34 citations · 96 across the 17 of their papers we have counts for
17 papers
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Yuhui Xu, Lingxi Xie, Xiaotao Gu +6
Recently years have witnessed a rapid development of large language models (LLMs). Despite the strong ability in many language-understanding tasks, the heavy computational burden l…
ControlVideo: Training-free Controllable Text-to-Video Generation
Yabo Zhang, Yuxiang Wei, Dongsheng Jiang +3
Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temp…
ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories
Zijian Zhang, Zhou Zhao, Jun Yu +1
Diffusion models have recently exhibited remarkable abilities to synthesize striking image samples since the introduction of denoising diffusion probabilistic models (DDPMs). Their…
M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios
Ning Liao, Xiaopeng Zhang, Min Cao +1
In realistic open-set scenarios where labels of a part of testing data are totally unknown, when vision-language (VL) prompt learning methods encounter inputs related to unknown cl…
Rethinking Visual Prompt Learning as Masked Visual Token Modeling
Ning Liao, Bowen Shi, Xiaopeng Zhang +3
Prompt learning has achieved great success in efficiently exploiting large-scale pre-trained models in natural language processing (NLP). It reformulates the downstream tasks as th…
ConfounderGAN: Protecting Image Data Privacy with Causal Confounder
Qi Tian, Kun Kuang, Kelu Jiang +3
The success of deep learning is partly attributed to the availability of massive data downloaded freely from the Internet. However, it also means that users' private data may be co…
See Blue Sky: Deep Image Dehaze Using Paired and Unpaired Training Images
Xiaoyan Zhang, Gaoyang Tang, Yingying Zhu +1
The issue of image haze removal has attracted wide attention in recent years. However, most existing haze removal methods cannot restore the scene with clear blue sky, since the co…
SdAE: Self-distillated Masked Autoencoder
Yabo Chen, Yuchen Liu, Dongsheng Jiang +4
With the development of generative-based self-supervised learning (SSL) approaches like BeiT and MAE, how to learn good representations by masking random patches of the input image…
DE-Net: Dynamic Text-guided Image Editing Adversarial Networks
Ming Tao, Bing-Kun Bao, Hao Tang +3
Text-guided image editing models have shown remarkable results. However, there remain two problems. First, they employ fixed manipulation modules for various editing requirements (…
DATA: Domain-Aware and Task-Aware Self-supervised Learning
Qing Chang, Junran Peng, Lingxie Xie +4
The paradigm of training models on massive data without label through self-supervised learning (SSL) and finetuning on many downstream tasks has become a trend recently. However, d…
Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection
Rui Liu, Yahong Han, Yaowei Wang +1
Domain adaptive object detection (DAOD) aims to improve the generalization ability of detectors when the training and test data are from different domains. Considering the signific…
DVCFlow: Modeling Information Flow Towards Human-like Video Captioning
Xu Yan, Zhengcong Fei, Shuhui Wang +2
Dense video captioning (DVC) aims to generate multi-sentence descriptions to elucidate the multiple events in the video, which is challenging and demands visual consistency, discou…
Domain Adaptation without Model Transferring
Kunhong Wu, Yucheng Shi, Yahong Han +3
In recent years, researchers have been paying increasing attention to the threats brought by deep learning models to data security and privacy, especially in the field of domain ad…
Analysis and Applications of Class-wise Robustness in Adversarial Training
Qi Tian, Kun Kuang, Kelu Jiang +2
Adversarial training is one of the most effective approaches to improve model robustness against adversarial examples. However, previous works mainly focus on the overall robustnes…
Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
Hui Wang, Jian Tian, Songyuan Li +4
Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning. In principle, e…
MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning
Hanbin Zhao, Yongjian Fu, Mintong Kang +3
As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and f…
TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge
Junyi Feng, Songyuan Li, Xi Li +4
Real-time semantic video segmentation is a challenging task due to the strict requirements of inference speed. Recent approaches mainly devote great efforts to reducing the model s…