Webly Supervised Multi-Label Recognition: Evaluation Benchmark and Dual-Branch Multi-Label Contrastive Learning

2026-07-22

AI Summary

This work addresses the challenges of multi-label image recognition under weak supervision, particularly noisy labels and the absence of standardized benchmarks. To this end, it introduces Web-COCO and Web-Pascal, the first webly supervised multi-label recognition benchmarks. The authors propose a dual-branch multi-label contrastive learning framework that jointly optimizes instance-level and category-level semantic representations to simultaneously correct noisy labels and learn robust features. Extensive experiments demonstrate that the proposed method significantly outperforms existing baselines on both newly established benchmarks, confirming its effectiveness and generalization capability in noisy-label scenarios.

Abstract

Training deep learning models with freely available web images can reduce their dependence on costly manual annotations. Although webly supervised learning has been widely studied for single-label recognition, its multi-label counterpart remains underexplored, partly due to the lack of unified benchmarks and fair comparison protocols. To address this gap, we construct a benchmark for webly supervised multi-label recognition (WS-MLR), including Web-COCO and Web-Pascal, and re-implement representative baselines under a unified setting. The two datasets cover the same 80 and 20 categories as MS-COCO and Pascal VOC, respectively, and contain about 300 thousand images retrieved from the Internet using category-word combinations as search keywords. We further propose a Dual-Branch Multi-Label Contrastive Learning (DBMLCL) framework, which learns category-specific instance-level and category-level representations together with their similarities to identify and correct noisy labels. Extensive experiments on the benchmark demonstrate that DBMLCL achieves superior performance compared to representative baselines.

Problem

• webly supervised learning
• multi-label recognition
• noisy labels
• benchmark
• image retrieval

Innovation

• webly supervised learning
• multi-label recognition
• contrastive learning
• noisy label correction
• benchmark dataset