Discriminability Distillation in Group Representation Learning
arXiv:2008.10850
Abstract
Learning group representation is a commonly concerned issue in tasks where the basic unit is a group, set, or sequence. Previously, the research community tries to tackle it by aggregating the elements in a group based on an indicator either defined by humans such as the quality and saliency, or generated by a black box such as the attention score. This article provides a more essential and explicable view. We claim the most significant indicator to show whether the group representation can be benefited from one of its element is not the quality or an inexplicable score, but the discriminability w.r.t. the model. We explicitly design the discrimiability using embedded class centroids on a proxy set. We show the discrimiability knowledge has good properties that can be distilled by a light-weight distillation network and can be generalized on the unseen target set. The whole procedure is denoted as discriminability distillation learning (DDL). The proposed DDL can be flexibly plugged into many group-based recognition tasks without influencing the original training procedures. Comprehensive experiments on various tasks have proven the effectiveness of DDL for both accuracy and efficiency. Moreover, it pushes forward the state-of-the-art results on these tasks by an impressive margin.
arXiv commentTo appear in Proceedings of the European Conference on Computer Vision (ECCV), 2020
References in corpus (15)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- In Defense of the Triplet Loss for Person Re-Identification
- The Kinetics Human Action Video Dataset
- Deep Learning Face Representation by Joint Identification-Verification
- RetinaFace: Single-stage Dense Face Localisation in the Wild
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
- Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
- FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
- SlowFast Networks for Video Recognition
- Revisiting Temporal Modeling for Video-based Person ReID
- Multicolumn Networks for Face Recognition
- Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification
- Talking Face Generation by Adversarially Disentangled Audio-Visual Representation
- Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition
- Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)