CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglement

• URL: http://arxiv.org/abs/2511.16378v1
• Date: Thu, 20 Nov 2025 14:00:17 GMT
• Title: CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglement
• Authors: Pan Yang, Cheng Deng, Jing Yang, Han Zhao, Yun Liu, Yuling Chen, Xiaoli Ruan, Yanping Chen,
• Abstract summary: Compositional zero-shot learning (CZSL) aims to learn the concepts of attributes and objects in seen compositions and to recognize their unseen compositions.<n>We propose CAMS, which aims to extract semantic features from visual features and perform semantic disentanglement in multidimensional spaces.<n>CAMS achieves state-of-the-art performance in both closed-world and open-world settings.
• Score: 47.59163940599447
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Compositional zero-shot learning (CZSL) aims to learn the concepts of attributes and objects in seen compositions and to recognize their unseen compositions. Most Contrastive Language-Image Pre-training (CLIP)-based CZSL methods focus on disentangling attributes and objects by leveraging the global semantic representation obtained from the image encoder. However, this representation has limited representational capacity and do not allow for complete disentanglement of the two. To this end, we propose CAMS, which aims to extract semantic features from visual features and perform semantic disentanglement in multidimensional spaces, thereby improving generalization over unseen attribute-object compositions. Specifically, CAMS designs a Gated Cross-Attention that captures fine-grained semantic features from the high-level image encoding blocks of CLIP through a set of latent units, while adaptively suppressing background and other irrelevant information. Subsequently, it conducts Multi-Space Disentanglement to achieve disentanglement of attribute and object semantics. Experiments on three popular benchmarks (MIT-States, UT-Zappos, and C-GQA) demonstrate that CAMS achieves state-of-the-art performance in both closed-world and open-world settings. The code is available at https://github.com/ybyangjing/CAMS.

Related papers

• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)
• Efficiently Disentangling CLIP for Multi-Object Perception [62.523137132812764]
  Vision-language models like CLIP excel at recognizing the single, prominent object in a scene, but struggle in complex scenes containing multiple objects.<n>We propose DCLIP, an efficient framework that learns an optimal level of mutual information while adding only minimal learnable parameters to a frozen VLM.
  arXiv  Detail & Related papers  (2025-02-05T08:20:31Z)
• Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training [17.893694262999826]
  This paper introduces a novel framework, Understanding and Linking Attributes and Objects (ULAO) in Compositional Zero-Shot Learning (CZSL)<n>ULAO comprises two innovative modules. The Understanding Attributes and Objects (UAO) module improves primitive understanding by sequential primitive prediction and leveraging recognized objects as contextual hints for attribute classification.<n>The Linking Attributes and Objects (LAO) module improves the attribute-object linkage understanding through a new contrastive learning strategy that incorporates tailored hard negative generation and adaptive loss adjustments.
  arXiv  Detail & Related papers  (2024-12-10T03:41:20Z)
• LMSeg: Unleashing the Power of Large-Scale Models for Open-Vocabulary Semantic Segmentation [16.864086165056698]
  Existing open-vocabulary approaches leverage vision-language models, such as CLIP, to align visual features with rich semantic features acquired through pre-training on large-scale vision-language datasets.<n>We propose to alleviate the issues by leveraging multiple large-scale models to enhance the alignment between fine-grained visual features and enriched linguistic features.<n>Our method achieves state-of-the-art performance across all major open-vocabulary segmentation benchmarks.
  arXiv  Detail & Related papers  (2024-11-30T05:49:42Z)
• Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning [21.488599805772054]
  Compositional zero-shot learning aims to recognize novel compositions of attributes and objects learned from seen compositions.<n>Previous works disentangle attributes and objects by extracting shared and exclusive parts between the image pair sharing the same attribute (object)<n>We propose a novel framework named multimodal large language model (MLLM) embeddings and attribute smoothing guided disentanglement for CZSL.
  arXiv  Detail & Related papers  (2024-11-18T07:55:54Z)
• Graph-guided Cross-composition Feature Disentanglement for Compositional Zero-shot Learning [54.08741382593959]
  Disentanglement of visual features of primitives (i.e., attributes and objects) has shown exceptional results in Compositional Zero-shot Learning (CZSL)<n>It is challenging to learn disentangled primitive features that are general across different compositions.<n>We propose the solution of cross-composition feature disentanglement, which takes multiple primitive-sharing compositions as inputs.
  arXiv  Detail & Related papers  (2024-08-19T08:23:09Z)
• Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning [52.506434446439776]
  Compositional zero-shot learning (CZSL) aims to recognize compositions with prior knowledge of known primitives (attribute and object) We propose a simple and scalable framework called Composition Transformer (CoT) to address these issues. Our method achieves SoTA performance on several benchmarks, including MIT-States, C-GQA, and VAW-CZSL.
  arXiv  Detail & Related papers  (2023-08-08T03:24:21Z)
• De-coupling and De-positioning Dense Self-supervised Learning [65.56679416475943]
  Dense Self-Supervised Learning (SSL) methods address the limitations of using image-level feature representations when handling images with multiple objects. We show that they suffer from coupling and positional bias, which arise from the receptive field increasing with layer depth and zero-padding. We demonstrate the benefits of our method on COCO and on a new challenging benchmark, OpenImage-MINI, for object classification, semantic segmentation, and object detection.
  arXiv  Detail & Related papers  (2023-03-29T18:07:25Z)
• Semantic Disentangling Generalized Zero-Shot Learning [50.259058462272435]
  Generalized Zero-Shot Learning (GZSL) aims to recognize images from both seen and unseen categories. In this paper, we propose a novel feature disentangling approach based on an encoder-decoder architecture. The proposed model aims to distill quality semantic-consistent representations that capture intrinsic features of seen images.
  arXiv  Detail & Related papers  (2021-01-20T05:46:21Z)

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.