Related papers: Pinwheel-shaped Convolution and Scale-based Dynami…

Despite the remarkable success of deep learning, an optimal convolution operation on point clouds remains elusive owing to their irregular data structure. Existing methods mainly focus on designing an effective continuous kernel function…

Infrared small target detection (IRSTD) has recently benefitted greatly from U-shaped neural models. However, largely overlooking effective global information modeling, existing techniques struggle when the target has high similarities with…

Confocal laser scanning microscopy (CLSM) stands out as one of the most widely used microscopy techniques, thanks to its three-dimensional imaging capability and its sub-diffraction spatial resolution, achieved through the closure of a…

Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method. There are…

Visual tracking is a fundamental problem in computer vision. Recently, some deep-learning-based tracking algorithms have been achieving record-breaking performances. However, due to the high complexity of deep learning, most deep trackers…

Infrared small target detection (IRSTD) poses a significant challenge in the field of computer vision. While substantial efforts have been made over the past two decades to improve the detection capabilities of IRSTD algorithms, there has…

This paper shows the effectiveness of 2D backbone scaling and pretraining for pillar-based 3D object detectors. Pillar-based methods mainly employ randomly initialized 2D convolution neural network (ConvNet) for feature extraction and fail…

Change detection is the process of identifying pixelwise differences in bitemporal co-registered images. It is of great significance to Earth observations. Recently, with the emergence of deep learning (DL), the power and feasibility of…

Many targets are often very small in infrared images due to the long-distance imaging meachnism. UNet and its variants, as popular detection backbone networks, downsample the local features early and cause the irreversible loss of these…

Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., pedestrians, cyclists)…

Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise…

Single domain generalization aims to train a generalizable model with only one source domain to perform well on arbitrary unseen target domains. Image augmentation based on Random Convolutions (RandConv), consisting of one convolution layer…

Small area change detection from synthetic aperture radar (SAR) is a highly challenging task. In this paper, a robust unsupervised approach is proposed for small area change detection from multi-temporal SAR images using deep learning.…

Unmanned aerial vehicles serve as primary sensing platforms for surveillance, traffic monitoring, and disaster response, making aerial object detection a central problem in applied computer vision. Current detectors struggle with…

A major bottleneck of pedestrian detection lies on the sharp performance deterioration in the presence of small-size pedestrians that are relatively far from the camera. Motivated by the observation that pedestrians of disparate spatial…

Point supervision has become a scalable solution to address dense annotation for infrared small target detection, but its performance is limited by two coupled bottlenecks: unstable pseudo-label evolution in cluttered, low-contrast infrared…

Recently, infrared small target detection with single-point supervision has attracted extensive attention. However, the detection accuracy of existing methods has difficulty meeting actual needs. Therefore, we propose an innovative refined…

The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has…

Computer vision researchers have extensively worked on fundamental infrared visual recognition for the past few decades. Among various approaches, deep learning has emerged as the most promising candidate. However, Infrared Small Object…

In computer vision, convolutional networks (CNNs) often adopts pooling to enlarge receptive field which has the advantage of low computational complexity. However, pooling can cause information loss and thus is detrimental to further…