6 citations · 21 across the 8 of their papers we have counts for
7 papers · 1 filter
Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts
Zhili Liu, Kai Chen, Jianhua Han +4
Masked Autoencoder~(MAE) is a prevailing self-supervised learning method that achieves promising results in model pre-training. However, when the various downstream tasks have data…
Implicit Concept Removal of Diffusion Models
Zhili Liu, Kai Chen, Yifan Zhang +6
Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. These concepts, termed as the "implicit concepts", could b…
DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning
Enze Xie, Lewei Yao, Han Shi +5
Diffusion models have proven to be highly effective in generating high-quality images. However, adapting large pre-trained diffusion models to new domains remains an open challenge…
Mixed Autoencoder for Self-supervised Visual Representation Learning
Kai Chen, Zhili Liu, Lanqing Hong +3
Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data augmentation s…
Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing
Zhili Liu, Jianhua Han, Lanqing Hong +4
Self-supervised learning (SSL), especially contrastive methods, has raised attraction recently as it learns effective transferable representations without semantic annotations. A c…
Relaxed Conditional Image Transfer for Semi-supervised Domain Adaptation
Qijun Luo, Zhili Liu, Lanqing Hong +7
Semi-supervised domain adaptation (SSDA), which aims to learn models in a partially labeled target domain with the assistance of the fully labeled source domain, attracts increasin…
EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement
Linpu Fang, Hang Xu, Zhili Liu +2
Object detectors trained on fully-annotated data currently yield state of the art performance but require expensive manual annotations. On the other hand, weakly-supervised detecto…