Occlusion Based Discriminative Feature Mining for Vehicle Re-identification

Lin, Xianmin; Peng, Shengwang; Ma, Zhiqi; Zhou, Xiaoyi; Zheng, Aihua

doi:10.1007/978-981-15-7984-4_19

Cited by 3 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently occluded person Re-ID has attracted much attention but there is still little research related to occluded vehicle Re-ID. [29] increases the model generalization by synthesizing occlusion samples and resorts to an attention mechanism for fine-grained feature learning. ASAN [30] proposes a CAM-based segmentation module and a shift feature adaptation module to extract features within the visible part of the image.…”

Section: B Occluded Re-idmentioning

confidence: 99%

Looking Twice for Partial Clues: Weakly-supervised Part-Mentored Attention Network for Vehicle Re-Identification

Tang¹,

Wang²,

Chau³

2021

Preprint

View full text Add to dashboard Cite

Vehicle re-identification (Re-ID) is to retrieve images of the same vehicle across different cameras. Two key challenges lie in the subtle inter-instance discrepancy caused by nearduplicate identities and the large intra-instance variance caused by different views. Since the holistic appearance suffers from viewpoint variation and distortion, part-level feature learning has been introduced to enhance vehicle description. However, existing approaches to localize and amplify significant parts often fail to handle spatial misalignment as well as occlusion and require expensive annotations. In this paper, we propose a weakly-supervised Part-Mentored Attention Network (PMANet) consisting of a Part Attention Network (PANet) for vehicle part localization with self-attention and a Part-Mentored Network (PMNet) for mentoring the global and local feature aggregation. Firstly, PANet is introduced to predict a foreground mask and pinpoint K prominent vehicle parts only with a weak identity supervision. Secondly, we propose a PMNet to learn global and part-level features with multi-scale spatial and channel attention and aggregate them in K main-partial tasks via part transfer. Like humans who first differentiate objects with general information and then observe salient parts for more detailed clues, PANet and PMNet construct a two-stage attention structure to perform a coarse-to-fine search among identities. Finally, we address this Re-ID issue as a multi-task problem, including global feature learning, identity classification, and part transfer. We adopt Homoscedastic Uncertainty to learn the optimal weighing of different losses. Comprehensive experiments are conducted on two benchmark datasets. Our approach outperforms recent stateof-the-art methods by averagely 2.63% in CMC@1 on VehicleID and 2.2% in mAP on VeRi776. Moreover, Experimental results on occluded test sets demonstrate that PMANet has a good generalization ability.

show abstract

Section: B Occluded Re-idmentioning

confidence: 99%

Looking Twice for Partial Clues: Weakly-supervised Part-Mentored Attention Network for Vehicle Re-Identification

Tang¹,

Wang²,

Chau³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…To handle occluded Re-ID without additional supervision, Zheng et al [82] proposed a local patch-level matching model and a global part-based matching model which supplies complementary spatial alignment clues. [56] designs a self-supervised model to locate the visible regions.Nevertheless, there is still little research related to occluded vehicle Re-ID [34]. increases the model generalization by synthesizing occlusion samples and resorts to an attention mechanism for fine-grained feature learning.…”

mentioning

confidence: 99%

Vehicle re-identification using machine learning

Tang¹

View full text Add to dashboard Cite

Vehicle Re-ID aims to retrieve images of the same vehicle across non-overlapping cameras. The key challenges lie in the subtle inter-class discrepancy caused by near-duplicated identities and the significant intra-class distance due to diverse factors, including illumination, viewpoints, and background interference. This thesis starts with reviewing the development history of vehicle Re-ID and proposes a Part-Mentored Attention Network (PMANet) consisting of a Part Attention Network (PANet) for weakly-supervised vehicle part localization and a Part-Mentored Network (PMNet) for mentoring the global and local feature aggregation. Firstly, PANet predicts a foreground mask and pinpoint K prominent vehicle parts without additional part-level supervision. Secondly, PMNet applies multi-scale soft attention on localized regions and compensates inaccurate part masks with part-guided learning. PANet and PMNet construct a two-stage attention structure to perform a coarse-to-fine search among identities. Finally, we address thisRe-ID issue as a multi-task problem and employ Homoscedastic Uncertainty Learning to automatically balance the loss weightings. Experimental results show that 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.

show abstract