4 citations · 8 across the 7 of their papers we have counts for
7 papers
Inter-Feature-Map Differential Coding of Surveillance Video
Kei Iino, Miho Takahashi, Hiroshi Watanabe +5
In Collaborative Intelligence, a deep neural network (DNN) is partitioned and deployed at the edge and the cloud for bandwidth saving and system optimization. When a model input is…
Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switching
Shohei Enomoto, Naoya Hasegawa, Kazuki Adachi +4
Deep neural networks have achieved remarkable success in a variety of computer vision applications. However, there is a problem of degrading accuracy when the data distribution shi…
Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss
Kei Iino, Shunsuke Akamatsu, Hiroshi Watanabe +3
Image coding for machines (ICM) aims to compress images for machine analysis using recognition models rather than human vision. Hence, in ICM, it is important for the encoder to re…
Incorporating Supervised Domain Generalization into Data Augmentation
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 compressi…
Dynamic Test-Time Augmentation via Differentiable Functions
Shohei Enomoto, Monikka Roslianna Busto, Takeharu Eda
Distribution shifts, which often occur in the real world, degrade the accuracy of deep learning systems, and thus improving robustness to distribution shifts is essential for pract…
Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems
Shohei Enomoto, Takeharu Eda
Recently, deep neural networks have become to be used in a variety of applications. While the accuracy of deep neural networks is increasing, the confidence score, which indicates…
Effective Data Augmentation with Multi-Domain Learning GANs
Shin'ya Yamaguchi, Sekitoshi Kanai, Takeharu Eda
For deep learning applications, the massive data development (e.g., collecting, labeling), which is an essential process in building practical applications, still incurs seriously…