FlowComposer: Composable Flows for Compositional Zero-Shot Learning

• URL: http://arxiv.org/abs/2603.16641v1
• Date: Tue, 17 Mar 2026 15:12:39 GMT
• Title: FlowComposer: Composable Flows for Compositional Zero-Shot Learning
• Abstract summary: Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by recombining primitives learned from seen pairs.<n>Recent CZSL methods built on vision-language models (VLMs) typically adopt parameter-efficient fine-tuning (PEFT)<n>We introduce FlowComposer, a model-agnostic framework that learns two primitive flows to transport visual features toward attribute and object text embeddings.
• Score: 10.977642730831361
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by recombining primitives learned from seen pairs. Recent CZSL methods built on vision-language models (VLMs) typically adopt parameter-efficient fine-tuning (PEFT). They apply visual disentanglers for decomposition and manipulate token-level prompts or prefixes to encode compositions. However, such PEFT-based designs suffer from two fundamental limitations: (1) Implicit Composition Construction, where composition is realized only via token concatenation or branch-wise prompt tuning rather than an explicit operation in the embedding space; (2) Remained Feature Entanglement, where imperfect disentanglement leaves attribute, object, and composition features mutually contaminated. Together, these issues limit the generalization ability of current CZSL models. In this paper, we are the first to systematically study flow matching for CZSL and introduce FlowComposer, a model-agnostic framework that learns two primitive flows to transport visual features toward attribute and object text embeddings, and a learnable Composer that explicitly fuses their velocity fields into a composition flow. To exploit the inevitable residual entanglement, we further devise a leakage-guided augmentation scheme that reuses leaked features as auxiliary signals. We thoroughly evaluate FlowComposer on three public CZSL benchmarks by integrating it as a plug-and-play component into various baselines, consistently achieving significant improvements.

Related papers

• AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning [52.47988016454267]
  Vision-Language-Action (VLA) models excel at end-to-end robotic manipulation but struggle with out-of-distribution (OOD) generalization.<n>We identify two mutually reinforcing modes: emphtrajectory overfitting, where models overfit to holistic trajectory patterns rather than compositional sub-skill semantics; and emphperceptual shortcut, where action tokens over-rely on wrist-view textures at the expense of global spatial grounding.<n>We introduce textbfAC-VLA, a plug-and-play Action Compositional learning
  arXiv  Detail & Related papers  (2026-07-17T07:51:03Z)
• PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation [58.1914505657064]
  This paper proposes a simple yet effective parallel cost aggregation (PCA-Seg) paradigm to alleviate the challenge of knowledge interference between class-level semantics and spatial context.<n>Experiments on eight benchmarks show that each parallel block in PCA-Seg adds merely 0.35M parameters while achieving state-of-the-art OSPS performance.
  arXiv  Detail & Related papers  (2026-03-18T09:26:43Z)
• 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)
• 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)
• CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning [62.090051975043544]
  Attribute and object (A-O) disentanglement is a fundamental and critical problem for Compositional Zero-shot Learning (CZSL) We propose a novel A-O disentangled framework for CZSL, namely Class-specified Cascaded Network (CSCNet)
  arXiv  Detail & Related papers  (2024-03-09T14:18:41Z)
• 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)
• ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning [29.591615811894265]
  Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novel compositions of state and object primitives in images with no priors on the compositional space. We propose a novel method, termed Progressive Cross-primitive Compatibility (ProCC), to mimic the human learning process for OW-CZSL tasks.
  arXiv  Detail & Related papers  (2022-11-19T10:09:46Z)
• KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning [52.422873819371276]
  The goal of open-world compositional zero-shot learning (OW-CZSL) is to recognize compositions of state and objects in images. Here, we revisit a simple CZSL baseline and predict the primitives, i.e. states and objects, independently. We estimate the feasibility of each composition through external knowledge, using this prior to remove unfeasible compositions from the output space. Our model, Knowledge-Guided Simple Primitives (KG-SP), achieves state of the art in both OW-CZSL and pCZSL.
  arXiv  Detail & Related papers  (2022-05-13T17:18:15Z)

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.