Progressive Multi-stage Feature Mix for Person Re-Identification

• URL: http://arxiv.org/abs/2007.08779v2
• Date: Mon, 26 Oct 2020 06:39:04 GMT
• Title: Progressive Multi-stage Feature Mix for Person Re-Identification
• Authors: Yan Zhang, Binyu He, Li Sun
• Abstract summary: CNN suffers from paying too much attention on the most salient local areas. %BDB proposes to randomly drop one block in a batch to enlarge the high response areas. 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.
• Score: 11.161336369536818
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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. %BDB proposes to randomly drop one block in a batch to enlarge the high response areas. Although BDB has achieved remarkable results, there still room for improvement. 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, 1. 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. 2. 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. 3. extensive experiments have been carried out on reID datasets such as the Market-1501, DukeMTMC-reID and CUHK03, showing that the proposed method can boost the re-identification performance significantly.

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)
• Matryoshka Multimodal Models [92.41824727506751]
  We propose M3: Matryoshka Multimodal Models, which learns to represent visual content as nested sets of visual tokens. We find that COCO-style benchmarks only need around 9 visual tokens to obtain accuracy similar to that of using all 576 tokens.
  arXiv  Detail & Related papers  (2024-05-27T17:59:56Z)
• Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification [64.36210786350568]
  We propose a novel learning framework named textbfEDITOR to select diverse tokens from vision Transformers for multi-modal object ReID. Our framework can generate more discriminative features for multi-modal object ReID.
  arXiv  Detail & Related papers  (2024-03-15T12:44:35Z)
• Exploring Diverse Representations for Open Set Recognition [51.39557024591446]
  Open set recognition (OSR) requires the model to classify samples that belong to closed sets while rejecting unknown samples during test. Currently, generative models often perform better than discriminative models in OSR. We propose a new model, namely Multi-Expert Diverse Attention Fusion (MEDAF), that learns diverse representations in a discriminative way.
  arXiv  Detail & Related papers  (2024-01-12T11:40:22Z)
• Hierarchical Forgery Classifier On Multi-modality Face Forgery Clues [61.37306431455152]
  We propose a novel Hierarchical Forgery for Multi-modality Face Forgery Detection (HFC-MFFD) The HFC-MFFD learns robust patches-based hybrid representation to enhance forgery authentication in multiple-modality scenarios. The specific hierarchical face forgery is proposed to alleviate the class imbalance problem and further boost detection performance.
  arXiv  Detail & Related papers  (2022-12-30T10:54:29Z)
• TriPINet: Tripartite Progressive Integration Network for Image Manipulation Localization [3.7359400978194675]
  We propose a tripartite progressive integration network (TriPINet) for end-to-end image manipulation localization. We develop a guided cross-modality dual-attention (gCMDA) module to fuse different types of forged clues. Extensive experiments are conducted to compare our method with state-of-the-art image forensics approaches.
  arXiv  Detail & Related papers  (2022-12-25T02:27:58Z)
• Dynamic Prototype Mask for Occluded Person Re-Identification [88.7782299372656]
  Existing methods mainly address this issue by employing body clues provided by an extra network to distinguish the visible part. We propose a novel Dynamic Prototype Mask (DPM) based on two self-evident prior knowledge. Under this condition, the occluded representation could be well aligned in a selected subspace spontaneously.
  arXiv  Detail & Related papers  (2022-07-19T03:31:13Z)
• Exploring the Diversity and Invariance in Yourself for Visual Pre-Training Task [192.74445148376037]
  Self-supervised learning methods have achieved remarkable success in visual pre-training task. These methods only focus on limited regions or the extracted features on totally different regions inside each image are nearly the same. This paper introduces Exploring the Diversity and Invariance in Yourself E-DIY.
  arXiv  Detail & Related papers  (2021-06-01T14:52:36Z)
• Diversity-Achieving Slow-DropBlock Network for Person Re-Identification [11.907116133358022]
  A big challenge of person re-identification (Re-ID) using a multi-branch network architecture is to learn diverse features from the ID-labeled dataset. The 2-branch Batch DropBlock (BDB) network was recently proposed for achieving diversity between the global branch and the feature-dropping branch. We show that the proposed method performs superior to BDB on popular person Re-ID datasets, including Market-1501, DukeMTMC-reID and CUHK03.
  arXiv  Detail & Related papers  (2020-02-09T08:05:39Z)

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.