Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing
arXiv:1903.00839
Abstract
Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as visual attributes, location and interactions with surrounding regions. Although the attention mechanism has been successfully applied for cross-modal alignments, previous attention models focus on only the most dominant features of both modalities, and neglect the fact that there could be multiple comprehensive textual-visual correspondences between images and referring expressions. To tackle this issue, we design a novel cross-modal attention-guided erasing approach, where we discard the most dominant information from either textual or visual domains to generate difficult training samples online, and to drive the model to discover complementary textual-visual correspondences. Extensive experiments demonstrate the effectiveness of our proposed method, which achieves state-of-the-art performance on three referring expression grounding datasets.
Accepted by CVPR 2019
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
- Bilinear Attention Networks
- Stacked Cross Attention for Image-Text Matching
- Dual Attention Networks for Multimodal Reasoning and Matching
- Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
- Question-Guided Hybrid Convolution for Visual Question Answering
- Self-Erasing Network for Integral Object Attention