Related papers: NETNet: Neighbor Erasing and Transferring Network …

This paper considers the problem of single image depth estimation. The employment of convolutional neural networks (CNNs) has recently brought about significant advancements in the research of this problem. However, most existing methods…

The automated surface defect detection is a fundamental task in industrial production, and the existing saliencybased works overcome the challenging scenes and give promising detection results. However, the cutting-edge efforts often suffer…

Neural networks (NNs) are capable of learning complex patterns and relationships in data to make predictions with high accuracy, making them useful for various tasks. However, NNs are both computation-intensive and memory-intensive methods,…

This paper proposes the Parallel Residual Bi-Fusion Feature Pyramid Network (PRB-FPN) for fast and accurate single-shot object detection. Feature Pyramid (FP) is widely used in recent visual detection, however the top-down pathway of FP…

CNN-based object detection methods have achieved significant progress in recent years. The classic structures of CNNs produce pyramid-like feature maps due to the pooling or other re-scale operations. The feature maps in different levels of…

Most image matching methods perform poorly when encountering large scale changes in images. To solve this problem, firstly, we propose a scale-difference-aware image matching method (SDAIM) that reduces image scale differences before local…

The intricacy of 3D surfaces often results cutting-edge point cloud denoising (PCD) models in surface degradation including remnant noise, wrongly-removed geometric details. Although using multi-scale patches to encode the geometry of a…

The current advances in object detection depend on large-scale datasets to get good performance. However, there may not always be sufficient samples in many scenarios, which leads to the research on few-shot detection as well as its extreme…

Salient object detection is a fundamental topic in computer vision. Previous methods based on RGB-D often suffer from the incompatibility of multi-modal feature fusion and the insufficiency of multi-scale feature aggregation. To tackle…

Nanopore resistive pulse sensors are emerging technologies for single-molecule protein sequencing. But they can hardly detect small post-translational modifications (PTMs) such as hydroxylation in single-molecule level. While a combination…

We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and not yet effective on large scale datasets like ImageNet. This…

The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem,namely LEDNet, which employs an asymmetric encoder-decoder…

Building change detection remains challenging for urban development, disaster assessment, and military reconnaissance. While foundation models like Segment Anything Model (SAM) show strong segmentation capabilities, SAM is limited in the…

Recently, adversarial erasing for weakly-supervised object attention has been deeply studied due to its capability in localizing integral object regions. However, such a strategy raises one key problem that attention regions will gradually…

Existing edge-aware camouflaged object detection (COD) methods normally output the edge prediction in the early stage. However, edges are important and fundamental factors in the following segmentation task. Due to the high visual…

We consider a multi-object detection problem over a sensor network (SNET) with limited range sensors. This problem complements the widely considered decentralized detection problem where all sensors observe the same object. While the…

As the scale of object detection dataset is smaller than that of image recognition dataset ImageNet, transfer learning has become a basic training method for deep learning object detection models, which will pretrain the backbone network of…

Object pose estimation enables robots to understand and interact with their environments. Training with synthetic data is necessary in order to adapt to novel situations. Unfortunately, pose estimation under domain shift, i.e., training on…

Consecutive frames in a video are highly redundant. Therefore, to perform the task of video object detection, executing single frame detectors on every frame without reusing any information is quite wasteful. It is with this idea in mind…

Although current deep learning methods have achieved impressive results for semantic segmentation, they incur high computational costs and have a huge number of parameters. For real-time applications, inference speed and memory usage are…