Adaptive weight part-based convolutional network for person re-identification

Shu, Xiu; Li, Qiao; Liu, Jiaqi

doi:10.1007/s11042-020-09018-x

Cited by 15 publications

(7 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different works [30,34,44,[46][47][48] introduced local part based feature representations to enhance the re-id performance. Some methods perform inaccurate part localization by directly splitting images into local stripes.…”

Section: Part Based Deep Neural Networkmentioning

confidence: 99%

“…Zhang et al [44] computed local and global losses by partitioning the body parts into horizontal stripes. Shu et al [30] learned part based features by dividing images into parts and used a network to assign weights to each part.…”

Section: Part Based Deep Neural Networkmentioning

confidence: 99%

“…Recently, part based models [30,34,44,[46][47][48]53] have represent the state of art performance in person re-id by learning part based local feature representations from the person's image. Some of these methods [34,47] compute a strong discriminative representation of the image by splitting it into several body parts and then evolve the local features from all the parts into a single representation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Consistent attentive dual branch network for person re-identification

Munir

Martinel

Micheloni

2022

Multimed Tools Appl

View full text Add to dashboard Cite

Several recent person re-identification methods are focusing on learning discriminative representations by designing efficient metric learning loss functions. Other approaches design part based architectures to compute an informative descriptor based on local features from semantically coherent parts. Few efforts learn the relationship between distant similar regions and parts by adjusting them to their most feasible positions with the help of soft attention. However, they focus on calibrating distant similar parts features and ignore to learn the noise (blur) free and distinct feature representations as the person re-identification datasets contain degraded images. To tackle these issues, we propose a novel Consistent Attention Dual Branch Network (CadNet) that has ability to model long-range dependencies (correlations) between channels as well as feature maps. We adopt multiple classifiers trained to learn the most discriminative global features for a unique representation of a person. Correlation between channels are consistently computed by using channel attention mechanism to make the learned feature noise free and distict from noisy and blurry data. Feature correlations interpret the relationship between distant similarities in the images computed by the self attention mechanism. The proposed CadNet significantly enhances the performance with respect to the baseline on the person re-identification benchmarks.

show abstract

Section: Part Based Deep Neural Networkmentioning

confidence: 99%

Section: Part Based Deep Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Consistent attentive dual branch network for person re-identification

Munir

Martinel

Micheloni

2022

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Early research on person Re-ID focused on how to design better visual features manually and how to learn better similarity measures [3]. With continual progress in computing capabilities, research on convolutional neural networks has advanced rapidly, and their superior performance in person Re-ID has been widely documented [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Multi‐scale feature combination for person re‐identification

Huang

Piao

Zhang

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Person re-identification (Re-ID) is an instance-level task of image retrieval, and its identification accuracy depends on the distinguishable features extracted from people. However, most identification methods based on deep learning only mechanically extract distinguishable features of person images, and some important details are frequently overlooked. For scenes with substantial background differences or occlusions, the Re-ID efficiency is not high and the network scalability is not good. Here, the authors propose a multi-scale feature combination network (MFC-Net) model that combines structural feature information with global comprehensive feature information of the person images through a convolution neural network that can effectively retain distinguishing character detail information. The authors also propose a Gaussian stochastic pooling layer to solve the defects of the pooling layer. For the problem of many network parameters and weak performance, the authors propose an attentive feature convolutions layer. The authors perform many comparative experiments on three benchmark datasets. The results prove that our MFC-Net model performs well in person Re-ID and that its identification accuracy is higher than that of other investigated models.

show abstract

“…Object detection is an important branch of computer vision, which plays a crucial role in the task of instance segmentation [1] and target tracking [2], [3], [4]. It has been widely used in various fields (e.g., face recognition [5], [6] and automatic driving technology [7], [8]).…”

Section: Introductionmentioning

confidence: 99%

Real-Time Detection of River Surface Floating Object Based on Improved RefineDet

et al. 2021

View full text Add to dashboard Cite

Object detection is widely used in robot navigation, intelligent security and industrial detection, but it is rarely used in water conservancy industry. In the aspect of river and lake health management, it is important to clean out the floating objects in time, which prevents water pollution caused by the accumulation of the floating objects. The early methods of water surface object detection, such as background subtraction and frame difference, are greatly affected by the change of object shape and background, resulting in poor robustness. Therefore, we propose a real-time detection method of surface floating objects based on improved RefineDet model, which includes three modules: the anchor refinement module, the transfer connection block and the object detection module. We improve anchor refinement module by adding convolution layers to obtain higher-level semantic, and fuse high-level features with low-level features to improve detection accuracy. Moreover, we adjust the parameters setting of anchors according to the scale and aspect ratio distribution to match the multi-scale object better. Aiming at the foreground-background class imbalance caused by dense anchors sampling, we introduce focal loss function to solve it and make our model more efficient by adjusting the parameters of the function. We verify the performance of the proposed method on the floating object datasets we constructed. The experiments show that the accuracy of the improved RefineDet is 83.8%, and the detection speed is 28 FPS, which realizes high-precision and real-time detection.

show abstract

Adaptive weight part-based convolutional network for person re-identification

Cited by 15 publications

References 49 publications

Consistent attentive dual branch network for person re-identification

Consistent attentive dual branch network for person re-identification

Multi‐scale feature combination for person re‐identification

Real-Time Detection of River Surface Floating Object Based on Improved RefineDet

Contact Info

Product

Resources

About