paper-with-me

홈 › Papers

Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation

2018-12-07 · Idoia Ruiz, Bogdan Raducanu, Rakesh Mehta, Jaume Amores

Finding a person across a camera network plays an important role in video surveillance. For a real-world person re-identification application, in order to guarantee an optimal time response, it is crucial to find the balance between accuracy and speed. We analyse this trade-off, comparing a classical method, that comprises hand-crafted feature description and metric learning, in particular, LOMO and XQDA, to deep learning based techniques, using image classification networks, ResNet and MobileNets. Additionally, we propose and analyse network distillation as a learning strategy to reduce the computational cost of the deep learning approach at test time. We evaluate both methods on the Market-1501 and DukeMTMC-reID large-scale datasets, showing that distillation helps reducing the computational cost at inference time while even increasing the accuracy performance.

📄 PDF Abstract BibTeX arXiv:1812.02937

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningGeneral Classificationimage-classificationImage ClassificationKnowledge DistillationMetric LearningPerson Re-Identification

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

A Little Bit Attention Is All You Need for Person Re-Identification

2023-02-28 · Markus Eisenbach, Jannik Lübberstedt, Dustin Aganian, Horst-Michael Gross

Person re-identification plays a key role in applications where a mobile robot needs to track its users over a long period of time, even if they are partially unobserved for some time, in order to follow them or be avail…

AllNeural Architecture SearchPerson Re-Identification

A Multi-task Joint Framework for Real-time Person Search

2020-12-11 · Ye Li, Kangning Yin, Jie Liang, Chunyu Wang 외

Person search generally involves three important parts: person detection, feature extraction and identity comparison. However, person search integrating detection, extraction and comparison has the following drawbacks. F…

Human DetectionPerson Search

Distance-based Camera Network Topology Inference for Person Re-identification

2017-12-01 · Yeong-Jun Cho, Kuk-Jin Yoon

In this paper, we propose a novel distance-based camera network topology inference method for efficient person re-identification. To this end, we first calibrate each camera and estimate relative scales between cameras. …

Person Re-Identification

EnviroLLM: Resource Tracking and Optimization for Local AI

2025-12-12 · Troy Allen arxiv

Large language models (LLMs) are increasingly deployed locally for privacy and accessibility, yet users lack tools to measure their resource usage, environmental impact, and efficiency metrics. This paper presents Enviro…

Towards Privacy-Preserving Person Re-identification via Person Identify Shift

2022-07-15 · Shuguang Dou, Xinyang Jiang, Qingsong Zhao, Dongsheng Li 외

Recently privacy concerns of person re-identification (ReID) raise more and more attention and preserving the privacy of the pedestrian images used by ReID methods become essential. De-identification (DeID) methods allev…

De-identificationPerson Re-IdentificationPrivacy Preserving