Related papers: EdgeNAT: Transformer for Efficient Edge Detection

Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features. However, local details are gradually suppressed with the enlarging of receptive fields. Recently,…

While the integration of transformers in vision models have yielded significant improvements on vision tasks they still require significant amounts of computation for both training and inference. Restricted attention mechanisms…

Semantic segmentation of remotely sensed urban scene images is required in a wide range of practical applications, such as land cover mapping, urban change detection, environmental protection, and economic assessment.Driven by rapid…

In the pursuit of achieving ever-increasing accuracy, large and complex neural networks are usually developed. Such models demand high computational resources and therefore cannot be deployed on edge devices. It is of great interest to…

Visual intelligence at the edge is becoming a growing necessity for low latency applications and situations where real-time decision is vital. Object detection, the first step in visual data analytics, has enjoyed significant improvements…

Surface defect detection is an extremely crucial step to ensure the quality of industrial products. Nowadays, convolutional neural networks (CNNs) based on encoder-decoder architecture have achieved tremendous success in various defect…

Scene analysis is essential for enabling autonomous systems, such as mobile robots, to operate in real-world environments. However, obtaining a comprehensive understanding of the scene requires solving multiple tasks, such as panoptic…

Edge points on 3D point clouds can clearly convey 3D geometry and surface characteristics, therefore, edge detection is widely used in many vision applications with high industrial and commercial demands. However, the fine-grained edge…

Transformer-based models have achieved strong performance in remote sensing image captioning by capturing long-range dependencies and contextual information. However, their practical deployment is hindered by high computational costs,…

The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of…

As a key technology of enabling Artificial Intelligence (AI) applications in 5G era, Deep Neural Networks (DNNs) have quickly attracted widespread attention. However, it is challenging to run computation-intensive DNN-based tasks on mobile…

In this work, we present Eformer - Edge enhancement based transformer, a novel architecture that builds an encoder-decoder network using transformer blocks for medical image denoising. Non-overlapping window-based self-attention is used in…

Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome the limitations presented by inductive convolutional biases. However, directly applying the transformer structure to remove noise is…

Scene text segmentation aims at cropping texts from scene images, which is usually used to help generative models edit or remove texts. The existing text segmentation methods tend to involve various text-related supervisions for better…

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Medical image segmentation is crucial for the development of computer-aided diagnostic and therapeutic systems, but still faces numerous difficulties. In recent years, the commonly used encoder-decoder architecture based on CNNs has been…

Transformers are quickly becoming one of the most heavily applied deep learning architectures across modalities, domains, and tasks. In vision, on top of ongoing efforts into plain transformers, hierarchical transformers have also gained…

Transformers have been widely used in numerous vision problems especially for visual recognition and detection. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the…

We present SceneNAT, a single-stage masked non-autoregressive Transformer that synthesizes complete 3D indoor scenes from natural language instructions through only a few parallel decoding passes, offering improved performance and…

The objective of dense material segmentation is to identify the material categories for every image pixel. Recent studies adopt image patches to extract material features. Although the trained networks can improve the segmentation…