Further Non-local and Channel Attention Networks for Vehicle Re-identification

Vehicle re-identification remains challenging due to large intra-class difference and small inter-class variance. To address this problem, in AICity Vehicle Re-ID task 2020, we propose a two-branch adaptive attention network—Further Non-local and Channel attention (FNC) to improve feature representation and discrimination. Specifically, inspired by two-stream theory of visual cortex, based on Non-local and channel relation, a two-branch FNC network is constructed to capture multiple useful information. Second, an effective attention fusion method is proposed to sufficiently model the effects from spatial and channel attention. The experimental results show that our algorithm achieves 66.25%/Rank-1 and 53.54%/mAP in 2020 AIC-ity Challenge Vehicle Re-ID task without using extra data, annotation and other auxiliary information, which demonstrate the effectiveness of the proposed FNC network.

[1]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Jenq-Neng Hwang,et al.  Multi-View Vehicle Re-Identification using Temporal Attention Model and Metadata Re-ranking , 2019, CVPR Workshops.

[3]  Jenq-Neng Hwang,et al.  CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Wei Jiang,et al.  SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification , 2018, J. Vis. Commun. Image Represent..

[5]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Abhinav Gupta,et al.  Non-local Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Lucas Beyer,et al.  In Defense of the Triplet Loss for Person Re-Identification , 2017, ArXiv.

[8]  Geoffrey E. Hinton,et al.  Lookahead Optimizer: k steps forward, 1 step back , 2019, NeurIPS.

[9]  Xiong Chen,et al.  Learning Discriminative Features with Multiple Granularities for Person Re-Identification , 2018, ACM Multimedia.

[10]  Ping Tan,et al.  Batch Feature Erasing for Person Re-identification and Beyond , 2018, ArXiv.

[11]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[13]  Yi Yang,et al.  Random Erasing Data Augmentation , 2017, AAAI.

[14]  Liyuan Liu,et al.  On the Variance of the Adaptive Learning Rate and Beyond , 2019, ICLR.

[15]  Francois Bremond,et al.  Partition and Reunion: A Two-Branch Neural Network for Vehicle Re-identification , 2019, CVPR Workshops.

[16]  Yi Yang,et al.  VehicleNet: Learning Robust Feature Representation for Vehicle Re-identification , 2019, CVPR Workshops.

[17]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[18]  Enhua Wu,et al.  Squeeze-and-Excitation Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Rongrong Ji,et al.  Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Wei Jiang,et al.  Bag of Tricks and a Strong Baseline for Deep Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[21]  Qi Tian,et al.  Beyond Part Models: Person Retrieval with Refined Part Pooling , 2017, ECCV.

[22]  Christian Poellabauer,et al.  Second-Order Non-Local Attention Networks for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[23]  Xiao Tan,et al.  Multi-camera vehicle tracking and re-identification based on visual and spatial-temporal features , 2019, CVPR Workshops.

[24]  Liang Zheng,et al.  Re-ranking Person Re-identification with k-Reciprocal Encoding , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).