TL;DR
This paper introduces a Locally Aware Transformer for person re-identification that leverages local tokens and blockwise fine-tuning, achieving state-of-the-art accuracy on benchmark datasets.
Contribution
The paper proposes a novel LA-Transformer architecture that utilizes local tokens and ensemble classification, along with blockwise fine-tuning, to improve re-ID accuracy.
Findings
Achieves 98.27% rank-1 accuracy on Market-1501
Achieves 98.7% rank-1 accuracy on CUHK03
Outperforms existing state-of-the-art methods
Abstract
Person Re-Identification is an important problem in computer vision-based surveillance applications, in which the same person is attempted to be identified from surveillance photographs in a variety of nearby zones. At present, the majority of Person re-ID techniques are based on Convolutional Neural Networks (CNNs), but Vision Transformers are beginning to displace pure CNNs for a variety of object recognition tasks. The primary output of a vision transformer is a global classification token, but vision transformers also yield local tokens which contain additional information about local regions of the image. Techniques to make use of these local tokens to improve classification accuracy are an active area of research. We propose a novel Locally Aware Transformer (LA-Transformer) that employs a Parts-based Convolution Baseline (PCB)-inspired strategy for aggregating globally enhanced…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsMulti-Head Attention · Attention Is All You Need · Linear Layer · Attentive Walk-Aggregating Graph Neural Network · Absolute Position Encodings · Position-Wise Feed-Forward Layer · Byte Pair Encoding · Adam · Label Smoothing · Residual Connection
