TransReID: Transformer-based Object Re-Identification

Extracting robust feature representation is one of the key challenges in object re-identification (ReID). Although convolution neural network (CNN)-based methods have achieved great success, they only process one local neighborhood at a time and suffer from information loss on details caused by convolution and downsampling operators (e.g. pooling and strided convolution). To overcome these limitations, we propose a pure transformer-based object ReID framework named TransReID. Specifically, we first encode an image as a sequence of patches and build a transformer-based strong baseline with a few critical improvements, which achieves competitive results on several ReID benchmarks with CNN-based methods. To further enhance the robust feature learning in the context of transformers, two novel modules are carefully designed. (i) The jigsaw patch module (JPM) is proposed to rearrange the patch embeddings via shift and patch shuffle operations which generates robust features with improved discrimination ability and more diversified coverage. (ii) The side information embeddings (SIE) is introduced to mitigate feature bias towards camera/view variations by plugging in learnable embeddings to incorporate these non-visual clues. To the best of our knowledge, this is the first work to adopt a pure transformer for ReID research. Experimental results of TransReID are superior promising, which achieve state-of-the-art performance on both person and vehicle ReID benchmarks.

PDF Abstract ICCV 2021 PDF ICCV 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Person Re-Identification DukeMTMC-reID TransReID (w/o RK) Rank-1 91.1 # 22
mAP 82.1 # 28
Person Re-Identification Market-1501 TransReID (w/o RK) Rank-1 95.2 # 51
mAP 89.5 # 43
Person Re-Identification Market-1501-C TransReID Rank-1 53.19 # 1
mAP 27.38 # 1
mINP 1.98 # 1
Person Re-Identification MSMT17 TransReID Rank-1 86.20 # 11
mAP 69.40 # 10
Vehicle Re-Identification VeRi-776 TransReID mAP 82.3 # 5
Rank-1 97.1 # 3