Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval

TL;DR

This paper introduces TAGS-DC, a method for generating challenging synthetic negative sentences for image-text retrieval, improving model training by enhancing negative sample difficulty and semantic mismatch detection.

Contribution

The paper proposes a novel negative sentence generation approach with masking and refilling, and auxiliary tasks for better semantic mismatch utilization in image-text retrieval.

Findings

Improves retrieval performance on MS-COCO and Flickr30K datasets.

Demonstrates robustness and faithfulness through extensive analysis.

Outperforms current state-of-the-art models.

Abstract

Matching model is essential for Image-Text Retrieval framework. Existing research usually train the model with a triplet loss and explore various strategy to retrieve hard negative sentences in the dataset. We argue that current retrieval-based negative sample construction approach is limited in the scale of the dataset thus fail to identify negative sample of high difficulty for every image. We propose our TAiloring neGative Sentences with Discrimination and Correction (TAGS-DC) to generate synthetic sentences automatically as negative samples. TAGS-DC is composed of masking and refilling to generate synthetic negative sentences with higher difficulty. To keep the difficulty during training, we mutually improve the retrieval and generation through parameter sharing. To further utilize fine-grained semantic of mismatch in the negative sentence, we propose two auxiliary tasks, namely word discrimination and word correction to improve the training. In experiments, we verify the effectiveness of our model on MS-COCO and Flickr30K compared with current state-of-the-art models and demonstrates its robustness and faithfulness in the further analysis. Our code is available in https://github.com/LibertFan/TAGS.