Related papers: HieraEdgeNet: A Multi-Scale Edge-Enhanced Framewor…
We propose a novel Enhanced Feature Aggregation and Selection network (EFASNet) for multi-person 2D human pose estimation. Due to enhanced feature representation, our method can well handle crowded, cluttered and occluded scenes. More…
Cotton harvesting is a critical phase where cotton capsules are physically manipulated and can lead to fibre degradation. To maintain the highest quality, harvesting methods must emulate delicate manual grasping, to preserve cotton's…
The importance of hierarchical image organization has been witnessed by a wide spectrum of applications in computer vision and graphics. Different from image segmentation with the spatial whole-part consideration, this work designs a modern…
Semi-supervised change detection (SSCD) aims to detect changes between bi-temporal remote sensing images by utilizing limited labeled data and abundant unlabeled data. Existing methods struggle in complex scenarios, exhibiting poor…
We present HetNet (Multi-level \textbf{Het}erogeneous \textbf{Net}work), a highly efficient mirror detection network. Current mirror detection methods focus more on performance than efficiency, limiting the real-time applications (such as…
Modern agriculture heavily relies on Site-Specific Farm Management practices, necessitating accurate detection, localization, and quantification of crops and weeds in the field, which can be achieved using deep learning techniques. In this…
Accurate lesion segmentation in ultrasound images is essential for preventive screening and clinical diagnosis, yet remains challenging due to low contrast, blurry boundaries, and significant scale variations. Although existing deep…
Image harmonization is a critical task in computer vision, which aims to adjust the foreground to make it compatible with the background. Recent works mainly focus on using global transformations (i.e., normalization and color curve…
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…
While nowadays deep neural networks achieve impressive performances on semantic segmentation tasks, they are usually trained by optimizing pixel-wise losses such as cross-entropy. As a result, the predictions outputted by such networks…
Point cloud completion is essential for robotic perception, object reconstruction and supporting downstream tasks like grasp planning, obstacle avoidance, and manipulation. However, incomplete geometry caused by self-occlusion and sensor…
The quadratic computational cost of processing vision tokens in Multimodal Large Language Models (MLLMs) hinders their widespread adoption. While progressive vision token pruning offers a promising solution, current methods misinterpret…
Deep learning-based coastline detection algorithms have begun to outshine traditional statistical methods in recent years. However, they are usually trained only as single-purpose models to either segment land and water or delineate the…
For a globally recognized planting breeding organization, manually-recorded field observation data is crucial for plant breeding decision making. However, certain phenotypic traits such as plant color, height, kernel counts, etc. can only…
Designing a lightweight and robust portrait segmentation algorithm is an important task for a wide range of face applications. However, the problem has been considered as a subset of the object segmentation problem and less handled in the…
The rapid growth of high-resolution, meticulously crafted AI-generated images poses a significant challenge to existing detection methods, which are often trained and evaluated on low-resolution, automatically generated datasets that do not…
We present a framework for the Convolutional Hierarchical Deep-learning Neural Network (C-HiDeNN) tailored for nonlinear finite element analysis. Building upon the structured foundation of HiDeNN, C-HiDeNN introduces a convolution operator…
High resolution and advanced semantic representation are both vital for dense prediction. Empirically, low-resolution feature maps often achieve stronger semantic representation, and high-resolution feature maps generally can better…
We propose Fiber Bundle Networks (FiberNet), a novel machine learning framework integrating differential geometry with machine learning. Unlike traditional deep neural networks relying on black-box function fitting, we reformulate…
We deal with the solution of the forward problem for high-dimensional parabolic PDEs with random feature (projection) neural networks (RFNNs). We first prove that there exists a single-hidden layer neural network with randomized…