Related papers: ASC-SW: Atrous strip convolution network with slid…
Extracting multi-scale information is key to semantic segmentation. However, the classic convolutional neural networks (CNNs) encounter difficulties in achieving multi-scale information extraction: expanding convolutional kernel incurs the…
In a real-world infrared imaging system, effectively learning a consistent stripe noise removal model is essential. Most existing destriping methods cannot precisely reconstruct images due to cross-level semantic gaps and insufficient…
Deep Convolutional Neural Networks (DCNNs) have recently shown outstanding performance in semantic image segmentation. However, state-of-the-art DCNN-based semantic segmentation methods usually suffer from high computational complexity due…
Structured weight pruning is a representative model compression technique of DNNs for hardware efficiency and inference accelerations. Previous works in this area leave great space for improvement since sparse structures with combinations…
3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects. In this paper, we analyze major components of existing sparse 3D CNNs and find that…
Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…
Recent advancements in synthetic aperture radar (SAR) ship detection using deep learning have significantly improved accuracy and speed, yet effectively detecting small objects in complex backgrounds with fewer parameters remains a…
As a deep learning model typically contains millions of trainable weights, there has been a growing demand for a more efficient network structure with reduced storage space and improved run-time efficiency. Pruning is one of the most…
Due to the limitations of optical lens focal length and detector resolution, distant clustered infrared small targets often appear as mixed spots. The Close Small Object Unmixing (CSOU) task aims to recover the number, sub-pixel positions,…
The Siamese network is becoming the mainstream in change detection of remote sensing images (RSI). However, in recent years, the development of more complicated structure, module and training processe has resulted in the cumbersome model,…
Object detection on drone images with low-latency is an important but challenging task on the resource-constrained unmanned aerial vehicle (UAV) platform. This paper investigates optimizing the detection head based on the sparse…
Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference. However, their practical runtime usually lags behind the theoretical…
This paper proposes a new deep neural network for object detection. The proposed network, termed ASSD, builds feature relations in the spatial space of the feature map. With the global relation information, ASSD learns to highlight useful…
Detecting Resident Space Objects (RSOs) and preventing collisions with other satellites is crucial. Recently, deep convolutional neural networks (DCNNs) have shown superior performance in object detection when large-scale datasets are…
Manipulating Deformable Linear Objects (DLOs) is challenging in robotics due to their infinite-dimensional configuration space and complex nonlinear dynamics. In teleoperation, depth uncertainty hinders state perception and reaction.…
Rotated object detection aims to identify and locate objects in images with arbitrary orientation. In this scenario, the oriented directions of objects vary considerably across different images, while multiple orientations of objects exist…
Rapid, accurate and robust detection of looming objects in cluttered moving backgrounds is a significant and challenging problem for robotic visual systems to perform collision detection and avoidance tasks. Inspired by the neural circuit…
Modern autonomous vehicles (AVs) often rely on vision, LIDAR, and even radar-based simultaneous localization and mapping (SLAM) frameworks for precise localization and navigation. However, modern SLAM frameworks often lead to unacceptably…
In remote sensing images, complex backgrounds, weak object signals, and small object scales make accurate detection particularly challenging, especially under low-quality imaging conditions. A common strategy is to integrate single-image…
Change detection of high-resolution remote sensing images is an important task in earth observation and was extensively investigated. Recently, deep learning has shown to be very successful in plenty of remote sensing tasks. The current…