Related papers: Region-Aware Deformable Convolutions
In recent years, there have been attempts to increase the kernel size of Convolutional Neural Nets (CNNs) to mimic the global receptive field of Vision Transformers' (ViTs) self-attention blocks. That approach, however, quickly hit an upper…
An important development direction in the Single-Image Super-Resolution (SISR) algorithms is to improve the efficiency of the algorithms. Recently, efficient Super-Resolution (SR) research focuses on reducing model complexity and improving…
Deep neural networks face several challenges in hyperspectral image classification, including insufficient utilization of joint spatial-spectral information, gradient vanishing with increasing depth, and overfitting. To enhance feature…
In modern computer vision, images are typically represented as a fixed uniform grid with some stride and processed via a deep convolutional neural network. We argue that deforming the grid to better align with the high-frequency image…
RGB-D semantic segmentation has attracted increasing attention over the past few years. Existing methods mostly employ homogeneous convolution operators to consume the RGB and depth features, ignoring their intrinsic differences. In fact,…
3D object detection from LiDAR data for autonomous driving has been making remarkable strides in recent years. Among the state-of-the-art methodologies, encoding point clouds into a bird's eye view (BEV) has been demonstrated to be both…
We introduce an approach to integrate segmentation information within a convolutional neural network (CNN). This counter-acts the tendency of CNNs to smooth information across regions and increases their spatial precision. To obtain…
Transformer models have made tremendous progress in various fields in recent years. In the field of computer vision, vision transformers (ViTs) also become strong alternatives to convolutional neural networks (ConvNets), yet they have not…
Convolutional Neural Networks (CNNs) have exhibited their great power in a variety of vision tasks. However, the lack of transform-invariant property limits their further applications in complicated real-world scenarios. In this work, we…
Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection. But, they do not work well with objects of multiple scales. To overcome such a limitation, in this work, we propose a recurrent attentional…
Transposed convolution is crucial for generating high-resolution outputs, yet has received little attention compared to convolution layers. In this work we revisit transposed convolution and introduce a novel layer that allows us to place…
Neural networks for visual content understanding have recently evolved from convolutional ones (CNNs) to transformers. The prior (CNN) relies on small-windowed kernels to capture the regional clues, demonstrating solid local expressiveness.…
Semantic segmentation is an important branch of image processing and computer vision. With the popularity of deep learning, various convolutional neural networks have been proposed for pixel-level classification and segmentation tasks. In…
Deep neural networks face numerous challenges in hyperspectral image classification, including high-dimensional data, sparse ground object distributions, and spectral redundancy, which often lead to classification overfitting and limited…
Achieving rotation invariance in deep neural networks without relying on data has always been a hot research topic. Intrinsic rotation invariance can enhance the model's feature representation capability, enabling better performance in…
Thanks to the application of deep learning technology in point cloud processing of the remote sensing field, point cloud segmentation has become a research hotspot in recent years, which can be applied to real-world 3D, smart cities, and…
Convolutional neural networks use regular quadrilateral convolution kernels to extract features. Since the number of parameters increases quadratically with the size of the convolution kernel, many popular models use small convolution…
Cracks play a crucial role in assessing the safety and durability of manufactured buildings. However, the long and sharp topological features and complex background of cracks make the task of crack segmentation extremely challenging. In…
Retrieving spatial information and understanding the semantic information of the surroundings are important for Bird's-Eye-View (BEV) semantic segmentation. In the application of autonomous driving, autonomous vehicles need to be aware of…
Deep learning-based image registration methods have shown state-of-the-art performance and rapid inference speeds. Despite these advances, many existing approaches fall short in capturing spatially varying information in non-local regions…