Sorry, you need to enable JavaScript to visit this website.

PROGRESSIVE MULTI-STAGE FEATURE MIX FOR PERSON RE-IDENTIFICATION

Citation Author(s):
Submitted by:
Yan Zhang
Last updated:
22 June 2021 - 11:18am
Document Type:
Poster
Document Year:
Event:

Abstract 

up
0 users have voted:

Comments

Image features from a small local region often give strong evidence in person re-identification task. However, CNN suffers from paying too much attention on the most salient local areas, thus ignoring other discriminative clues, e.g., hair, shoes or logos on clothes. In this work, we propose a Progressive Multi-stage feature Mix network (PMM), which enables the model to find out the more precise and diverse features in a progressive manner. Specifically, (i) to enforce the model to look for different clues in the image, we adopt a multi-stage classifier and expect that the model is able to focus on a complementary region in each stage. (ii) we propose an Attentive feature Hard-Mix (A-Hard-Mix) to replace the salient feature blocks by the negative example in the current batch, whose label is different from the current sample. (iii) extensive experiments have been carried out on reID datasets such as the Market-1501, DukeMTMCreID and CUHK03, showing that the proposed method can boost the re-identification performance significantly.

Dataset Files

poster_0420.pdf

(73)

slides.pdf

(58)