely-adopted Flickr30k dataset show a significant improvement over existing weakly-supervised methods.
  arXiv  Detail & Related papers  (2020-10-12T00:43:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.