Adaptive Exploration for Unsupervised Person Re-Identification

Abstract

Due to domain bias, directly deploying a deep person re-identification (re-ID) model trained on one dataset often achieves considerably poor accuracy on another dataset. In this paper, we propose an Adaptive Exploration (AE) method to address the domain-shift problem for re-ID in an unsupervised manner. Specifically, in the target domain, the re-ID model is inducted to 1) maximize distances between all person images and 2) minimize distances between similar person images. In the first case, by treating each person image as an individual class, a non-parametric classifier with a feature memory is exploited to encourage person images to move far away from each other. In the second case, according to a similarity threshold, our method adaptively selects neighborhoods for each person image in the feature space. By treating these similar person images as the same class, the non-parametric classifier forces them to stay closer. However, a problem of the adaptive selection is that, when an image has too many neighborhoods, it is more likely to attract other images as its neighborhoods. As a result, a minority of images may select a large number of neighborhoods while a majority of images have only a few neighborhoods. To address this issue, we additionally integrate a balance strategy into the adaptive selection. We evaluate our methods with two protocols. The first one is called "target-only re-ID", in which only the unlabeled target data is used for training. The second one is called "domain adaptive re-ID", in which both the source data and the target data are used during training. Experimental results on large-scale re-ID datasets demonstrate the effectiveness of our method. Our code has been released at https://github.com/dyh127/Adaptive-Exploration-for-Unsupervised-Person-Re-Identification.

arXiv commentACM Transactions on Multimedia Computing, Communications and Application (TOMCCAP)

References in corpus (12)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• In Defense of the Triplet Loss for Person Re-Identification
• A Discriminatively Learned CNN Embedding for Person Re-identification
• Random Erasing Data Augmentation
• End-to-End Comparative Attention Networks for Person Re-identification
• Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder
• Deep Ranking for Person Re-identification via Joint Representation Learning
• Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classification
• Adaptive Exploration for Unsupervised Person Re-Identification
• Joint Discriminative and Generative Learning for Person Re-identification
• Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
• Person Search via A Mask-Guided Two-Stream CNN Model

Cited by in corpus (16)

• VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
• Adaptive Exploration for Unsupervised Person Re-Identification
• Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series
• Parameter-Efficient Person Re-identification in the 3D Space
• Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation
• Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
• Receptive Multi-granularity Representation for Person Re-Identification
• Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
• Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification
• Semantics-Guided Clustering with Deep Progressive Learning for Semi-Supervised Person Re-identification
• Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification
• IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
• Viewpoint-aware Progressive Clustering for Unsupervised Vehicle Re-identification
• CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion
• Towards Precise Intra-camera Supervised Person Re-identification
• Unsupervised Domain Adaptation Network with Category-Centric Prototype Aligner for Biomedical Image Segmentation