Illumination adaptive person reid based on teacher-student model and adversarial training
Most existing works in Person Re-identification (ReID) focus on settings where illumination either is kept the same or has very little fluctuation. However, the changes in the illumination degree may affect the robustness of a ReID algorithm significantly. To address this problem, we proposed a Two-Stream Network that can separate ReID features from lighting features to enhance ReID performance. Its innovations are threefold: (1) A discriminative entropy loss to ensure the ReID features contain no lighting information. (2) A ReID Teacher model trained by images under "neutral" lighting conditions to guide ReID classification. (3) An illumination Teacher model trained by the differences between the illumination-adjusted and original images to guide illumination classification. We construct two augmented datasets by synthetically changing a set of predefined lighting conditions in two of the most popular ReID benchmarks: Market1501 and DukeMTMC-ReID. Experiments demonstrate that our algorithm outperforms other state-of-the-art works and particularly potent in handling images under extremely low light.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationPerson Re-IdentificationSimilar Papers 제목 키워드 기반
RGB-IR Cross-modality Person ReID based on Teacher-Student GAN Model
RGB-Infrared (RGB-IR) person re-identification (ReID) is a technology where the system can automatically identify the same person appearing at different parts of a video when light is unavailable. The critical challenge …
Generative Adversarial NetworkPerson Re-IdentificationIllumination-Adaptive Person Re-identification
Most person re-identification (ReID) approaches assume that person images are captured under relatively similar illumination conditions. In reality, long-term person retrieval is common, and person images are often captu…
DisentanglementPerson Re-IdentificationPerson RetrievalRetrievalLearning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification
Unsupervised domain adaptive (UDA) person re-identification (ReID) has gained increasing attention for its effectiveness on the target domain without manual annotations. Most fine-tuning based UDA person ReID methods foc…
Unsupervised Domain AdaptationUnsupervised Domain AdaptationnUnsupervised Domain Adaptation on Duke to MarketUnsupervised Domain Adaptation on Market to DukePart Representation Learning with Teacher-Student Decoder for Occluded Person Re-identification
Occluded person re-identification (ReID) is a very challenging task due to the occlusion disturbance and incomplete target information. Leveraging external cues such as human pose or parsing to locate and align part feat…
DecoderHuman ParsingLong-range modelingOccluded Person Re-Identification+2Graph Consistency Based Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification
Recent works show that mean-teaching is an effective framework for unsupervised domain adaptive person re-identification. However, existing methods perform contrastive learning on selected samples between teacher and stu…
Contrastive LearningDomain Adaptive Person Re-IdentificationPerson Re-IdentificationRepresentation Learning