paper-with-me

Papers

DMRNet++: Learning Discriminative Features with Decoupled Networks and Enriched Pairs for One-Step Person Search

2022-11-10 · IEEE Transactions on Pattern Analysis and Machine Intelligence 2022 11 · Chuchu Han, Zhedong Zheng, Kai Su, Dongdong Yu, Zehuan Yuan, Changxin Gao, Nong Sang, Yi Yang

Person search aims at localizing and recognizing query persons from raw video frames, which is a combination of two sub-tasks, i.e., pedestrian detection and person re-identification. The dominant fashion is termed as the one-step person search that jointly optimizes detection and identification in a unified network, exhibiting higher efficiency. However, there remain major challenges: (i) conflicting objectives of multiple sub-tasks under the shared feature space, (ii) inconsistent memory bank caused by the limited batch size, (iii) underutilized unlabeled identities during the identification learning. To address these issues, we develop an enhanced decoupled and memory-reinforced network (DMRNet++). First, we simplify the standard tightly coupled pipelines and establish a task-decoupled framework (TDF). Second, we build a memory-reinforced mechanism (MRM), with a slow-moving average of the network to better encode the consistency of the memorized features. Third, considering the potential of unlabeled samples, we model the recognition process as semi-supervised learning. An unlabeled-aided contrastive loss (UCL) is developed to boost the identification feature learning by exploiting the aggregation of unlabeled identities. Experimentally, the proposed DMRNet++ obtains the mAP of 94.5% and 52.1% on CUHK-SYSU and PRW datasets, which exceeds most existing methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Pedestrian DetectionPerson Re-IdentificationPerson Search

Similar Papers 제목 키워드 기반

Robust Multimodal Learning via Representation Decoupling

2024-07-05 · Shicai Wei, Yang Luo, Yuji Wang, Chunbo Luo

Multimodal learning robust to missing modality has attracted increasing attention due to its practicality. Existing methods tend to address it by learning a common subspace representation for different modality combinati…

Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search

2021-02-22 · Chuchu Han, Zhedong Zheng, Changxin Gao, Nong Sang 외

The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and identification sub-tasks using …

Metric LearningMulti-Task LearningPedestrian DetectionPerson Search

Decoupled Mixup for Generalized Visual Recognition

2022-10-26 · Haozhe Liu, Wentian Zhang, Jinheng Xie, Haoqian Wu 외

Convolutional neural networks (CNN) have demonstrated remarkable performance when the training and testing data are from the same distribution. However, such trained CNN models often largely degrade on testing data which…

Exploring Modality-Aware Fusion and Decoupled Temporal Propagation for Multi-Modal Object Tracking

2026-03-10 · Shilei Wang, Pujian Lai, Dong Gao, Jifeng Ning 외 arxiv

Most existing multimodal trackers adopt uniform fusion strategies, overlooking the inherent differences between modalities. Moreover, they propagate temporal information through mixed tokens, leading to entangled and les…

Object Tracking

Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning

2025-11-05 · Liwei Luo, Shuaitengyuan Li, Dongwei Ren, Qilong Wang 외 arxiv

Recently, remarkable progress has been made in large-scale pre-trained model tuning, and inference efficiency is becoming more crucial for practical deployment. Early exiting in conjunction with multi-stage predictors, w…

parameter-efficient fine-tuning