Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning
This work considers the problem of domain shift in person re-identification.Being trained on one dataset, a re-identification model usually performs much worse on unseen data. Partially this gap is caused by the relatively small scale of person re-identification datasets (compared to face recognition ones, for instance), but it is also related to training objectives. We propose to use the metric learning objective, namely AM-Softmax loss, and some additional training practices to build well-generalizing, yet, computationally efficient models. We use recently proposed Omni-Scale Network (OSNet) architecture combined with several training tricks and architecture adjustments to obtain state-of-the art results in cross-domain generalization problem on a large-scale MSMT17 dataset in three setups: MSMT17-all->DukeMTMC, MSMT17-train->Market1501 and MSMT17-all->Market1501.
Code (1)
Tasks
Domain GeneralizationFace RecognitionMetric LearningPerson Re-IdentificationSimilar Papers 제목 키워드 기반
Generalizing Person Re-Identification by Camera-Aware Invariance Learning and Cross-Domain Mixup
Despite the impressive performance under the single-domain setup, current fully-supervised models for person re-identification (re-ID) degrade significantly when deployed to an unseen domain. According to the characteris…
Person Re-IdentificationFrustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice
Contemporary person re-identification (\reid) methods usually require access to data from the deployment camera network during training in order to perform well. This is because contemporary \reid{} models trained on one…
Person Re-IdentificationContinual Person Identification using Footstep-Induced Floor Vibrations on Heterogeneous Floor Structures
Person identification is important for smart buildings to provide personalized services such as health monitoring, activity tracking, and personnel management. However, previous person identification relies on pre-collec…
Person IdentificationUnveiling personnel movement in a larger indoor area with a non-overlapping multi-camera system
Surveillance cameras are widely applied for indoor occupancy measurement and human movement perception, which benefit for building energy management and social security. To address the challenges of limited view angle of…
energy managementManagementPerson Re-IdentificationCombined Depth Space based Architecture Search For Person Re-identification
Most works on person re-identification (ReID) take advantage of large backbone networks such as ResNet, which are designed for image classification instead of ReID, for feature extraction. However, these backbones may no…
image-classificationImage ClassificationPerson Re-IdentificationTriplet