Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Marios Savvides

Marios Savvides

An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning

Nov 20, 2022
Hao Chen, Yue Fan, Yidong Wang, Jindong Wang, Bernt Schiele, Xing Xie, Marios Savvides, Bhiksha Raj

Figure 1 for An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning

Figure 2 for An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning

Figure 3 for An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning

Figure 4 for An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning

* Imbalanced Semi-Supervised Learning

Access Paper or Ask Questions

Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition

Sep 11, 2022
Thanh-Dat Truong, Chi Nhan Duong, Ngan Le, Marios Savvides, Khoa Luu

Figure 1 for Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition

Figure 2 for Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition

Figure 3 for Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition

Figure 4 for Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition

* arXiv admin note: substantial text overlap with arXiv:2003.06958

Access Paper or Ask Questions

Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets

Aug 24, 2022
Hao Chen, Ran Tao, Han Zhang, Yidong Wang, Wei Ye, Jindong Wang, Guosheng Hu, Marios Savvides

Figure 1 for Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets

Figure 2 for Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets

Figure 3 for Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets

Figure 4 for Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets

* wrong version

Access Paper or Ask Questions

USB: A Unified Semi-supervised Learning Benchmark

Aug 12, 2022
Yidong Wang, Hao Chen, Yue Fan, Wang Sun, Ran Tao, Wenxin Hou, Renjie Wang, Linyi Yang, Zhi Zhou, Lan-Zhe Guo, Heli Qi, Zhen Wu, Yu-Feng Li, Satoshi Nakamura, Wei Ye, Marios Savvides, Bhiksha Raj, Takahiro Shinozaki, Bernt Schiele, Jindong Wang, Xing Xie, Yue Zhang

Figure 1 for USB: A Unified Semi-supervised Learning Benchmark

Figure 2 for USB: A Unified Semi-supervised Learning Benchmark

Figure 3 for USB: A Unified Semi-supervised Learning Benchmark

Figure 4 for USB: A Unified Semi-supervised Learning Benchmark

* Submitted to NeurIPS'22 dataset and benchmark track; code at https://github.com/microsoft/Semi-supervised-learning

Access Paper or Ask Questions

Powering Finetuning in Few-shot Learning: Domain-Agnostic Feature Adaptation with Rectified Class Prototypes

Apr 07, 2022
Ran Tao, Han Zhang, Yutong Zheng, Marios Savvides

Figure 1 for Powering Finetuning in Few-shot Learning: Domain-Agnostic Feature Adaptation with Rectified Class Prototypes

Figure 2 for Powering Finetuning in Few-shot Learning: Domain-Agnostic Feature Adaptation with Rectified Class Prototypes

Figure 3 for Powering Finetuning in Few-shot Learning: Domain-Agnostic Feature Adaptation with Rectified Class Prototypes

Figure 4 for Powering Finetuning in Few-shot Learning: Domain-Agnostic Feature Adaptation with Rectified Class Prototypes

* published in AAAI-22

Access Paper or Ask Questions

Unitail: Detecting, Reading, and Matching in Retail Scene

Apr 01, 2022
Fangyi Chen, Han Zhang, Zaiwang Li, Jiachen Dou, Shentong Mo, Hao Chen, Yongxin Zhang, Uzair Ahmed, Chenchen Zhu, Marios Savvides

Figure 1 for Unitail: Detecting, Reading, and Matching in Retail Scene

Figure 2 for Unitail: Detecting, Reading, and Matching in Retail Scene

Figure 3 for Unitail: Detecting, Reading, and Matching in Retail Scene

Figure 4 for Unitail: Detecting, Reading, and Matching in Retail Scene

* Technical Report

Access Paper or Ask Questions