paper-with-me

홈 › Papers

Generalizing A Person Retrieval Model Hetero- and Homogeneously

2018-09-01 · ECCV 2018 9 · Zhun Zhong, Liang Zheng, Shaozi Li, Yi Yang

Person re-identification (re-ID) poses unique challenges for unsupervised domain adaptation (UDA) in that classes in the source and target sets (domains) are entirely different and that image variations are largely caused by cameras. Given a labeled source training set and an unlabeled target training set, we aim to improve the generalization ability of re-ID models on the target testing set. To this end, we introduce a Hetero-Homogeneous Learning (HHL) method. Our method enforces two properties simultaneously: 1) camera invariance, learned via positive pairs formed by unlabeled target images and their camera style transferred counterparts; 2) domain connectedness, by regarding source / target images as negative matching pairs to the target / source images. The first property is implemented by homogeneous learning because training pairs are collected from the same domain. The second property is achieved by heterogeneous learning because we sample training pairs from both the source and target domains. On Market-1501, DukeMTMC-reID and CUHK03, we show that the two properties contribute indispensably and that very competitive re-ID UDA accuracy is achieved. Code is available at: https://github.com/zhunzhong07/HHL

📄 PDF Abstract BibTeX

Code (1)

zhunzhong07/HHL 공식 구현 pytorch

Tasks

Domain AdaptationmodelPerson Re-IdentificationPerson RetrievalRetrievalUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings

2026-05-11 · Byeongchan Kim, Arijit Sehanobish, Avinava Dubey, Min-hwan Oh 외 arxiv

We present a new class of efficient attention mechanisms applying universal 3D Relative Positional Encoding (RPE) methods given by arbitrary integrable modulation functions $f$. They lead to the new class of 3D-Transform…

Point Clouds

Heterogeneous Responses to the U.S. Narrative Tax Changes: Evidence from the U.S. States

2021-07-29 · Masud Alam

This paper investigates the assumption of homogeneous effects of federal tax changes across the U.S. states and identifies where and why that assumption may not be valid. More specifically, what determines the transmissi…

valid

Text-based Aerial-Ground Person Retrieval

2025-11-11 · Xinyu Zhou, Yu Wu, Jiayao Ma, Wenhao Wang 외 arxiv

This work introduces Text-based Aerial-Ground Person Retrieval (TAG-PR), which aims to retrieve person images from heterogeneous aerial and ground views with textual descriptions. Unlike traditional Text-based Person Ret…

Person RetrievalText Generation

Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization

2026-04-24 · Hefeng Zhou, Xuan Liu, Sicheng Chen, Wutong Zhang 외 arxiv

Federated cross-modal retrieval faces severe challenges from heterogeneous client data, particularly non-IID semantic distributions and missing modalities. Under such heterogeneity, a single global model is often insuffi…

Cross-Modal Retrieval

A Silicon Photonic Accelerator for Convolutional Neural Networks with Heterogeneous Quantization

2022-05-17 · Febin Sunny, Mahdi Nikdast, Sudeep Pasricha

Parameter quantization in convolutional neural networks (CNNs) can help generate efficient models with lower memory footprint and computational complexity. But, homogeneous quantization can result in significant degradat…

Quantization