Search Results for author: Subhankar Roy

Found 7 papers, 4 papers with code

Neighborhood Contrastive Learning for Novel Class Discovery

no code implementations CVPR 2021 Zhun Zhong, Enrico Fini, Subhankar Roy, Zhiming Luo, Elisa Ricci, Nicu Sebe

In this paper, we address Novel Class Discovery (NCD), the task of unveiling new classes in a set of unlabeled samples given a labeled dataset with known classes.

Contrastive Learning

Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation

1 code implementation CVPR 2021 Subhankar Roy, Evgeny Krivosheev, Zhun Zhong, Nicu Sebe, Elisa Ricci

In this paper we address multi-target domain adaptation (MTDA), where given one labeled source dataset and multiple unlabeled target datasets that differ in data distributions, the task is to learn a robust predictor for all the target domains.

Curriculum Learning Domain Adaptation +1

TriGAN: Image-to-Image Translation for Multi-Source Domain Adaptation

no code implementations19 Apr 2020 Subhankar Roy, Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe, Elisa Ricci

In this paper we propose the first approach for Multi-Source Domain Adaptation (MSDA) based on Generative Adversarial Networks.

Domain Adaptation Image-to-Image Translation +1

Motion-supervised Co-Part Segmentation

1 code implementation7 Apr 2020 Aliaksandr Siarohin, Subhankar Roy, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe

To overcome this limitation, we propose a self-supervised deep learning method for co-part segmentation.

Regularized Evolutionary Algorithm for Dynamic Neural Topology Search

no code implementations15 May 2019 Cristiano Saltori, Subhankar Roy, Nicu Sebe, Giovanni Iacca

Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i. e., network architectures) and is therefore memory expensive.

Neural Architecture Search Object Recognition

Metric-Learning based Deep Hashing Network for Content Based Retrieval of Remote Sensing Images

1 code implementation2 Apr 2019 Subhankar Roy, Enver Sangineto, Begüm Demir, Nicu Sebe

Hashing methods have been recently found very effective in retrieval of remote sensing (RS) images due to their computational efficiency and fast search speed.

Metric Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.