Learning Disentangled Representation Implicitly Via Transformer for Occluded Person Re-Identification

• Published in: IEEE transactions on multimedia Vol. 25; pp. 1294 - 1305
• Main Authors: Jia, Mengxi, Cheng, Xinhua, Lu, Shijian, Zhang, Jian
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Alignment; Body parts; Decoding; Feature extraction; Interference; Misalignment; Occlusion; Occlusion scene; person Re-identification; Queries; Representation learning; Representations; Semantics; Task analysis; Transformers; visual Transformer
• ISSN: 1520-9210; 1941-0077
• DOI: 10.1109/TMM.2022.3141267

Person re-IDentification (re-ID) under various occlusions has been a long-standing challenge as person images with different types of occlusions often suffer from misalignment in image matching and ranking. Most existing methods tackle this challenge by aligning spatial features of body parts according to external semantic cues or feature similarities but this alignment approach is complicated and sensitive to noises. We design DRL-Net, a disentangled representation learning network that handles occluded re-ID without requiring strict person image alignment or any additional supervision. Leveraging transformer architectures, DRL-Net achieves alignment-free re-ID via global reasoning of local features of occluded person images. It measures image similarity by automatically disentangling the representation of undefined semantic components, e.g., human body parts or obstacles, under the guidance of semantic preference object queries in the transformer. In addition, we design a decorrelation constraint in the transformer decoder and impose it over object queries for better focus on different semantic components. To better eliminate interference from occlusions, we design a contrast feature learning technique (CFL) for better separation of occlusion features and discriminative ID features. Extensive experiments over occluded and holistic re-ID benchmarks show that the DRL-Net achieves superior re-ID performance consistently and outperforms the state-offi-the-art by large margins for occluded re-ID dataset.