Related papers: PBRnet: Pyramidal Bounding Box Refinement to Impro…

Feature pyramid network (FPN) is a critical component in modern object detection frameworks. The performance gain in most of the existing FPN variants is mainly attributed to the increase of computational burden. An attempt to enhance the…

6-DoF object pose estimation from a monocular image is challenging, and a post-refinement procedure is generally needed for high-precision estimation. In this paper, we propose a framework based on a recurrent neural network (RNN) for…

Remote sensor image object detection is an important technology for Earth observation, and is used in various tasks such as forest fire monitoring and ocean monitoring. Image object detection technology, despite the significant…

Multi-head detectors typically employ a features-fused-pyramid-neck for multi-scale detection and are widely adopted in the industry. However, this approach faces feature misalignment when representations from different hierarchical levels…

Corrosion detection on metal constructions is a major challenge in civil engineering for quick, safe and effective inspection. Existing image analysis approaches tend to place bounding boxes around the defected region which is not adequate…

Lane is critical in the vision navigation system of the intelligent vehicle. Naturally, lane is a traffic sign with high-level semantics, whereas it owns the specific local pattern which needs detailed low-level features to localize…

As an important research topic in computer vision, fine-grained classification which aims to recognition subordinate-level categories has attracted significant attention. We propose a novel region based ensemble learning network for…

To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple…

Object detection and instance segmentation are two fundamental computer vision tasks. They are closely correlated but their relations have not yet been fully explored in most previous work. This paper presents RDSNet, a novel deep…

Benefiting from the great success of deep learning in computer vision, CNN-based object detection methods have drawn significant attentions. Various frameworks have been proposed which show awesome and robust performance for a large range…

Multi-scale features are essential for dense prediction tasks, such as object detection, instance segmentation, and semantic segmentation. The prevailing methods usually utilize a classification backbone to extract multi-scale features and…

Compared with model architectures, the training process, which is also crucial to the success of detectors, has received relatively less attention in object detection. In this work, we carefully revisit the standard training practice of…

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…

Current state-of-the-art two-stage detectors generate oriented proposals through time-consuming schemes. This diminishes the detectors' speed, thereby becoming the computational bottleneck in advanced oriented object detection systems. This…

Efficient model inference is an important and practical issue in the deployment of deep neural network on resource constraint platforms. Network quantization addresses this problem effectively by leveraging low-bit representation and…

Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image. This is an ill-posed problem with a major difficulty lying in the information loss by depth-agnostic cameras. Conventional…

Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection. However, such success greatly relies on costly computation resources, which hinders people with cheap…

Fine-grained object categorization aims for distinguishing objects of subordinate categories that belong to the same entry-level object category. The task is challenging due to the facts that (1) training images with ground-truth labels are…

Real-time semantic segmentation has received considerable attention due to growing demands in many practical applications, such as autonomous vehicles, robotics, etc. Existing real-time segmentation approaches often utilize feature fusion…

Convolutional neural networks (CNNs) have shown remarkable performance in various computer vision tasks in recent years. However, the increasing model size has raised challenges in adopting them in real-time applications as well as mobile…