Fine-Grained Re-Identification

• URL: http://arxiv.org/abs/2011.13475v2
• Date: Mon, 22 Mar 2021 17:06:19 GMT
• Title: Fine-Grained Re-Identification
• Authors: Priyank Pathak
• Abstract summary: This paper proposes a computationally efficient fine-grained ReID model, FGReID, which is among the first models to unify image and video ReID. FGReID takes advantage of video-based pre-training and spatial feature attention to improve performance on both video and image ReID tasks.
• Score: 1.8275108630751844
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Research into the task of re-identification (ReID) is picking up momentum in computer vision for its many use cases and zero-shot learning nature. This paper proposes a computationally efficient fine-grained ReID model, FGReID, which is among the first models to unify image and video ReID while keeping the number of training parameters minimal. FGReID takes advantage of video-based pre-training and spatial feature attention to improve performance on both video and image ReID tasks. FGReID achieves state-of-the-art (SOTA) on MARS, iLIDS-VID, and PRID-2011 video person ReID benchmarks. Eliminating temporal pooling yields an image ReID model that surpasses SOTA on CUHK01 and Market1501 image person ReID benchmarks. The FGReID achieves near SOTA performance on the vehicle ReID dataset VeRi as well, demonstrating its ability to generalize. Additionally we do an ablation study analyzing the key features influencing model performance on ReID tasks. Finally, we discuss the moral dilemmas related to ReID tasks, including the potential for misuse. Code for this work is publicly available at https: //github.com/ppriyank/Fine-grained-ReIdentification.

Related papers

• Cross-video Identity Correlating for Person Re-identification Pre-training [38.43616465478059]
  We propose a Cross-video Identity-cOrrelating pre-traiNing (CION) framework. CION seeks the identity correlation from cross-video images by modeling it as a progressive multi-level denoising problem. We also contribute a model zoo named ReIDZoo to meet diverse research and application needs in this field.
  arXiv  Detail & Related papers  (2024-09-27T09:12:33Z)
• Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training [51.87027943520492]
  We present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities. Benefiting from our proposed paradigm, we first create a new large-scale person Re-ID dataset Diff-Person, which consists of over 777K images from 5,183 identities.
  arXiv  Detail & Related papers  (2024-06-10T06:26:03Z)
• Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification [62.894790379098005]
  We propose a novel instruct-ReID task that requires the model to retrieve images according to the given image or language instructions. Instruct-ReID is the first exploration of a general ReID setting, where existing 6 ReID tasks can be viewed as special cases by assigning different instructions. We propose a novel baseline model, IRM, with an adaptive triplet loss to handle various retrieval tasks within a unified framework.
  arXiv  Detail & Related papers  (2024-05-28T03:35:46Z)
• Generalizable Re-Identification from Videos with Cycle Association [60.920036335996414]
  We propose Cycle Association (CycAs) as a scalable self-supervised learning method for re-ID with low training complexity. We construct a large-scale unlabeled re-ID dataset named LMP-video, tailored for the proposed method. CycAs learns re-ID features by enforcing cycle consistency of instance association between temporally successive video frame pairs.
  arXiv  Detail & Related papers  (2022-11-07T16:21:57Z)
• Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification [10.045028405219641]
  We design an Unsupervised Pre-training framework for ReID based on the contrastive learning (CL) pipeline, dubbed UP-ReID. We introduce an intra-identity (I$2$-)regularization in the UP-ReID, which is instantiated as two constraints coming from global image aspect and local patch aspect. Our UP-ReID pre-trained model can significantly benefit the downstream ReID fine-tuning and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-12-01T07:16:37Z)
• Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization [65.50321170655225]
  We introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations. Experiments on image-based Cloth-Changing ReID benchmarks, e.g., LTCC, PRCC, Real28, and VC-Clothes, demonstrate that GI-ReID performs favorably against the state-of-the-arts.
  arXiv  Detail & Related papers  (2021-03-29T12:10:50Z)
• Unsupervised Pre-training for Person Re-identification [90.98552221699508]
  We present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" We make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation.
  arXiv  Detail & Related papers  (2020-12-07T14:48:26Z)
• ESA-ReID: Entropy-Based Semantic Feature Alignment for Person re-ID [7.978877859859102]
  Person re-identification (re-ID) is a challenging task in real-world. Besides the typical application in surveillance system, re-ID also has significant values to improve the recall rate of people identification in content video (TV or Movies) In this paper we propose an entropy based semantic feature alignment model, which takes advantages of the detailed information of the human semantic feature. Considering the uncertainty of semantic segmentation, we introduce a semantic alignment with an entropy-based mask which can reduce the negative effects of mask segmentation errors.
  arXiv  Detail & Related papers  (2020-07-09T08:56:28Z)
• Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification [51.110453988705395]
  Video-based person re-identification (Re-ID) is an important computer vision task. We introduce a new metric learning method called Attribute-aware Identity-hard Triplet Loss (AITL) To achieve a complete model of video-based person Re-ID, a multi-task framework with Attribute-driven Spatio-Temporal Attention (ASTA) mechanism is also proposed.
  arXiv  Detail & Related papers  (2020-06-13T09:15:38Z)

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.