Relation preserving triplet mining for stabilising the triplet loss in re-identification systems

• Main Authors: GHOSH, Adhiraj, SHANMUGALINGAM, Kuruparan, LIN, Wen-yan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Algorithms; Machine learning architectures; and algorithms (including transfer); formulations; Image recognition and understanding (object detection; categorization; segmentation; scene modeling; visual reasoning); Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/7806; https://ink.library.smu.edu.sg/context/sis_research/article/8809/viewcontent/TripletMining_2023_av.pdf
• Institution: Singapore Management University

Object appearances change dramatically with pose variations. This creates a challenge for embedding schemes that seek to map instances with the same object ID to locations that are as close as possible. This issue becomes significantly heightened in complex computer vision tasks such as re-identification(reID). In this paper, we suggest that these dramatic appearance changes are indications that an object ID is composed of multiple natural groups, and it is counterproductive to forcefully map instances from different groups to a common location. This leads us to introduce Relation Preserving Triplet Mining (RPTM), a feature matching guided triplet mining scheme, that ensures that triplets will respect the natural subgroupings within an object ID. We use this triplet mining mechanism to establish a pose-aware, well-conditioned triplet loss by implicitly enforcing view consistency. This allows a single network to be trained with fixed parameters across datasets, while providing state-of-the-art results. Code is available at https://github.com/adhirajghosh/RPTM_reid.