Related papers: HorNet: Efficient High-Order Spatial Interactions …

Point cloud completion is essential for robotic perception, object reconstruction and supporting downstream tasks like grasp planning, obstacle avoidance, and manipulation. However, incomplete geometry caused by self-occlusion and sensor…

This paper presents MOAT, a family of neural networks that build on top of MObile convolution (i.e., inverted residual blocks) and ATtention. Unlike the current works that stack separate mobile convolution and transformer blocks, we…

Convolution and transposed convolution are fundamental operators widely used in neural networks. However, transposed convolution (a.k.a. deconvolution) does not serve as a true inverse of convolution due to inherent differences in their…

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…

By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose…

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation…

Evidence is mounting that Convolutional Networks (ConvNets) are the most effective representation learning method for visual recognition tasks. In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the…

Due to the depth degradation effect in residual connections, many efficient Vision Transformers models that rely on stacking layers for information exchange often fail to form sufficient information mixing, leading to unnatural visual…

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…

Understanding the relationship between different parts of an image is crucial in a variety of applications, including object recognition, scene understanding, and image classification. Despite the fact that Convolutional Neural Networks…

In order to enhance the real-time performance of convolutional neural networks(CNNs), more and more researchers are focusing on improving the efficiency of CNN. Based on the analysis of some CNN architectures, such as ResNet, DenseNet,…

Vision Transformers (ViT) serve as powerful vision models. Unlike convolutional neural networks, which dominated vision research in previous years, vision transformers enjoy the ability to capture long-range dependencies in the data.…

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…

The formidable accomplishment of Transformers in natural language processing has motivated the researchers in the computer vision community to build Vision Transformers. Compared with the Convolution Neural Networks (CNN), a Vision…

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise.…

Deep neural networks employ specialized architectures for vision, sequential and language tasks, yet this proliferation obscures their underlying commonalities. We introduce a unified matrix-order framework that casts convolutional,…

Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction and fusion, are…

For medical image semantic segmentation (MISS), Vision Transformers have emerged as strong alternatives to convolutional neural networks thanks to their inherent ability to capture long-range correlations. However, existing research uses…

Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or…

Convolutional neural nets (convnets) trained from massive labeled datasets have substantially improved the state-of-the-art in image classification and object detection. However, visual understanding requires establishing correspondence on…