43 citations · 88 across the 6 of their papers we have counts for
6 papers
A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?
Hiroaki Mikami, Kenji Fukumizu, Shogo Murai +5
Synthetic-to-real transfer learning is a framework in which a synthetically generated dataset is used to pre-train a model to improve its performance on real vision tasks. The most…
Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score
He Huang, Shunta Saito, Yuta Kikuchi +3
Scene graph parsing aims to detect objects in an image scene and recognize their relations. Recent approaches have achieved high average scores on some popular benchmarks, but fail…
Phase transition encoded in neural network
Kouji Kashiwa, Yuta Kikuchi, Akio Tomiya
We discuss an aspect of neural networks for the purpose of phase transition detection. To this end, we first train the neural network by feeding Ising/Potts configurations with lab…
Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions
Jun Hatori, Yuta Kikuchi, Sosuke Kobayashi +5
Comprehension of spoken natural language is an essential component for robots to communicate with human effectively. However, handling unconstrained spoken instructions is challeng…
Neural Sequence Model Training via -divergence Minimization
Sotetsu Koyamada, Yuta Kikuchi, Atsunori Kanemura +2
We propose a new neural sequence model training method in which the objective function is defined by -divergence. We demonstrate that the objective function generalizes the maxi…
Controlling Output Length in Neural Encoder-Decoders
Yuta Kikuchi, Graham Neubig, Ryohei Sasano +2
Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not investigated situations in which we would like to control t…