paper-with-me

홈 › Papers

Self-training with progressive augmentation for unsupervised cross-domain person re-identification

2019-07-31 · ICCV 2019 10 · Xin-Yu Zhang, Jiewei Cao, Chunhua Shen, Mingyu You

Person re-identification (Re-ID) has achieved great improvement with deep learning and a large amount of labelled training data. However, it remains a challenging task for adapting a model trained in a source domain of labelled data to a target domain of only unlabelled data available. In this work, we develop a self-training method with progressive augmentation framework (PAST) to promote the model performance progressively on the target dataset. Specially, our PAST framework consists of two stages, namely, conservative stage and promoting stage. The conservative stage captures the local structure of target-domain data points with triplet-based loss functions, leading to improved feature representations. The promoting stage continuously optimizes the network by appending a changeable classification layer to the last layer of the model, enabling the use of global information about the data distribution. Importantly, we propose a new self-training strategy that progressively augments the model capability by adopting conservative and promoting stages alternately. Furthermore, to improve the reliability of selected triplet samples, we introduce a ranking-based triplet loss in the conservative stage, which is a label-free objective function basing on the similarities between data pairs. Experiments demonstrate that the proposed method achieves state-of-the-art person Re-ID performance under the unsupervised cross-domain setting. Code is available at: https://tinyurl.com/PASTReID

📄 PDF Abstract BibTeX arXiv:1907.13315

Code (1)

zhangxinyu-xyz/PAST-ReID pytorch

Tasks

Person Re-IdentificationTripletUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Similar Papers 제목 키워드 기반

SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning

2020-09-16 · CVPR 2021 1 · Colorado J Reed, Sean Metzger, Aravind Srinivas, Trevor Darrell 외

A common practice in unsupervised representation learning is to use labeled data to evaluate the quality of the learned representations. This supervised evaluation is then used to guide critical aspects of the training p…

Data AugmentationRepresentation LearningSelf-Supervised Learning

Unsupervised Domain Adaptation with Progressive Domain Augmentation

2020-04-03 · Kevin Hua, Yuhong Guo

Domain adaptation aims to exploit a label-rich source domain for learning classifiers in a different label-scarce target domain. It is particularly challenging when there are significant divergences between the two domai…

Domain AdaptationUnsupervised Domain Adaptation

MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection

2023-02-09 · Yuhe Ding, Jian Liang, Bo Jiang, Aihua Zheng 외

Existing cross-domain keypoint detection methods always require accessing the source data during adaptation, which may violate the data privacy law and pose serious security concerns. Instead, this paper considers a real…

Data AugmentationKeypoint Detection

Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding

2022-10-06 · Guofeng Mei, Cristiano Saltori, Fabio Poiesi, Jian Zhang 외

Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods. However, data augmentation is not ideal as it requires a careful selection of th…

3D Object ClassificationContrastive LearningData AugmentationPseudo Label+1

UXLA: A Robust Unsupervised Data Augmentation Framework for Zero-Resource Cross-Lingual NLP

2020-04-28 · ACL 2021 5 · M Saiful Bari, Tasnim Mohiuddin, Shafiq Joty

Transfer learning has yielded state-of-the-art (SoTA) results in many supervised NLP tasks. However, annotated data for every target task in every target language is rare, especially for low-resource languages. We propos…

Cross-Lingual TransferData AugmentationNamed Entity Recognition (NER)Natural Language Inference+2