Saved in:
Bibliographic Details
Main Authors: Tan, Hao, Tan, Zichang, Li, Jun, Liu, Ajian, Wan, Jun, Lei, Zhen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.15337
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915205228789760
author Tan, Hao
Tan, Zichang
Li, Jun
Liu, Ajian
Wan, Jun
Lei, Zhen
author_facet Tan, Hao
Tan, Zichang
Li, Jun
Liu, Ajian
Wan, Jun
Lei, Zhen
contents Identifying multiple novel classes in an image, known as open-vocabulary multi-label recognition, is a challenging task in computer vision. Recent studies explore the transfer of powerful vision-language models such as CLIP. However, these approaches face two critical challenges: (1) The local semantics of CLIP are disrupted due to its global pre-training objectives, resulting in unreliable regional predictions. (2) The matching property between image regions and candidate labels has been neglected, relying instead on naive feature aggregation such as average pooling, which leads to spurious predictions from irrelevant regions. In this paper, we present RAM (Recover And Match), a novel framework that effectively addresses the above issues. To tackle the first problem, we propose Ladder Local Adapter (LLA) to enforce refocusing on local regions, recovering local semantics in a memory-friendly way. For the second issue, we propose Knowledge-Constrained Optimal Transport (KCOT) to suppress meaningless matching to non-GT labels by formulating the task as an optimal transport problem. As a result, RAM achieves state-of-the-art performance on various datasets from three distinct domains, and shows great potential to boost the existing methods. Code: https://github.com/EricTan7/RAM.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15337
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport
Tan, Hao
Tan, Zichang
Li, Jun
Liu, Ajian
Wan, Jun
Lei, Zhen
Computer Vision and Pattern Recognition
Identifying multiple novel classes in an image, known as open-vocabulary multi-label recognition, is a challenging task in computer vision. Recent studies explore the transfer of powerful vision-language models such as CLIP. However, these approaches face two critical challenges: (1) The local semantics of CLIP are disrupted due to its global pre-training objectives, resulting in unreliable regional predictions. (2) The matching property between image regions and candidate labels has been neglected, relying instead on naive feature aggregation such as average pooling, which leads to spurious predictions from irrelevant regions. In this paper, we present RAM (Recover And Match), a novel framework that effectively addresses the above issues. To tackle the first problem, we propose Ladder Local Adapter (LLA) to enforce refocusing on local regions, recovering local semantics in a memory-friendly way. For the second issue, we propose Knowledge-Constrained Optimal Transport (KCOT) to suppress meaningless matching to non-GT labels by formulating the task as an optimal transport problem. As a result, RAM achieves state-of-the-art performance on various datasets from three distinct domains, and shows great potential to boost the existing methods. Code: https://github.com/EricTan7/RAM.
title Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.15337