陈俊帆
点赞：
陈俊帆
点赞：
论文
Momentum Pseudo-Labeling for Weakly Supervised Phrase Grounding
发布时间：2025-10-22点击次数：
发表刊物：
Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI), CCF-A
摘要：
Weakly supervised phrase grounding tasks aim to learn alignments between phrases and regions with coarse image-caption match information. One branch of previous methods established pseudo-label relationships between phrases and regions based on the Expectation-Maximization (EM) algorithm combined with contrastive learning. However, adopting a simplified batch-level local update (partial) of pseudo-labels in E-step is sub-optimal, while extending it to global update requires inefficiently numerous computations. In addition, their failure to consider potential false negative examples in contrastive loss negatively impacts the effectiveness of M-step optimization. To address these issues, we propose a Momentum Pseudo Labeling (MPL) method, which efficiently uses a momentum model to synchronize global pseudo-label updates on the fly with model parameter updating. Additionally, we explore potential relationships between phrases and regions from non-matching image-caption pairs and convert these false negative examples to positive ones in contrastive learning. Our approach achieved SOTA performance on 3 commonly used grounding datasets for weakly supervised phrase grounding tasks.
合写作者：
Dongdong Kuang,张日崇, Zhijie Nie,陈俊帆, Jaein Kim
论文类型：
国际学术会议
页面范围：
24348--24356
是否译文：
否
发表时间：
2025-01-01