Resolution based Feature Distillation for Cross Resolution Person Re-Identification

• URL: http://arxiv.org/abs/2109.07871v1
• Date: Thu, 16 Sep 2021 11:07:59 GMT
• Title: Resolution based Feature Distillation for Cross Resolution Person Re-Identification
• Authors: Asad Munir, Chengjin Lyu, Bart Goossens, Wilfried Philips, Christian Micheloni
• Abstract summary: Person re-identification (re-id) aims to retrieve images of same identities across different camera views. Resolution mismatch occurs due to varying distances between person of interest and cameras. We propose a Resolution based Feature Distillation (RFD) approach to overcome the problem of multiple resolutions.
• Score: 17.86505685442293
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Person re-identification (re-id) aims to retrieve images of same identities across different camera views. Resolution mismatch occurs due to varying distances between person of interest and cameras, this significantly degrades the performance of re-id in real world scenarios. Most of the existing approaches resolve the re-id task as low resolution problem in which a low resolution query image is searched in a high resolution images gallery. Several approaches apply image super resolution techniques to produce high resolution images but ignore the multiple resolutions of gallery images which is a better realistic scenario. In this paper, we introduce channel correlations to improve the learning of features from the degraded data. In addition, to overcome the problem of multiple resolutions we propose a Resolution based Feature Distillation (RFD) approach. Such an approach learns resolution invariant features by filtering the resolution related features from the final feature vectors that are used to compute the distance matrix. We tested the proposed approach on two synthetically created datasets and on one original multi resolution dataset with real degradation. Our approach improves the performance when multiple resolutions occur in the gallery and have comparable results in case of single resolution (low resolution re-id).

Related papers

• Continuous Cross-resolution Remote Sensing Image Change Detection [28.466756872079472]
  Real-world applications raise the need for cross-resolution change detection, aka, CD based on bitemporal images with different spatial resolutions. We propose scale-invariant learning to enforce the model consistently predicting HR results given synthesized samples of varying resolution differences. Our method significantly outperforms several vanilla CD methods and two cross-resolution CD methods on three datasets.
  arXiv  Detail & Related papers  (2023-05-24T04:57:24Z)
• ResFormer: Scaling ViTs with Multi-Resolution Training [100.01406895070693]
  We introduce ResFormer, a framework for improved performance on a wide spectrum of, mostly unseen, testing resolutions. In particular, ResFormer operates on replicated images of different resolutions and enforces a scale consistency loss to engage interactive information across different scales. We demonstrate, moreover, ResFormer is flexible and can be easily extended to semantic segmentation, object detection and video action recognition.
  arXiv  Detail & Related papers  (2022-12-01T18:57:20Z)
• Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection [77.3530907443279]
  We propose a novel self-supervised framework to detect objects in degraded low resolution images. Our methods has achieved superior performance compared with existing methods when facing variant degradation situations.
  arXiv  Detail & Related papers  (2022-08-05T09:36:13Z)
• Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification [49.57112924976762]
  Cross-resolution person re-identification problem aims to match low-resolution (LR) query identity images against high resolution (HR) gallery images. It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras. This paper explores an alternative SR-free paradigm to directly compare HR and LR images via a dynamic metric, which is adaptive to the resolution of a query image.
  arXiv  Detail & Related papers  (2022-07-09T03:49:51Z)
• Low Resolution Information Also Matters: Learning Multi-Resolution Representations for Person Re-Identification [37.01666917620271]
  Cross-resolution person re-ID aims to match person images captured from non-overlapped cameras. emphtextbfMulti-Resolution textbfRepresentations textbfJoint textbfLearning (textbfMRJL) Our method consists of a Resolution Reconstruction Network (RRN) and a Dual Feature Fusion Network (DFFN)
  arXiv  Detail & Related papers  (2021-05-26T16:54:56Z)
• Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification [22.104449922937338]
  Person re-identification (re-ID) tackles the problem of matching person images with the same identity from different cameras. We propose a Deep High-Resolution Pseudo-Siamese Framework (PS-HRNet) to solve the problem. Our proposed PS-HRNet improves 3.4%, 6.2%, 2.5%,1.1% and 4.2% at Rank-1 on MLR-Market-1501, MLR-CUHK03, MLR-VIPeR, MLR-DukeMTMC-reID, and CAVIAR datasets.
  arXiv  Detail & Related papers  (2021-05-25T07:45:38Z)
• Image Matching with Scale Adjustment [57.18604132027697]
  We show how to represent and extract interest points at variable scales. We devise a method allowing the comparison of two images at two different resolutions.
  arXiv  Detail & Related papers  (2020-12-10T11:03:25Z)
• Gated Fusion Network for Degraded Image Super Resolution [78.67168802945069]
  We propose a dual-branch convolutional neural network to extract base features and recovered features separately. By decomposing the feature extraction step into two task-independent streams, the dual-branch model can facilitate the training process.
  arXiv  Detail & Related papers  (2020-03-02T13:28:32Z)
• Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond [59.149653740463435]
  Person re-identification (re-ID) aims at matching images of the same person across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected. We propose a novel generative adversarial network to address cross-resolution person re-ID.
  arXiv  Detail & Related papers  (2020-02-19T07:21:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.