activity
20182022
most citedNon-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets

1 citations · 1 across the 1 of their papers we have counts for

collaborators

5 papers

cs.CV20221 cited

Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets

Yuki Tanaka, Shuhei M. Yoshida, Makoto Terao

We propose a non-iterative method to optimize pseudo-labeling thresholds for learning object detection from a collection of low-cost datasets, each of which is annotated for only a…

stat.ML2021

Lower-Bounded Proper Losses for Weakly Supervised Classification

Shuhei M. Yoshida, Takashi Takenouchi, Masashi Sugiyama

This paper discusses the problem of weakly supervised classification, in which instances are given weak labels that are produced by some label-corruption process. The goal is to de…

cond-mat.quant-gas2021

Quantum behavior of a heavy impurity strongly coupled to a Bose gas

Jesper Levinsen, Luis A. Peña Ardila, Shuhei M. Yoshida +1

We investigate the problem of an infinitely heavy impurity interacting with a dilute Bose gas at zero temperature. When the impurity-boson interactions are short ranged, we show th…

cond-mat.quant-gas2018

Few-body states of bosons interacting with a heavy quantum impurity

Shuhei M. Yoshida, Zhe-Yu Shi, Jesper Levinsen +1

We consider the problem of a fixed impurity coupled to a small number of non-interacting bosons. We focus on impurity-boson interactions that are mediated by a closed-channel m…

cond-mat.quant-gas2018

Impurity-induced multi-body resonances in a Bose gas

Zhe-Yu Shi, Shuhei M. Yoshida, Meera M. Parish +1

We investigate the problem of identical bosons that are coupled to an impurity particle with infinite mass. For non-interacting bosons, we show that a dynamical impurity-boson…