PSF-C-Net: A Counterfactual Deep Learning Model for Person Re-Identification Based on Random Cropping Patch and Shuffling Filling
Open Access
- 24 June 2024
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 12 (13) , 1957
Abstract
In the task of person re-identification (re-ID), capturing the long-range dependency of instances is crucial for accurate identification. The existing methods excel at extracting local features but often overlook the global information of instance images. To address this limitation, we propose a convolution-based counterfactual learning framework, called PSF-C-Net, to focus on global information rather than local detailed features. PSF-C-Net adopts a parameter-sharing dual-path structure to perform counterfactual operations in the prediction space. It takes both the actual instance image and a counterfactual instance image that disrupts the contextual relationship as the input. The counterfactual framework enables the interpretable modeling of global features without introducing additional parameters. Additionally, we propose a novel method for generating counterfactual instance images, which effectively constructs an explicit counterfactual space, to reliably implement counterfactual strategies. We have conducted extensive experiments to evaluate the performance of PSF-C-Net on the Market-1501 and Duke-MTMC-reID datasets. The results demonstrate that PSF-C-Net achieves state-of-the-art performance.Keywords
This publication has 45 references indexed in Scilit:
- RandoMix: a mixed sample data augmentation method with multiple mixed modesMultimedia Tools and Applications, 2024
- CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models2021
- Graph-based Person Signature for Person Re-Identifications2021
- Self-augmentation: Generalizing deep networks to unseen classes for few-shot learningNeural Networks, 2021
- Style Normalization and Restitution for Generalizable Person Re-Identification2020
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features2019
- Bag of Tricks and a Strong Baseline for Deep Person Re-Identification2019
- Joint Discriminative and Generative Learning for Person Re-Identification2019
- SphereReID: Deep hypersphere manifold embedding for person re-identificationJournal of Visual Communication and Image Representation, 2019
- Deep Transfer Learning for Person Re-Identification2018