activity
20152022
most citedRevisiting Fine-tuning for Few-shot Learning

30 citations · 193 across the 34 of their papers we have counts for

collaborators
Showing 2019Show all

17 papers · 1 filter

cs.CV20197 cited

Self-supervised Learning of 3D Objects from Natural Images

Hiroharu Kato, Tatsuya Harada

We present a method to learn single-view reconstruction of the 3D shape, pose, and texture of objects from categorized natural images in a self-supervised manner. Since this is a s…

cs.CV201925 cited

Domain Generalization Using a Mixture of Multiple Latent Domains

Toshihiko Matsuura, Tatsuya Harada

When domains, which represent underlying data distributions, vary during training and testing processes, deep neural networks suffer a drop in their performance. Domain generalizat…

cs.CV2019

Noise Robust Generative Adversarial Networks

Takuhiro Kaneko, Tatsuya Harada

Generative adversarial networks (GANs) are neural networks that learn data distributions through adversarial training. In intensive studies, recent GANs have shown promising result…

cs.CV2019

Unsupervised Keyword Extraction for Full-sentence VQA

Kohei Uehara, Tatsuya Harada

In the majority of the existing Visual Question Answering (VQA) research, the answers consist of short, often single words, as per instructions given to the annotators during datas…

eess.IV20197 cited

Multi-Stage Pathological Image Classification using Semantic Segmentation

Shusuke Takahama, Yusuke Kurose, Yusuke Mukuta +5

Histopathological image analysis is an essential process for the discovery of diseases such as cancer. However, it is challenging to train CNN on whole slide images (WSIs) of gigap…

cs.LG20193 cited

A General Upper Bound for Unsupervised Domain Adaptation

Dexuan Zhang, Tatsuya Harada

In this work, we present a novel upper bound of target error to address the problem for unsupervised domain adaptation. Recent studies reveal that a deep neural network can learn t…