Search Results for author: Jianze Li

Found 8 papers, 3 papers with code

One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation

no code implementations4 Feb 2025 Jianze Li, JieZhang Cao, Yong Guo, Wenbo Li, Yulun Zhang

We use the state-of-the-art diffusion model FLUX. 1-dev as both the teacher model and the base model.

Distillation-Free One-Step Diffusion for Real-World Image Super-Resolution

1 code implementation5 Oct 2024 Jianze Li, JieZhang Cao, Zichen Zou, Xiongfei Su, Xin Yuan, Yulun Zhang, Yong Guo, Xiaokang Yang

However, these methods incur substantial training costs and may constrain the performance of the student model by the teacher's limitations.

Image Super-Resolution Knowledge Distillation

Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation

no code implementations28 Aug 2024 Weilin Lin, Li Liu, Jianze Li, Hui Xiong

This method, based on our findings on neuron weight changes (NWCs) of random unlearning, uses optimal transport (OT)-based model fusion to combine the advantages of both pruned and backdoored models.

backdoor defense

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness

no code implementations30 May 2024 Weilin Lin, Li Liu, Shaokui Wei, Jianze Li, Hui Xiong

Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.

backdoor defense

TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks

no code implementations25 Nov 2022 Taoyong Cui, Jianze Li, Yuhan Dong, Li Liu

In the first stage, we propose a novel algorithm called polar decomposition-based orthogonal initialization (PDOI) to find a good initialization for the orthogonal optimization.

Data-free Backdoor Removal based on Channel Lipschitzness

1 code implementation5 Aug 2022 Runkai Zheng, Rongjun Tang, Jianze Li, Li Liu

Pruning these channels was then shown to be effective in mitigating the backdoor behaviors.

Point cloud denoising based on tensor Tucker decomposition

no code implementations20 Feb 2019 Jianze Li, Xiao-Ping Zhang, Tuan Tran

In this paper, we propose a new algorithm for point cloud denoising based on the tensor Tucker decomposition.

Denoising

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