Feature Erasing and Diffusion Network for Occluded Person Re-Identification

• URL: http://arxiv.org/abs/2112.08740v1
• Date: Thu, 16 Dec 2021 09:47:17 GMT
• Title: Feature Erasing and Diffusion Network for Occluded Person Re-Identification
• Authors: Zhikang Wang, Feng Zhu, Shixiang Tang, Rui Zhao, Lihuo He, Jiangning Song
• Abstract summary: Occluded person re-identification aims at matching occluded person images to holistic ones across different camera views. Previous methods mainly focus on increasing model's robustness against NPO while ignoring feature contamination from NTP. We propose a novel Feature Erasing and Diffusion Network (FED) to simultaneously handle NPO and NTP.
• Score: 20.720999782234216
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Occluded person re-identification (ReID) aims at matching occluded person images to holistic ones across different camera views. Target Pedestrians (TP) are usually disturbed by Non-Pedestrian Occlusions (NPO) and NonTarget Pedestrians (NTP). Previous methods mainly focus on increasing model's robustness against NPO while ignoring feature contamination from NTP. In this paper, we propose a novel Feature Erasing and Diffusion Network (FED) to simultaneously handle NPO and NTP. Specifically, NPO features are eliminated by our proposed Occlusion Erasing Module (OEM), aided by the NPO augmentation strategy which simulates NPO on holistic pedestrian images and generates precise occlusion masks. Subsequently, we Subsequently, we diffuse the pedestrian representations with other memorized features to synthesize NTP characteristics in the feature space which is achieved by a novel Feature Diffusion Module (FDM) through a learnable cross attention mechanism. With the guidance of the occlusion scores from OEM, the feature diffusion process is mainly conducted on visible body parts, which guarantees the quality of the synthesized NTP characteristics. By jointly optimizing OEM and FDM in our proposed FED network, we can greatly improve the model's perception ability towards TP and alleviate the influence of NPO and NTP. Furthermore, the proposed FDM only works as an auxiliary module for training and will be discarded in the inference phase, thus introducing little inference computational overhead. Experiments on occluded and holistic person ReID benchmarks demonstrate the superiority of FED over state-of-the-arts, where FED achieves 86.3% Rank-1 accuracy on Occluded-REID, surpassing others by at least 4.7%.

Related papers

• Augmented Neural Fine-Tuning for Efficient Backdoor Purification [16.74156528484354]
  Recent studies have revealed the vulnerability of deep neural networks (DNNs) to various backdoor attacks. We propose Neural mask Fine-Tuning (NFT) with an aim to optimally re-organize the neuron activities. NFT relaxes the trigger synthesis process and eliminates the requirement of the adversarial search module.
  arXiv  Detail & Related papers  (2024-07-14T02:36:54Z)
• Feature Attenuation of Defective Representation Can Resolve Incomplete Masking on Anomaly Detection [1.0358639819750703]
  In unsupervised anomaly detection (UAD) research, it is necessary to develop a computationally efficient and scalable solution. We revisit the reconstruction-by-inpainting approach and rethink to improve it by analyzing strengths and weaknesses. We propose Feature Attenuation of Defective Representation (FADeR) that only employs two layers which attenuates feature information of anomaly reconstruction.
  arXiv  Detail & Related papers  (2024-07-05T15:44:53Z)
• DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery [71.6345505427213]
  DPMesh is an innovative framework for occluded human mesh recovery. It capitalizes on the profound diffusion prior about object structure and spatial relationships embedded in a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-04-01T18:59:13Z)
• Open-Set Face Recognition with Maximal Entropy and Objectosphere Loss [7.710785884166695]
  This work concentrates on watchlists, an open-set task that is expected to operate at a low False Positive Identification Rate. We introduce a compact adapter network that benefits from additional negative face images when combined with distinct cost functions. The proposed approach adopts pre-trained deep neural networks (DNNs) for face recognition as feature extractors.
  arXiv  Detail & Related papers  (2023-11-01T09:52:02Z)
• Improving Neural Additive Models with Bayesian Principles [54.29602161803093]
  Neural additive models (NAMs) enhance the transparency of deep neural networks by handling calibrated input features in separate additive sub-networks. We develop Laplace-approximated NAMs (LA-NAMs) which show improved empirical performance on datasets and challenging real-world medical tasks.
  arXiv  Detail & Related papers  (2023-05-26T13:19:15Z)
• OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks [7.797299214812479]
  Occlusion is a prevalent and easily realizable semantic perturbation to deep neural networks (DNNs) It can fool a DNN into misclassifying an input image by occluding some segments, possibly resulting in severe errors. Most existing robustness verification approaches for DNNs are focused on non-semantic perturbations.
  arXiv  Detail & Related papers  (2023-01-27T18:54:00Z)
• AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network [60.650035708621786]
  Blind-spot network (BSN) and its variants have made significant advances in self-supervised denoising. It is challenging to deal with spatially correlated real-world noise using self-supervised BSN. Recently, pixel-shuffle downsampling (PD) has been proposed to remove the spatial correlation of real-world noise. We propose an Asymmetric PD (AP) to address this issue, which introduces different PD stride factors for training and inference.
  arXiv  Detail & Related papers  (2022-03-22T15:04:37Z)
• Quality-aware Part Models for Occluded Person Re-identification [77.24920810798505]
  Occlusion poses a major challenge for person re-identification (ReID) Existing approaches typically rely on outside tools to infer visible body parts, which may be suboptimal in terms of both computational efficiency and ReID accuracy. We propose a novel method named Quality-aware Part Models (QPM) for occlusion-robust ReID.
  arXiv  Detail & Related papers  (2022-01-01T03:51:09Z)
• Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning [54.15303628138665]
  Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks. Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance. We propose Dual Spoof Disentanglement Generation framework to tackle this challenge by "anti-spoofing via generation"
  arXiv  Detail & Related papers  (2021-12-01T15:36:59Z)
• NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection [39.417540296897194]
  We propose a novel NMS-Loss making the NMS procedure can be trained end-to-end without any additional network parameters. Our NMS-Loss punishes two cases when FP is not suppressed and FN is wrongly eliminated by NMS. With the help of NMS-Loss, our detector, namely NMS-Ped, achieves impressive results with Miss Rate of 5.92% on Caltech dataset and 10.08% on CityPersons dataset.
  arXiv  Detail & Related papers  (2021-06-04T12:06:46Z)
• End-to-End Object Detection with Fully Convolutional Network [71.56728221604158]
  We introduce a Prediction-aware One-To-One (POTO) label assignment for classification to enable end-to-end detection. A simple 3D Max Filtering (3DMF) is proposed to utilize the multi-scale features and improve the discriminability of convolutions in the local region. Our end-to-end framework achieves competitive performance against many state-of-the-art detectors with NMS on COCO and CrowdHuman datasets.
  arXiv  Detail & Related papers  (2020-12-07T09:14:55Z)

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.