Related papers: EdgeNAT: Transformer for Efficient Edge Detection

Over the past few years, deep convolutional neural network-based methods have made great progress in semantic segmentation of street scenes. Some recent methods align feature maps to alleviate the semantic gap between them and achieve high…

Recent advances in deep learning have established Transformer architectures as the predominant modeling paradigm. Central to the success of Transformers is the self-attention mechanism, which scores the similarity between query and key…

Deep Neural Network (DNN) trained object detectors are widely deployed in many mission-critical systems for real time video analytics at the edge, such as autonomous driving and video surveillance. A common performance requirement in these…

Infrared small target detection is crucial for remote sensing applications like disaster warning and maritime surveillance. However, due to the lack of distinctive texture and morphological features, infrared small targets are highly…

Convolutional neural networks (CNNs) achieved the state-of-the-art performance in medical image segmentation due to their ability to extract highly complex feature representations. However, it is argued in recent studies that traditional…

The deployment of transformer-based models on resource-constrained edge devices represents a critical challenge in enabling real-time artificial intelligence applications. This comprehensive survey examines lightweight transformer…

Hybrid vision transformers combine the elements of conventional neural networks (NN) and vision transformers (ViT) to enable lightweight and accurate detection. However, several challenges remain for their efficient deployment on…

Recently, token-based generation have demonstrated their effectiveness in image synthesis. As a representative example, non-autoregressive Transformers (NATs) can generate decent-quality images in a few steps. NATs perform generation in a…

In this paper, we examine a key limitation in query-based detectors for temporal action detection (TAD), which arises from their direct adaptation of originally designed architectures for object detection. Despite the effectiveness of the…

Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on FPGAs -- a field that has seen a recent surge in demand. We…

Remotely captured images possess an immense scale and object appearance variability due to the complex scene. It becomes challenging to capture the underlying attributes in the global and local context for their segmentation. Existing…

Deeply learned representations have achieved superior image retrieval performance in a retrieve-then-rerank manner. Recent state-of-the-art single stage model, which heuristically fuses local and global features, achieves promising…

Recent advances in transformer-based models have drawn attention to exploring these techniques in medical image segmentation, especially in conjunction with the U-Net model (or its variants), which has shown great success in medical image…

The design of more complex and powerful neural network models has significantly advanced the state-of-the-art in visual object tracking. These advances can be attributed to deeper networks, or the introduction of new building blocks, such…

Existing methods for Salient Object Detection in Optical Remote Sensing Images (ORSI-SOD) mainly adopt Convolutional Neural Networks (CNNs) as the backbone, such as VGG and ResNet. Since CNNs can only extract features within certain…

While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…

Point cloud segmentation is one of the most important tasks in computer vision with widespread scientific, industrial, and commercial applications. The research thereof has resulted in many breakthroughs in 3D object and scene…

This paper introduces a lightweight convolutional neural network, called FDDWNet, for real-time accurate semantic segmentation. In contrast to recent advances of lightweight networks that prefer to utilize shallow structure, FDDWNet makes…

As a fundamental building block in computer vision, edges can be categorised into four types according to the discontinuity in surface-Reflectance, Illumination, surface-Normal or Depth. While great progress has been made in detecting…

There has been a recent surge in transformer-based architectures for learning on graphs, mainly motivated by attention as an effective learning mechanism and the desire to supersede handcrafted operators characteristic of message passing…