323 citations · 2.1k across the 141 of their papers we have counts for
30 papers · 1 filter
Diffusion Probabilistic Model Made Slim
Xingyi Yang, Daquan Zhou, Jiashi Feng +1
Despite the recent visually-pleasing results achieved, the massive computational cost has been a long-standing flaw for diffusion probabilistic models (DPMs), which, in turn, great…
AvatarGen: A 3D Generative Model for Animatable Human Avatars
Jianfeng Zhang, Zihang Jiang, Dingdong Yang +6
Unsupervised generation of 3D-aware clothed humans with various appearances and controllable geometries is important for creating virtual human avatars and other AR/VR applications…
Deep Model Reassembly
Xingyi Yang, Daquan Zhou, Songhua Liu +2
In this paper, we explore a novel knowledge-transfer task, termed as Deep Model Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous models pre-t…
Task Residual for Tuning Vision-Language Models
Tao Yu, Zhihe Lu, Xin Jin +2
Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts. In principle, the well-learned kn…
Dataset Distillation via Factorization
Songhua Liu, Kai Wang, Xingyi Yang +2
In this paper, we study \xw{dataset distillation (DD)}, from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play…
Reachability-Aware Laplacian Representation in Reinforcement Learning
Kaixin Wang, Kuangqi Zhou, Jiashi Feng +2
In Reinforcement Learning (RL), Laplacian Representation (LapRep) is a task-agnostic state representation that encodes the geometry of the environment. A desirable property of LapR…
Training Spiking Neural Networks with Local Tandem Learning
Qu Yang, Jibin Wu, Malu Zhang +3
Spiking neural networks (SNNs) are shown to be more biologically plausible and energy efficient over their predecessors. However, there is a lack of an efficient and generalized tr…
Attention Diversification for Domain Generalization
Rang Meng, Xianfeng Li, Weijie Chen +7
Convolutional neural networks (CNNs) have demonstrated gratifying results at learning discriminative features. However, when applied to unseen domains, state-of-the-art models are…
MetaFormer Baselines for Vision
Weihao Yu, Chenyang Si, Pan Zhou +5
MetaFormer, the abstracted architecture of Transformer, has been found to play a significant role in achieving competitive performance. In this paper, we further explore the capaci…
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
Dongze Lian, Daquan Zhou, Jiashi Feng +1
Existing fine-tuning methods either tune all parameters of the pre-trained model (full fine-tuning), which is not efficient, or only tune the last linear layer (linear probing), wh…
Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons
Yu Cheng, Yihao Ai, Bo Wang +2
In multi-person 2D pose estimation, the bottom-up methods simultaneously predict poses for all persons, and unlike the top-down methods, do not rely on human detection. However, th…
AvatarGen: a 3D Generative Model for Animatable Human Avatars
Jianfeng Zhang, Zihang Jiang, Dingdong Yang +6
Unsupervised generation of clothed virtual humans with various appearance and animatable poses is important for creating 3D human avatars and other AR/VR applications. Existing met…
Federated Selective Aggregation for Knowledge Amalgamation
Donglin Xie, Ruonan Yu, Gongfan Fang +5
In this paper, we explore a new knowledge-amalgamation problem, termed Federated Selective Aggregation (FedSA). The goal of FedSA is to train a student model for a new task with th…
Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection
Gaoang Wang, Yibing Zhan, Xinchao Wang +2
Anomaly detection aims at identifying deviant samples from the normal data distribution. Contrastive learning has provided a successful way to sample representation that enables ef…
Learning with Recoverable Forgetting
Jingwen Ye, Yifang Fu, Jie Song +5
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge. However, the involved training data may not be life-long legitimate du…
Learning Graph Neural Networks for Image Style Transfer
Yongcheng Jing, Yining Mao, Yiding Yang +4
State-of-the-art parametric and non-parametric style transfer approaches are prone to either distorted local style patterns due to global statistics alignment, or unpleasing artifa…
DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation
Songhua Liu, Jingwen Ye, Sucheng Ren +1
One key challenge of exemplar-guided image generation lies in establishing fine-grained correspondences between input and guided images. Prior approaches, despite the promising res…
Factorizing Knowledge in Neural Networks
Xingyi Yang, Jingwen Ye, Xinchao Wang
In this paper, we explore a novel and ambitious knowledge-transfer task, termed Knowledge Factorization~(KF). The core idea of KF lies in the modularization and assemblability of k…
Ask-AC: An Initiative Advisor-in-the-Loop Actor-Critic Framework
Shunyu Liu, Kaixuan Chen, Na Yu +3
Despite the promising results achieved, state-of-the-art interactive reinforcement learning schemes rely on passively receiving supervision signals from advisor experts, in the for…
Slimmable Domain Adaptation
Rang Meng, Weijie Chen, Shicai Yang +7
Vanilla unsupervised domain adaptation methods tend to optimize the model with fixed neural architecture, which is not very practical in real-world scenarios since the target data…
Learning Domain Adaptive Object Detection with Probabilistic Teacher
Meilin Chen, Weijie Chen, Shicai Yang +8
Self-training for unsupervised domain adaptive object detection is a challenging task, of which the performance depends heavily on the quality of pseudo boxes. Despite the promisin…
Inception Transformer
Chenyang Si, Weihao Yu, Pan Zhou +3
Recent studies show that Transformer has strong capability of building long-range dependencies, yet is incompetent in capturing high frequencies that predominantly convey local inf…
Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction
Kuangqi Zhou, Kaixin Wang, Jiashi Feng +3
How to accurately predict the properties of molecules is an essential problem in AI-driven drug discovery, which generally requires a large amount of annotation for training deep l…
FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders
Kai Wang, Bo Zhao, Xiangyu Peng +5
Face recognition, as one of the most successful applications in artificial intelligence, has been widely used in security, administration, advertising, and healthcare. However, the…