no code implementations • 26 Mar 2024 • Shohei Enomoto, Naoya Hasegawa, Kazuki Adachi, Taku Sasaki, Shin'ya Yamaguchi, Satoshi Suzuki, Takeharu Eda
We hypothesize that enhancing the input image reduces prediction's uncertainty and increase the accuracy of TTA methods.
no code implementations • 13 Feb 2024 • Kei Iino, Shunsuke Akamatsu, Hiroshi Watanabe, Shohei Enomoto, Akira Sakamoto, Takeharu Eda
Image coding for machines (ICM) aims to compress images for machine analysis using recognition models rather than human vision.
no code implementations • 2 Oct 2023 • Shohei Enomoto, Monikka Roslianna Busto, Takeharu Eda
With the increasing utilization of deep learning in outdoor settings, its robustness needs to be enhanced to preserve accuracy in the face of distribution shifts, such as compression artifacts.
no code implementations • 9 Dec 2022 • Shohei Enomoto, Monikka Roslianna Busto, Takeharu Eda
We propose a novel image enhancement method, DynTTA, which is based on differentiable data augmentation techniques and generates a blended image from many augmented images to improve the recognition accuracy under distribution shifts.
1 code implementation • 15 Apr 2021 • Shohei Enomoto, Takeharu Eda
This paper focuses on cascade inference systems, one kind of systems using confidence scores, and discusses the desired confidence score to improve system performance in terms of inference accuracy and computational cost.
no code implementations • 25 Dec 2019 • Shin'ya Yamaguchi, Sekitoshi Kanai, Takeharu Eda
When trained on each target dataset reduced the samples to 5, 000 images, Domain Fusion achieves better classification accuracy than the data augmentation using fine-tuned GANs.