Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination

Abstract

Most existing image-text matching methods adopt triplet loss as the optimization objective, and choosing a proper negative sample for the triplet of <anchor, positive, negative> is important for effectively training the model, e.g., hard negatives make the model learn efficiently and effectively. However, we observe that existing methods mainly employ the most similar samples as hard negatives, which may not be true negatives. In other words, the samples with high similarity but not paired with the anchor may reserve positive semantic associations, and we call them false negatives. Repelling these false negatives in triplet loss would mislead the semantic representation learning and result in inferior retrieval performance. In this paper, we propose a novel False Negative Elimination (FNE) strategy to select negatives via sampling, which could alleviate the problem introduced by false negatives. Specifically, we first construct the distributions of positive and negative samples separately via their similarities with the anchor, based on the features extracted from image and text encoders. Then we calculate the false negative probability of a given sample based on its similarity with the anchor and the above distributions via the Bayes' rule, which is employed as the sampling weight during negative sampling process. Since there may not exist any false negative in a small batch size, we design a memory module with momentum to retain a large negative buffer and implement our negative sampling strategy spanning over the buffer. In addition, to make the model focus on hard negatives, we reassign the sampling weights for the simple negatives with a cut-down strategy. The extensive experiments are conducted on Flickr30K and MS-COCO, and the results demonstrate the superiority of our proposed false negative elimination strategy. The code is available at https://github.com/LuminosityX/FNE.

arXiv commentAccepted at ACM MM 2023

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Efficient Estimation of Word Representations in Vector Space
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Microsoft COCO Captions: Data Collection and Evaluation Server
• Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
• VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
• Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matching
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval

Cited by in corpus (5)

• Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval
• Multi-modal Reference Learning for Fine-grained Text-to-Image Retrieval
• Ambiguity-Aware and High-Order Relation Learning for Multi-Grained Image-Text Matching
• MM-Forecast: A Multimodal Approach to Temporal Event Forecasting with Large Language Models
• Leveraging Weak Cross-Modal Guidance for Coherence Modelling via Iterative Learning