Related papers: AttaNet: Attention-Augmented Network for Fast and …

The medical image is characterized by the inter-class indistinction, high variability, and noise, where the recognition of pixels is challenging. Unlike previous self-attention based methods that capture context information from one level,…

Surgical instrument segmentation is extremely important for computer-assisted surgery. Different from common object segmentation, it is more challenging due to the large illumination and scale variation caused by the special surgical…

Semantic segmentation is a challenging problem due to difficulties in modeling context in complex scenes and class confusions along boundaries. Most literature either focuses on context modeling or boundary refinement, which is less…

Semantic Segmentation (SS) is promising for outdoor scene perception in safety-critical applications like autonomous vehicles, assisted navigation and so on. However, traditional SS is primarily based on RGB images, which limits the…

In the past decade, convolutional neural networks (CNNs) have shown prominence for semantic segmentation. Although CNN models have very impressive performance, the ability to capture global representation is still insufficient, which…

In recent years, crowd counting and localization have become crucial techniques in computer vision, with applications spanning various domains. The presence of multi-scale crowd distributions within a single image remains a fundamental…

Semantic segmentation for extracting buildings and roads from uncrewed aerial vehicle (UAV) remote sensing images by deep learning becomes a more efficient and convenient method than traditional manual segmentation in surveying and mapping…

Semantic segmentation for lightweight object parsing is a very challenging task, because both accuracy and efficiency (e.g., execution speed, memory footprint or computational complexity) should all be taken into account. However, most…

Attention mechanism of late has been quite popular in the computer vision community. A lot of work has been done to improve the performance of the network, although almost always it results in increased computational complexity. In this…

Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient. In this work, we propose the "double attention…

High-resolution remote sensing (HRRS) image segmentation is challenging due to complex spatial layouts and diverse object appearances. While CNNs excel at capturing local features, they struggle with long-range dependencies, whereas…

Recently, methods based on deep learning have been successfully applied to ship detection for synthetic aperture radar (SAR) images. Despite the development of numerous ship detection methodologies, detecting small and coastal ships remains…

Semantic segmentation assigns labels to pixels in images, a critical yet challenging task in computer vision. Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers…

Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple…

Achieving optimal semantic segmentation with frame-based vision sensors poses significant challenges for real-time systems like UAVs and self-driving cars, which require rapid and precise processing. Traditional frame-based methods often…

Semantic segmentation necessitates approaches that learn high-level characteristics while dealing with enormous amounts of data. Convolutional neural networks (CNNs) can learn unique and adaptive features to achieve this aim. However, due…

Scene Text Recognition (STR) remains challenging due to real-world complexities, where decoupled visual-linguistic optimization in existing frameworks amplifies error propagation through cross-modal misalignment. Visual encoders exhibit…

We introduce SANDesc, a Streamlined Attention-Based Network for Descriptor extraction that aims to improve on existing architectures for keypoint description. Our descriptor network learns to compute descriptors that improve matching…

Due to real-time image semantic segmentation needs on power constrained edge devices, there has been an increasing desire to design lightweight semantic segmentation neural network, to simultaneously reduce computational cost and increase…

Transformers have proved to be very effective for visual recognition tasks. In particular, vision transformers construct compressed global representations through self-attention and learnable class tokens. Multi-resolution transformers have…