297 citations · 445 across the 19 of their papers we have counts for
20 papers
Two are better than one: Context window extension with multi-grained self-injection
Wei Han, Pan Zhou, Soujanya Poria +1
The limited context window of contemporary large language models (LLMs) remains a huge barrier to their broader application across various domains. While continual pre-training on…
Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction
Qiuhong Shen, Zike Wu, Xuanyu Yi +4
We tackle the challenge of efficiently reconstructing a 3D asset from a single image at millisecond speed. Existing methods for single-image 3D reconstruction are primarily based o…
Instant3D: Instant Text-to-3D Generation
Ming Li, Pan Zhou, Jia-Wei Liu +4
Text-to-3D generation has attracted much attention from the computer vision community. Existing methods mainly optimize a neural field from scratch for each text prompt, relying on…
ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection
Zhongzhan Huang, Pan Zhou, Shuicheng Yan +1
In diffusion models, UNet is the most popular network backbone, since its long skip connects (LSCs) to connect distant network blocks can aggregate long-distant information and all…
InceptionNeXt: When Inception Meets ConvNeXt
Weihao Yu, Pan Zhou, Shuicheng Yan +1
Inspired by the long-range modeling ability of ViTs, large-kernel convolutions are widely studied and adopted recently to enlarge the receptive field and improve model performance,…
MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer
Shanghua Gao, Pan Zhou, Ming-Ming Cheng +1
Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in a…
Contrastive Video Question Answering via Video Graph Transformer
Junbin Xiao, Pan Zhou, Angela Yao +4
We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1)…
STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition
Ming Li, Xiangyu Xu, Hehe Fan +7
Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks…
Position-guided Text Prompt for Vision-Language Pre-training
Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou +1
Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe t…
Towards Sustainable Self-supervised Learning
Shanghua Gao, Pan Zhou, Ming-Ming Cheng +1
Although increasingly training-expensive, most self-supervised learning (SSL) models have repeatedly been trained from scratch but not fully utilized, since only a few SOTAs are em…
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…
LPT: Long-tailed Prompt Tuning for Image Classification
Bowen Dong, Pan Zhou, Shuicheng Yan +1
For long-tailed classification, most works often pretrain a big model on a large-scale dataset, and then fine-tune the whole model for adapting to long-tailed data. Though promisin…
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
Xingyu Xie, Pan Zhou, Huan Li +2
In deep learning, different kinds of deep networks typically need different optimizers, which have to be chosen after multiple trials, making the training process inefficient. To r…
Video Graph Transformer for Video Question Answering
Junbin Xiao, Pan Zhou, Tat-Seng Chua +1
This paper proposes a Video Graph Transformer (VGT) model for Video Quetion Answering (VideoQA). VGT's uniqueness are two-fold: 1) it designs a dynamic graph transformer module whi…
Towards Understanding Why Mask-Reconstruction Pretraining Helps in Downstream Tasks
Jiachun Pan, Pan Zhou, Shuicheng Yan
For unsupervised pretraining, mask-reconstruction pretraining (MRP) approaches, e.g. MAE and data2vec, randomly mask input patches and then reconstruct the pixels or semantic featu…
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…
Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees
Binghui Wang, Youqi Li, Pan Zhou
Graph neural networks (GNNs) have achieved state-of-the-art performance in many graph-based tasks such as node classification and graph classification. However, many recent works h…
Mugs: A Multi-Granular Self-Supervised Learning Framework
Pan Zhou, Yichen Zhou, Chenyang Si +3
In self-supervised learning, multi-granular features are heavily desired though rarely investigated, as different downstream tasks (e.g., general and fine-grained classification) o…
Self-Promoted Supervision for Few-Shot Transformer
Bowen Dong, Pan Zhou, Shuicheng Yan +1
The few-shot learning ability of vision transformers (ViTs) is rarely investigated though heavily desired. In this work, we empirically find that with the same few-shot learning fr…
TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
Zhuolin Yang, Linyi Li, Xiaojun Xu +6
Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from diff…