Towards Generalizable Person Re-identification with a Bi-stream
Generative Model
- URL: http://arxiv.org/abs/2206.09362v1
- Date: Sun, 19 Jun 2022 09:18:25 GMT
- Title: Towards Generalizable Person Re-identification with a Bi-stream
Generative Model
- Authors: Xin Xu, Wei Liu, Zheng Wang, Ruiming Hu, Qi Tian
- Abstract summary: We propose a Bi-stream Generative Model (BGM) to learn the fine-grained representations fused with camera-invariant global feature and pedestrian-aligned local feature.
Our method outperforms the state-of-the-art methods on the large-scale generalizable re-ID benchmarks.
- Score: 81.0989316825134
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Generalizable person re-identification (re-ID) has attracted growing
attention due to its powerful adaptation capability in the unseen data domain.
However, existing solutions often neglect either crossing cameras (e.g.,
illumination and resolution differences) or pedestrian misalignments (e.g.,
viewpoint and pose discrepancies), which easily leads to poor generalization
capability when adapted to the new domain. In this paper, we formulate these
difficulties as: 1) Camera-Camera (CC) problem, which denotes the various human
appearance changes caused by different cameras; 2) Camera-Person (CP) problem,
which indicates the pedestrian misalignments caused by the same identity person
under different camera viewpoints or changing pose. To solve the above issues,
we propose a Bi-stream Generative Model (BGM) to learn the fine-grained
representations fused with camera-invariant global feature and
pedestrian-aligned local feature, which contains an encoding network and two
stream decoding sub-networks. Guided by original pedestrian images, one stream
is employed to learn a camera-invariant global feature for the CC problem via
filtering cross-camera interference factors. For the CP problem, another stream
learns a pedestrian-aligned local feature for pedestrian alignment using
information-complete densely semantically aligned part maps. Moreover, a
part-weighted loss function is presented to reduce the influence of missing
parts on pedestrian alignment. Extensive experiments demonstrate that our
method outperforms the state-of-the-art methods on the large-scale
generalizable re-ID benchmarks, involving domain generalization setting and
cross-domain setting.
Related papers
- ChangeBind: A Hybrid Change Encoder for Remote Sensing Change Detection [16.62779899494721]
Change detection (CD) is a fundamental task in remote sensing (RS) which aims to detect the semantic changes between the same geographical regions at different time stamps.
We propose an effective Siamese-based framework to encode the semantic changes occurring in the bi-temporal RS images.
arXiv Detail & Related papers (2024-04-26T17:47:14Z) - Domain-adaptive Person Re-identification without Cross-camera Paired
Samples [12.041823465553875]
Cross-camera pedestrian samples collected from long-distance scenes often have no positive samples.
It is extremely challenging to use cross-camera negative samples to achieve cross-region pedestrian identity matching.
A novel domain-adaptive person re-ID method that focuses on cross-camera consistent discriminative feature learning is proposed.
arXiv Detail & Related papers (2023-07-13T02:42:28Z) - Occluded Person Re-Identification via Relational Adaptive Feature
Correction Learning [8.015703163954639]
Occluded person re-identification (Re-ID) in images captured by multiple cameras is challenging because the target person is occluded by pedestrians or objects.
Most existing methods utilize the off-the-shelf pose or parsing networks as pseudo labels, which are prone to error.
We propose a novel Occlusion Correction Network (OCNet) that corrects features through relational-weight learning and obtains diverse and representative features without using external networks.
arXiv Detail & Related papers (2022-12-09T07:48:47Z) - Cross-modal Local Shortest Path and Global Enhancement for
Visible-Thermal Person Re-Identification [2.294635424666456]
We propose the Cross-modal Local Shortest Path and Global Enhancement (CM-LSP-GE) modules,a two-stream network based on joint learning of local and global features.
The experimental results on two typical datasets show that our model is obviously superior to the most state-of-the-art methods.
arXiv Detail & Related papers (2022-06-09T10:27:22Z) - AF$_2$: Adaptive Focus Framework for Aerial Imagery Segmentation [86.44683367028914]
Aerial imagery segmentation has some unique challenges, the most critical one among which lies in foreground-background imbalance.
We propose Adaptive Focus Framework (AF$), which adopts a hierarchical segmentation procedure and focuses on adaptively utilizing multi-scale representations.
AF$ has significantly improved the accuracy on three widely used aerial benchmarks, as fast as the mainstream method.
arXiv Detail & Related papers (2022-02-18T10:14:45Z) - Cross-Camera Feature Prediction for Intra-Camera Supervised Person
Re-identification across Distant Scenes [70.30052164401178]
Person re-identification (Re-ID) aims to match person images across non-overlapping camera views.
ICS-DS Re-ID uses cross-camera unpaired data with intra-camera identity labels for training.
Cross-camera feature prediction method to mine cross-camera self supervision information.
Joint learning of global-level and local-level features forms a global-local cross-camera feature prediction scheme.
arXiv Detail & Related papers (2021-07-29T11:27:50Z) - Looking Twice for Partial Clues: Weakly-supervised Part-Mentored
Attention Network for Vehicle Re-Identification [18.539658212171062]
Part-Mentored Attention Network (PMANet) for vehicle part localization with self-attention and a Part-Mentored Network (PMNet) for mentoring the global and local feature aggregation.
Our approach outperforms recent state-of-the-art methods by averagely 2.63% in CMC@1 on VehicleID and 2.2% in mAP on VeRi776.
arXiv Detail & Related papers (2021-07-17T12:19:12Z) - 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) - Watching You: Global-guided Reciprocal Learning for Video-based Person
Re-identification [82.6971648465279]
We propose a novel Global-guided Reciprocal Learning framework for video-based person Re-ID.
Our approach can achieve better performance than other state-of-the-art approaches.
arXiv Detail & Related papers (2021-03-07T12:27:42Z) - Channel-wise Alignment for Adaptive Object Detection [66.76486843397267]
Generic object detection has been immensely promoted by the development of deep convolutional neural networks.
Existing methods on this task usually draw attention on the high-level alignment based on the whole image or object of interest.
In this paper, we realize adaptation from a thoroughly different perspective, i.e., channel-wise alignment.
arXiv Detail & Related papers (2020-09-07T02:42:18Z)
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.