Related papers: When Less Is More: Simplicity Beats Complexity for…

In recent years, algorithm unrolling has emerged as a powerful technique for designing interpretable neural networks based on iterative algorithms. Imaging inverse problems have particularly benefited from unrolling-based deep network…

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…

Visual Place Recognition (vPR) plays a crucial role in Unmanned Aerial Vehicle (UAV) navigation, enabling robust localization across diverse environments. Despite significant advancements, aerial vPR faces unique challenges due to the…

Extending the success of 2D Large Kernel to 3D perception is challenging due to: 1. the cubically-increasing overhead in processing 3D data; 2. the optimization difficulties from data scarcity and sparsity. Previous work has taken the first…

3D object detection in point cloud data remains a challenging task due to the sparsity and lack of global structure inherent in the input. In this work, we propose a novel Multi-Scale Attention (MSA) mechanism integrated into the 3DETR…

Window-based transformers have demonstrated outstanding performance in super-resolution tasks due to their adaptive modeling capabilities through local self-attention (SA). However, they exhibit higher computational complexity and inference…

Visual place recognition (VPR) is a highly challenging task that has a wide range of applications, including robot navigation and self-driving vehicles. VPR is particularly difficult due to the presence of duplicate regions and the lack of…

Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various…

Feature foundation models - usually vision transformers - offer rich semantic descriptors of images, useful for downstream tasks such as (interactive) segmentation and object detection. For computational efficiency these descriptors are…

Joint estimation of surface normals and depth is essential for holistic 3D scene understanding, yet high-resolution prediction remains difficult due to the trade-off between preserving fine local detail and maintaining global consistency.…

Over the last century, deep learning models have become the state-of-the-art for solving complex computer vision problems. These modern computer vision models have millions of parameters, which presents two major challenges: (1) the…

Deep learning networks excel at classification, yet identifying minimal architectures that reliably solve a task remains challenging. We present a computational methodology for systematically exploring and analyzing the relationships among…

Convolutional neural networks (CNNs) remain a central approach in image classification, but their performance depends strongly on architectural and training choices. This paper presents an empirical ablation-based study of CNN optimization…

Large convolutional neural network models have recently demonstrated impressive performance on video attention prediction. Conventionally, these models are with intensive computation and large memory. To address these issues, we design an…

Although the U-Net architecture has been extensively used for segmentation of medical images, we address two of its shortcomings in this work. Firstly, the accuracy of vanilla U-Net degrades when the target regions for segmentation exhibit…

While lightweight ViT framework has made tremendous progress in image super-resolution, its uni-dimensional self-attention modeling, as well as homogeneous aggregation scheme, limit its effective receptive field (ERF) to include more…

LiDAR-based semantic segmentation is critical in the fields of robotics and autonomous driving as it provides a comprehensive understanding of the scene. This paper proposes a lightweight and efficient projection-based semantic segmentation…

The analysis of retinal images for the diagnosis of various diseases is one of the emerging areas of research. Recently, the research direction has been inclined towards investigating several changes in retinal blood vessels in subjects…

Unsupervised anomaly detection (UAD) has evolved from building specialized single-class models to unified multi-class models, yet existing multi-class models significantly underperform the most advanced one-for-one counterparts. Moreover,…

LiDAR scanning for surveying applications acquire measurements over wide areas and long distances, which produces large-scale 3D point clouds with significant local density variations. While existing 3D semantic segmentation models conduct…