Search Results for author: Kazuki Kozuka

Found 12 papers, 6 papers with code

Aligning Diffusion Models by Optimizing Human Utility

no code implementations6 Apr 2024 Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka

We present Diffusion-KTO, a novel approach for aligning text-to-image diffusion models by formulating the alignment objective as the maximization of expected human utility.

Wild2Avatar: Rendering Humans Behind Occlusions

no code implementations31 Dec 2023 Tiange Xiang, Adam Sun, Scott Delp, Kazuki Kozuka, Li Fei-Fei, Ehsan Adeli

In this work, we present Wild2Avatar, a neural rendering approach catered for occluded in-the-wild monocular videos.

Neural Rendering

Masking and Mixing Adversarial Training

no code implementations16 Feb 2023 Hiroki Adachi, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, Yasunori Ishii, Kazuki Kozuka

Adversarial training is a popular and straightforward technique to defend against the threat of adversarial examples.

Refine and Represent: Region-to-Object Representation Learning

1 code implementation25 Aug 2022 Akash Gokul, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato, Kazuki Kozuka, Trevor Darrell, Colorado J Reed

Recent works in self-supervised learning have demonstrated strong performance on scene-level dense prediction tasks by pretraining with object-centric or region-based correspondence objectives.

Object Representation Learning +4

Contrastive Neural Processes for Self-Supervised Learning

1 code implementation24 Oct 2021 Konstantinos Kallidromitis, Denis Gudovskiy, Kazuki Kozuka, Iku Ohama, Luca Rigazio

In this paper, we propose a novel self-supervised learning framework that combines contrastive learning with neural processes.

Contrastive Learning Data Augmentation +3

CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows

3 code implementations27 Jul 2021 Denis Gudovskiy, Shun Ishizaka, Kazuki Kozuka

Our approach results in a computationally and memory-efficient model: CFLOW-AD is faster and smaller by a factor of 10x than prior state-of-the-art with the same input setting.

Ranked #13 on Anomaly Detection on VisA (Detection AUROC metric)

Unsupervised Anomaly Detection

AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation

1 code implementation CVPR 2021 Denis Gudovskiy, Luca Rigazio, Shun Ishizaka, Kazuki Kozuka, Sotaro Tsukizawa

To overcome these limitations, we reformulate AutoAugment as a generalized automated dataset optimization (AutoDO) task that minimizes the distribution shift between test data and distorted train dataset.

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