Referring Image Segmentation via Cross-Modal Progressive Comprehension

Referring image segmentation aims at segmenting the foreground masks of the entities that can well match the description given in the natural language expression. Previous approaches tackle this problem using implicit feature interaction and fusion between visual and linguistic modalities, but usually fail to explore informative words of the expression to well align features from the two modalities for accurately identifying the referred entity. In this paper, we propose a Cross-Modal Progressive Comprehension (CMPC) module and a Text-Guided Feature Exchange (TGFE) module to effectively address the challenging task. Concretely, the CMPC module first employs entity and attribute words to perceive all the related entities that might be considered by the expression. Then, the relational words are adopted to highlight the correct entity as well as suppress other irrelevant ones by multimodal graph reasoning. In addition to the CMPC module, we further leverage a simple yet effective TGFE module to integrate the reasoned multimodal features from different levels with the guidance of textual information. In this way, features from multi-levels could communicate with each other and be refined based on the textual context. We conduct extensive experiments on four popular referring segmentation benchmarks and achieve new state-of-the-art performances.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Referring Expression Segmentation RefCOCO testA CPMC Overall IoU 64.53 # 5
Referring Expression Segmentation RefCOCO+ testA CPMC Overall IoU 53.44 # 6
Referring Expression Segmentation RefCOCO testB CPMC Overall IoU 59.64 # 5
Referring Expression Segmentation RefCOCO+ test B CPMC Overall IoU 43.23 # 6
Referring Expression Segmentation RefCoCo val CPMC Overall IoU 61.36 # 5
Referring Expression Segmentation RefCOCO+ val CPMC Overall IoU 49.56 # 6

Methods


No methods listed for this paper. Add relevant methods here