网络监督多标签识别：评估基准与双分支多标签对比学习
Webly Supervised Multi-Label Recognition: Evaluation Benchmark and Dual-Branch Multi-Label Contrastive Learning
查看机构详情
- Guangdong University of Technology（广东工业大学）
- Sun Yat-Sen University（中山大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对网络监督多标签识别缺乏统一基准等问题，构建了WS-MLR基准并重新实现基线，提出双分支多标签对比学习框架DBMLCL，经实验验证其在该基准上相比基线有更优性能。
中文摘要 AI 辅助
使用免费的网络图像训练深度学习模型可减少对昂贵人工标注的依赖。尽管网络监督学习在单标签识别中已被广泛研究，但其多标签对应部分仍未得到充分探索，部分原因是缺乏统一基准和公平比较协议。为填补这一空白，我们构建了网络监督多标签识别（WS-MLR）的基准，包括Web-COCO和Web-Pascal，并在统一设置下重新实现了代表性基线。这两个数据集分别与MS-COCO和Pascal VOC涵盖相同的80和20个类别，并包含约30万张使用类别-词组合作为搜索关键词从互联网检索的图像。我们进一步提出了双分支多标签对比学习（DBMLCL）框架，该框架学习特定类别的实例级和类别级表示及其相似性，以识别和纠正噪声标签。在基准上的大量实验表明，DBMLCL与代表性基线相比具有卓越性能。
英文摘要
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.
