Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
arXiv:2105.12355
Abstract
Recent years have witnessed significant progress in person re-identification (ReID). However, current ReID approaches still suffer from considerable performance degradation when unseen testing domains exhibit different characteristics from the source training ones, known as the domain generalization problem. Given multiple source training domains, previous Domain Generalizable ReID (DG-ReID) methods usually learn all domains together using a shared network, which can't learn sufficient knowledge from each domain. In this paper, we propose a novel Multiple Domain Experts Collaborative Learning (MECL) framework for better exploiting all training domains, which benefits from the proposed Domain-Domain Collaborative Learning (DDCL) and Universal-Domain Collaborative Learning (UDCL). DDCL utilizes domain-specific experts for fully exploiting each domain, and prevents experts from over-fitting the corresponding domain using a meta-learning strategy. In UDCL, a universal expert supervises the learning of domain experts and continuously gathers knowledge from all domain experts. Note, only the universal expert will be used for inference. Extensive experiments on DG-ReID benchmarks demonstrate the effectiveness of DDCL and UDCL, and show that the whole MECL framework significantly outperforms state-of-the-arts. Experimental results on DG-classification benchmarks also reveal the great potential of applying MECL to other DG tasks.
arXiv commentupdate the mAP results, and add the experiments on DG-classification task
References in corpus (20)
- Adam: A Method for Stochastic Optimization
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Distilling the Knowledge in a Neural Network
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Bootstrap your own latent: A new approach to self-supervised Learning
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Domain Generalization via Invariant Feature Representation
- Domain Generalization via Model-Agnostic Learning of Semantic Features
- Exploring Simple Siamese Representation Learning
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
- Domain Generalization by Marginal Transfer Learning
- In Search of Lost Domain Generalization
- Contrastive Representation Distillation
- Domain Generalization with MixStyle
- Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
- Augmented Hard Example Mining for Generalizable Person Re-Identification
- Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice
- Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
- Meta Batch-Instance Normalization for Generalizable Person Re-Identification