Multi-object Tracking is an important issue that has been widely investigated in computer vision. However, in practical applications, moving targets are often occluded due to complex changes in the background, which leads to frequent pedestrian ID switches in multi-object tracking. To solve the problem, we present a multi-object tracking algorithm based on FairMOT and Circle Loss. In this paper, HRNet is adopted as the baseline. Then, Polarized Self-Attention is added to HRNet-w32 to obtain weights of helpful information based on its modeling advantages. Moreover, the re-identification branch is optimized, and the Circle Loss is selected as the loss function to acquire more discriminative pedestrian features and to distinguish different pedestrians. The method proposed is assessed on the public MOT17 datasets. The experimental results show that the MOTA score achieves 69.5%, IDF1 reaches 70.0%, and the number of ID switches (IDs) decreases 636 times compared to the TraDes algorithm. 

https://www.nature.com/articles/s41598-023-31806-2.pdf

Pedestrian multiple-object tracking based on FairMOT and circle loss

3D tooth segmentation is a prerequisite for computer-aided dental diagnosis and treatment. However, segmenting all tooth regions manually is subjective and time-consuming. Recently, deep learning-based segmentation methods produce convincing results and reduce manual annotation efforts, but it requires a large quantity of ground truth for training. To our knowledge, there are few tooth data available for the 3D segmentation study. In this paper, we establish a fully annotated cone beam computed tomography dataset CTooth with tooth gold standard. This dataset contains 22 volumes (7363 slices) with fine tooth labels annotated by experienced radiographic interpreters. To ensure a relative even data sampling distribution, data variance is included in the CTooth including missing teeth and dental restoration. Several state-of-the-art segmentation methods are evaluated on this dataset. Afterwards, we further summarise and apply a series of 3D attention-based Unet variants for segmenting tooth volumes. This work provides a new benchmark for the tooth volume segmentation task. Experimental evidence proves that attention modules of the 3D UNet structure boost responses in tooth areas and inhibit the influence of background and noise. The best performance is achieved by 3D Unet with SKNet attention module, of 88.04% Dice and 78.71% IOU, respectively. The attention-based Unet framework outperforms other state-of-the-art methods on the CTooth dataset. The codebase and dataset are released here . 

/pdf/ctooth-a-fully-annotated-3d-dataset-and-benchmark-for-tooth-3115eyrp.pdf

CTooth: A Fully Annotated 3D Dataset and Benchmark for Tooth Volume Segmentation on Cone Beam Computed Tomography Images

In recent years, pixel-wise hyperspectral image (HSI) classification has received growing attention in the field of remote sensing. Plenty of spectral–spatial convolutional neural network (CNN) methods with diverse attention mechanisms have been proposed for HSI classification due to the attention mechanisms being able to provide more flexibility over standard convolutional blocks. However, it remains a challenge to effectively extract multiscale features of high-resolution HSI in a real-world complex environment. In this article, we propose a pyramidal multiscale spectral–spatial convolutional network with polarized self-attention for pixel-wise HSI classification. It contains three stages: channel-wise feature extraction network, spatial-wise feature extraction network, and classification network, which are used to extract spectral features, extract spatial features, and generate classification results, respectively. Pyramidal convolutional blocks and polarized attention blocks are combined to extract spectral and spatial features of HSI. Furthermore, residual aggregation and one-shot aggregation are employed to better converge the network. The experimental results on several public HSI datasets demonstrate that the proposed network outperforms other related methods.

https://ieeexplore.ieee.org/ielx7/36/4358825/10043832.pdf

Pyramidal Multiscale Convolutional Network With Polarized Self-Attention for Pixel-Wise Hyperspectral Image Classification

MFEFNet: Multi-scale feature enhancement and Fusion Network for polyp segmentation

FRE-Net: Full-region enhanced network for nuclei segmentation in histopathology images

Polarized self-attention: Towards high-quality pixel-wise mapping

Pixel-wise regression is probably the most common problem in fine-grained computer vision tasks, such as estimating keypoint heatmaps and segmentation masks. These regression problems are very challenging particularly because they require, at low computation overheads, modeling long-range dependencies on high-resolution inputs/outputs to estimate the highly nonlinear pixel-wise semantics. While attention mechanisms in Deep Convolutional Neural Networks(DCNNs) has become popular for boosting long-range dependencies, element-specific attention, such as Nonlocal blocks, is highly complex and noise-sensitive to learn, and most of simplified attention hybrids try to reach the best compromise among multiple types of tasks. In this paper, we present the Polarized Self-Attention(PSA) block that incorporates two critical designs towards high-quality pixel-wise regression: (1) Polarized filtering: keeping high internal resolution in both channel and spatial attention computation while completely collapsing input tensors along their counterpart dimensions. (2) Enhancement: composing non-linearity that directly fits the output distribution of typical fine-grained regression, such as the 2D Gaussian distribution (keypoint heatmaps), or the 2D Binormial distribution (binary segmentation masks). PSA appears to have exhausted the representation capacity within its channel-only and spatial-only branches, such that there is only marginal metric differences between its sequential and parallel layouts. Experimental results show that PSA boosts standard baselines by $2-4$ points, and boosts state-of-the-arts by $1-2$ points on 2D pose estimation and semantic segmentation benchmarks.

Fuqiang Liu

Papers

Polarized self-attention: Towards high-quality pixel-wise mapping

Polarized Self-Attention: Towards High-quality Pixel-wise Regression.