相关论文: Realtime Global Attention Network for Semantic Seg…

Transformer-based methods have demonstrated impressive performance in low-level visual tasks such as Image Super-Resolution (SR). However, its computational complexity grows quadratically with the spatial resolution. A series of works…

Semantic Segmentation is a crucial component in the perception systems of many applications, such as robotics and autonomous driving that rely on accurate environmental perception and understanding. In literature, several approaches are…

Learning representative, robust and discriminative information from images is essential for effective person re-identification (Re-Id). In this paper, we propose a compound approach for end-to-end discriminative deep feature learning for…

Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards. Here, we address three of its most prominent hurdles, namely, i) the adaptation of a single…

Due to the powerful ability to encode image details and semantics, many lightweight dual-resolution networks have been proposed in recent years. However, most of them ignore the benefit of boundary information. This paper introduces a…

Analyzing scenes thoroughly is crucial for mobile robots acting in different environments. Semantic segmentation can enhance various subsequent tasks, such as (semantically assisted) person perception, (semantic) free space detection,…

The multi-modal salient object detection model based on RGB-D information has better robustness in the real world. However, it remains nontrivial to better adaptively balance effective multi-modal information in the feature fusion phase. In…

Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherently limited to model such dependencies due to the naive…

The generalization of the end-to-end deep reinforcement learning (DRL) for object-goal visual navigation is a long-standing challenge since object classes and placements vary in new test environments. Learning domain-independent visual…

Semantic segmentation stands as a pivotal research focus in computer vision. In the context of industrial image inspection, conventional semantic segmentation models fail to maintain the segmentation consistency of fixed components across…

Since the point cloud data is inherently irregular and unstructured, point cloud semantic segmentation has always been a challenging task. The graph-based method attempts to model the irregular point cloud by representing it as a graph;…

Automatic segmentation of fine-grained brain structures remains a challenging task. Current segmentation methods mainly utilize 2D and 3D deep neural networks. The 2D networks take image slices as input to produce coarse segmentation in…

Low-resolution image segmentation is crucial in real-world applications such as robotics, augmented reality, and large-scale scene understanding, where high-resolution data is often unavailable due to computational constraints. To address…

Transformer-based methods for RGB-D Salient Object Detection (SOD) have gained significant interest, owing to the transformer's exceptional capacity to capture long-range pixel dependencies. Nevertheless, current RGB-D SOD methods face…

End-to-end Network has become increasingly important in multi-tasking. One prominent example of this is the growing significance of a driving perception system in autonomous driving. This paper systematically studies an end-to-end…

Global context information is vital in visual understanding problems, especially in pixel-level semantic segmentation. The mainstream methods adopt the self-attention mechanism to model global context information. However, pixels belonging…

Although deep neural networks generally have fixed network structures, the concept of dynamic mechanism has drawn more and more attention in recent years. Attention mechanisms compute input-dependent dynamic attention weights for…

Different from the general visual classification, some classification tasks are more challenging as they need the professional categories of the images. In the paper, we call them expert-level classification. Previous fine-grained vision…

As the scene information, including objectness and scene type, are important for people with visual impairment, in this work we present a multi-task efficient perception system for the scene parsing and recognition tasks. Building on the…

3D to 2D retinal vessel segmentation is a challenging problem in Optical Coherence Tomography Angiography (OCTA) images. Accurate retinal vessel segmentation is important for the diagnosis and prevention of ophthalmic diseases. However,…