710 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Huawei Technologies (United States)US3 papers
- University of RochesterUS3 papers
- University of Naples Federico IIIT2 papers
- Ames Research CenterUS1 paper
- Arizona State UniversityUS1 paper
- Centrum Wiskunde & InformaticaNL1 paper
- Delft University of TechnologyNL1 paper
- École de Technologie SupérieureCA1 paper
- Google (United States)US1 paper
- Imperial College LondonGB1 paper
- Institut National des Sciences Appliquées de LyonFR1 paper
- Lund UniversitySE1 paper
4 papers · 1 filter
K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
Haohang Xu, Hongkai Xiong, Guo-Jun Qi
In this paper, we propose the -Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual inst…
EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations
Xiao Wang, Daisuke Kihara, Jiebo Luo +1
Deep neural networks have been successfully applied to many real-world applications. However, such successes rely heavily on large amounts of labeled data that is expensive to obta…
Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
Guo-Jun Qi
In this paper, we present the Lipschitz regularization theory and algorithms for a novel Loss-Sensitive Generative Adversarial Network (LS-GAN). Specifically, it trains a loss func…
LOH and behold: Web-scale visual search, recommendation and clustering using Locally Optimized Hashing
Yannis Kalantidis, Lyndon Kennedy, Huy Nguyen +2
We propose a novel hashing-based matching scheme, called Locally Optimized Hashing (LOH), based on a state-of-the-art quantization algorithm that can be used for efficient, large-s…