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

arXiv: https://arxiv.org/abs/2607.20874 · HTML: https://mlsanity.com/paper/2607.20874/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [WebVision Database: Visual Learning and Understanding from Web Data](https://mlsanity.com/paper/1708.02862/) (2017)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition](https://mlsanity.com/paper/1908.07325/) (2019)
- [Webly Supervised Learning of Convolutional Networks](https://mlsanity.com/paper/1505.01554/) (2015)
- [Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition](https://mlsanity.com/paper/2012.02994/) (2020)
- [Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition](https://mlsanity.com/paper/2009.09450/) (2020)
- [MoPro: Webly Supervised Learning with Momentum Prototypes](https://mlsanity.com/paper/2009.07995/) (2020)
- [CNN: Single-label to Multi-label](https://mlsanity.com/paper/1406.5726/) (2014)
- [Residual Attention: A Simple but Effective Method for Multi-Label Recognition](https://mlsanity.com/paper/2108.02456/) (2021)
- [Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning](https://mlsanity.com/paper/2008.00923/) (2020)
- [Structured Semantic Transfer for Multi-Label Recognition with Partial Labels](https://mlsanity.com/paper/2112.10941/) (2021)
- [CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification](https://mlsanity.com/paper/2307.16634/) (2023)
- [LaSO: Label-Set Operations networks for multi-label few-shot learning](https://mlsanity.com/paper/1902.09811/) (2019)
- [Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach](https://mlsanity.com/paper/2108.02399/) (2021)
- [Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval](https://mlsanity.com/paper/1501.06272/) (2015)
- [Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels](https://mlsanity.com/paper/2205.11131/) (2022)
- [Dynamic Correlation Learning and Regularization for Multi-Label Confidence Calibration](https://mlsanity.com/paper/2407.06844/) (2024)
- [Semantic Representation and Dependency Learning for Multi-Label Image Recognition](https://mlsanity.com/paper/2204.03795/) (2022)
- [Learning Spatial-Temporal Coherent Correlations for Speech-Preserving Facial Expression Manipulation](https://mlsanity.com/paper/2604.20226/) (2026)

## Abstract (arXiv)

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.