Related papers: Efficiency Follows Global-Local Decoupling
Most of the existing object detection methods generate poor glass detection results, due to the fact that the transparent glass shares the same appearance with arbitrary objects behind it in an image. Different from traditional deep…
Over the last few years, neural image compression has gained wide attention from research and industry, yielding promising end-to-end deep neural codecs outperforming their conventional counterparts in rate-distortion performance. Despite…
Recent real-time semantic segmentation models, whether single-branch or multi-branch, achieve good performance and speed. However, their speed is limited by multi-path blocks, and some depend on high-performance teacher models for training.…
A recent trend among generalizable novel view synthesis methods is to learn a rendering operator acting over single camera rays. This approach is promising because it removes the need for explicit volumetric rendering, but it effectively…
Deep learning models, specifically convolutional neural networks, have transformed the landscape of image classification by autonomously extracting features directly from raw pixel data. This article introduces an innovative image…
Transformer-based models have transformed the landscape of natural language processing (NLP) and are increasingly applied to computer vision tasks with remarkable success. These models, renowned for their ability to capture long-range…
In the Bag-of-Words (BoW) model based image retrieval task, the precision of visual matching plays a critical role in improving retrieval performance. Conventionally, local cues of a keypoint are employed. However, such strategy does not…
In quantised autoencoders, images are usually split into local patches, each encoded by one token. This representation is redundant in the sense that the same number of tokens is spend per region, regardless of the visual information…
Restoring images affected by various types of degradation, such as noise, blur, or improper exposure, remains a significant challenge in computer vision. While recent trends favor complex monolithic all-in-one architectures, these models…
In this work we introduce a convolutional neural network (CNN) that jointly handles low-, mid-, and high-level vision tasks in a unified architecture that is trained end-to-end. Such a universal network can act like a `swiss knife' for…
Recently, biological perception has been a powerful tool for handling the camouflaged object detection (COD) task. However, most existing methods are heavily dependent on the local spatial information of diverse scales from convolutional…
Recently, there has been a substantial amount of interest in GNN-based anomaly detection. Existing efforts have focused on simultaneously mastering the node representations and the classifier necessary for identifying abnormalities with…
Deep convolutional neural networks have achieved competitive performance in salient object detection, in which how to learn effective and comprehensive features plays a critical role. Most of the previous works mainly adopted multiple level…
Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, their performance on previous tasks drops drastically. In this…
The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…
Recent works attempt to improve scene parsing performance by exploring different levels of contexts, and typically train a well-designed convolutional network to exploit useful contexts across all pixels equally. However, in this paper, we…
Recent advances in pixel-level tasks (e.g. segmentation) illustrate the benefit of of long-range interactions between aggregated region-based representations that can enhance local features. However, such aggregated representations, often…
The UNet architecture, based on Convolutional Neural Networks (CNN), has demonstrated its remarkable performance in medical image analysis. However, it faces challenges in capturing long-range dependencies due to the limited receptive…
We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise dilated separable convolutions to learn…
Making a single network effectively address diverse contexts---learning the variations within a dataset or multiple datasets---is an intriguing step towards achieving generalized intelligence. Existing approaches of deepening, widening, and…