Search Results for author: Jaesung Ahn

Found 4 papers, 0 papers with code

Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective

no code implementations19 Dec 2023 HyeongGwon Hong, Yooshin Cho, Hanbyel Cho, Jaesung Ahn, Junmo Kim

Gradient norm, which is commonly used as a vulnerability proxy for gradient inversion attack, cannot explain this as it remains constant regardless of the loss function for gradient matching.

Federated Learning

Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view

no code implementations CVPR 2023 Hanbyel Cho, Yooshin Cho, Jaesung Ahn, Junmo Kim

This is because we have a mental model that allows us to imagine a person's appearance at different viewing directions from a given image and utilize the consistency between them for inference.

3D Human Pose Estimation Human Mesh Recovery +1

Localization using Multi-Focal Spatial Attention for Masked Face Recognition

no code implementations3 May 2023 Yooshin Cho, Hanbyel Cho, Hyeong Gwon Hong, Jaesung Ahn, Dongmin Cho, JungWoo Chang, Junmo Kim

In our method, standard spatial attention and networks focus on unmasked regions, and extract mask-invariant features while minimizing the loss of the conventional Face Recognition (FR) performance.

Face Recognition

Rethinking Efficacy of Softmax for Lightweight Non-Local Neural Networks

no code implementations27 Jul 2022 Yooshin Cho, Youngsoo Kim, Hanbyel Cho, Jaesung Ahn, Hyeong Gwon Hong, Junmo Kim

Attention maps normalized with softmax operation highly rely upon magnitude of key vectors, and performance is degenerated if the magnitude information is removed.

Cannot find the paper you are looking for? You can Submit a new open access paper.