Learning Visual Proxy for Compositional Zero-Shot Learning

• URL: http://arxiv.org/abs/2501.13859v3
• Date: Thu, 13 Mar 2025 04:04:32 GMT
• Title: Learning Visual Proxy for Compositional Zero-Shot Learning
• Authors: Shiyu Zhang, Cheng Yan, Yang Liu, Chenchen Jing, Lei Zhou, Wenjun Wang,
• Abstract summary: We introduce Visual Proxy Learning, a novel approach that facilitates the learning of distinct visual distributions.<n>We propose an effective Cross-Modal Joint Learning strategy that imposes cross-modal constraints between the original text-image space and the fine-grained visual space.
• Score: 15.183106475115583
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Compositional Zero-Shot Learning (CZSL) aims to recognize novel attribute-object compositions by leveraging knowledge from seen compositions. Existing methods align textual prototypes with visual features through Vision-Language Models (VLMs), but they face two key limitations: (1) modality gaps hinder the discrimination of semantically similar composition pairs, and (2) single-modal textual prototypes lack fine-grained visual cues, creating bottlenecks in VLM-based CZSL. In this paper, we introduce Visual Proxy Learning, a novel approach that facilitates the learning of distinct visual distributions, effectively reducing the modality gap and improving compositional generalization performance. Specifically, we initialize visual proxies for various attributes, objects, and their compositions using text representations. By optimizing the visual space, we capture fine-grained visual cues and guide the learning of more discriminative visual representations for attributes, objects and compositions. Furthermore, we propose an effective Cross-Modal Joint Learning (CMJL) strategy that imposes cross-modal constraints between the original text-image space and the fine-grained visual space. This approach not only boosts generalization for previously unseen composition pairs but also sharpens the discrimination of similar pairs, fostering more robust and precise learning. Extensive experiments demonstrate state-of-the-art performance in closed-world scenarios and competitive open-world results across four established CZSL benchmarks, validating the effectiveness of our approach in advancing compositional generalization.

Related papers

• Duplex: Dual Prototype Learning for Compositional Zero-Shot Learning [17.013498508426398]
  Compositional Zero-Shot Learning (CZSL) aims to enable models to recognize novel compositions of visual states and objects that were absent during training.<n>We propose Duplex, a novel dual-prototype learning method that integrates semantic and visual prototypes through a carefully designed dual-branch architecture.
  arXiv  Detail & Related papers  (2025-01-13T08:04:32Z)
• Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP [19.697857943845012]
  We propose a framework to learn class-specific vision prototypes in vision space with the help of text prototypes.<n>We also propose a regional semantic contrast module that contrasts regions embedding with corresponding prototypes.<n>Our proposed framework achieves state-of-the-art performance on two benchmark datasets.
  arXiv  Detail & Related papers  (2024-12-27T13:55:11Z)
• Discriminative Image Generation with Diffusion Models for Zero-Shot Learning [53.44301001173801]
  We present DIG-ZSL, a novel Discriminative Image Generation framework for Zero-Shot Learning.<n>We learn a discriminative class token (DCT) for each unseen class under the guidance of a pre-trained category discrimination model (CDM)<n>In this paper, the extensive experiments and visualizations on four datasets show that our DIG-ZSL: (1) generates diverse and high-quality images, (2) outperforms previous state-of-the-art nonhuman-annotated semantic prototype-based methods by a large margin, and (3) achieves comparable or better performance than baselines that leverage human-annot
  arXiv  Detail & Related papers  (2024-12-23T02:18:54Z)
• Discriminative Fine-tuning of LVLMs [67.14293827774827]
  Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. We propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs.
  arXiv  Detail & Related papers  (2024-12-05T17:54:27Z)
• Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning [13.68867780184022]
  Few-shot learning aims to recognize new concepts using a limited number of visual samples. Our framework incorporates both the abstract class semantics and the concrete class entities extracted from Large Language Models (LLMs) For the challenging one-shot setting, our approach, utilizing the ResNet-12 backbone, achieves an average improvement of 1.95% over the second-best competitor.
  arXiv  Detail & Related papers  (2024-08-22T15:10:20Z)
• Multi-Modal Prototypes for Open-World Semantic Segmentation [37.84805778548119]
  We propose to encompass textual and visual clues as multi-modal prototypes to allow more comprehensive support for semantic segmentation. We decompose the high-level language information as multi-aspect prototypes and aggregate the low-level visual information as more semantic prototypes. Based on an elastic mask prediction module, we are able to solve the zero-shot, few-shot and generalized counterpart tasks in one architecture.
  arXiv  Detail & Related papers  (2023-07-05T03:27:31Z)
• Prompting Language-Informed Distribution for Compositional Zero-Shot Learning [73.49852821602057]
  Compositional zero-shot learning (CZSL) task aims to recognize unseen compositional visual concepts. We propose a model by prompting the language-informed distribution, aka., PLID, for the task. Experimental results on MIT-States, UT-Zappos, and C-GQA datasets show the superior performance of the PLID to the prior arts.
  arXiv  Detail & Related papers  (2023-05-23T18:00:22Z)
• Non-Contrastive Learning Meets Language-Image Pre-Training [145.6671909437841]
  We study the validity of non-contrastive language-image pre-training (nCLIP) We introduce xCLIP, a multi-tasking framework combining CLIP and nCLIP, and show that nCLIP aids CLIP in enhancing feature semantics.
  arXiv  Detail & Related papers  (2022-10-17T17:57:46Z)
• 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)
• Self-Supervised Visual Representation Learning with Semantic Grouping [50.14703605659837]
  We tackle the problem of learning visual representations from unlabeled scene-centric data. We propose contrastive learning from data-driven semantic slots, namely SlotCon, for joint semantic grouping and representation learning.
  arXiv  Detail & Related papers  (2022-05-30T17:50:59Z)
• 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)
• Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation [55.339405417090084]
  We propose a dual prototypical contrastive learning approach tailored to the few-shot semantic segmentation (FSS) task. The main idea is to encourage the prototypes more discriminative by increasing inter-class distance while reducing intra-class distance in prototype feature space. We demonstrate that the proposed dual contrastive learning approach outperforms state-of-the-art FSS methods on PASCAL-5i and COCO-20i datasets.
  arXiv  Detail & Related papers  (2021-11-09T08:14:50Z)
• 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)

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.