Part-Guided Attention Learning for Vehicle Instance Retrieval

• DOI: 10.48550/arxiv.1909.06023
• Publication Date: 2019-01-01
• Authors: Xinyu Zhang; Rufeng Zhang; Jiewei Cao; Dong Gong; Mingyu You; Chunhua Shen
• Keywords: Discriminative model; Feature (linguistics); Benchmark (surveying); Distortion (music)

Vehicle instance retrieval often requires one to recognize the fine-grained visual differences between vehicles. Besides holistic appearance of vehicles which is easily affected by viewpoint variation and distortion, vehicle parts also provide crucial cues differentiate near-identical Motivated these observations, we introduce a Part-Guided Attention Network (PGAN) pinpoint prominent part regions effectively combine global information for discriminative feature learning. PGAN first detects locations different components salient regardless identity, serve as bottom-up attention narrow down possible searching regions. To estimate importance detected parts, propose Part Module (PAM) adaptively locate most with high-attention weights suppress distraction irrelevant relatively low weights. The PAM guided loss therefore provides top-down that enables be calculated at level car other Finally, aggregate features improve performance further. combines part-guided attention, in an end-to-end framework. Extensive experiments demonstrate proposed method achieves new state-of-the-art on four large-scale benchmark datasets.