951 citations
- Centre National de la Recherche ScientifiqueFR35 papers
- University of WalesGB23 papers
- University College LondonGB17 papers
- Australian National UniversityAU16 papers
- Chinese Academy of SciencesCN14 papers
- Trinity College DublinIE14 papers
- University of TrentoIT14 papers
- UNSW SydneyAU14 papers
- Queen's University BelfastGB13 papers
- Evgeni Kharadze Georgian National Astrophysical ObservatoryGE12 papers
- Goddard Space Flight CenterUS12 papers
- Shandong UniversityCN11 papers
6 papers · 2 filters
Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning
Haokui Zhang, Ying Li, Yenan Jiang +3
Recently, hyperspectral image (HSI) classification approaches based on deep learning (DL) models have been proposed and shown promising performance. However, because of very limite…
FFD: Fast Feature Detector
Morteza Ghahremani, Yonghuai Liu, Bernard Tiddeman
Scale-invariance, good localization and robustness to noise and distortions are the main properties that a local feature detector should possess. Most existing local feature detect…
Robust Unsupervised Small Area Change Detection from SAR Imagery Using Deep Learning
Xinzheng Zhang, Hang Su, Ce Zhang +3
Small area change detection from synthetic aperture radar (SAR) is a highly challenging task. In this paper, a robust unsupervised approach is proposed for small area change detect…
Orderly Disorder in Point Cloud Domain
Morteza Ghahremani, Bernard Tiddeman, Yonghuai Liu +1
In the real world, out-of-distribution samples, noise and distortions exist in test data. Existing deep networks developed for point cloud data analysis are prone to overfitting an…
NAS-Count: Counting-by-Density with Neural Architecture Search
Yutao Hu, Xiaolong Jiang, Xuhui Liu +4
Most of the recent advances in crowd counting have evolved from hand-designed density estimation networks, where multi-scale features are leveraged to address the scale variation p…
Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification
Liuyu Xiang, Guiguang Ding, Jungong Han
In real-world scenarios, data tends to exhibit a long-tailed distribution, which increases the difficulty of training deep networks. In this paper, we propose a novel self-paced kn…