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

11/05/2021
by   Zhihao Fan, et al.
16

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.

READ FULL TEXT
research
08/08/2023

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

Most existing image-text matching methods adopt triplet loss as the opti...
research
10/05/2022

Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective

Visual-Semantic Embedding (VSE) aims to learn an embedding space where r...
research
06/16/2022

Towards Robust Ranker for Text Retrieval

A ranker plays an indispensable role in the de facto 'retrieval rera...
research
09/12/2021

Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval

Existing research for image text retrieval mainly relies on sentence-lev...
research
03/21/2023

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

This paper proposes a novel diffusion-based model, CompoDiff, for solvin...
research
03/07/2020

Adaptive Offline Quintuplet Loss for Image-Text Matching

Existing image-text matching approaches typically leverage triplet loss ...
research
05/03/2017

FOIL it! Find One mismatch between Image and Language caption

In this paper, we aim to understand whether current language and vision ...

Please sign up or login with your details

Forgot password? Click here to reset