Search Results for author: Kaiyu Song

Found 3 papers, 0 papers with code

Fisher Information Improved Training-Free Conditional Diffusion Model

no code implementations28 Apr 2024 Kaiyu Song, Hanjiang Lai

Recently, the diffusion model with the training-free methods has succeeded in conditional image generation tasks.

Conditional Image Generation

MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model

no code implementations8 Dec 2023 Kaiyu Song, Hanjiang Lai

Diffusion-based adversarial purification focuses on using the diffusion model to generate a clean image against such adversarial attacks.

Adversarial Purification

Target to Source: Guidance-Based Diffusion Model for Test-Time Adaptation

no code implementations8 Dec 2023 Kaiyu Song, Hanjiang Lai

However, 1) the semantic information loss from test data to the source domain and 2) the model shift between the source classifier and diffusion model would prevent the diffusion model from mapping the test data back to the source domain correctly.

Test-time Adaptation

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