13 citations · 27 across the 21 of their papers we have counts for
21 papers
Scaling Laws for Data-Efficient Visual Transfer Learning
Wenxuan Yang, Qingqu Wei, Chenxi Ma +2
Current scaling laws for visual AI models focus predominantly on large-scale pretraining, leaving a critical gap in understanding how performance scales for data-constrained downst…
Non-Uniform Class-Wise Coreset Selection for Vision Model Fine-tuning
Hanyu Zhang, Zhen Xing, Ruian He +4
Coreset selection aims to identify a small yet highly informative subset of data, thereby enabling more efficient model training while reducing storage overhead. Recently, this cap…
A Self-Supervised Paradigm for Data-Efficient Medical Foundation Model Pre-training: V-information Optimization Framework
Wenxuan Yang, Hanyu Zhang, Weimin Tan +2
Self-supervised pre-training medical foundation models on large-scale datasets demonstrate exceptional performance. Recent research challenges this common paradigm by introducing d…
Addressing Imbalance for Class Incremental Learning in Medical Image Classification
Xuze Hao, Wenqian Ni, Xuhao Jiang +2
Deep convolutional neural networks have made significant breakthroughs in medical image classification, under the assumption that training samples from all classes are simultaneous…
Context-Aware Iteration Policy Network for Efficient Optical Flow Estimation
Ri Cheng, Ruian He, Xuhao Jiang +3
Existing recurrent optical flow estimation networks are computationally expensive since they use a fixed large number of iterations to update the flow field for each sample. An eff…
A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models
Wenxuan Yang, Weimin Tan, Yuqi Sun +1
Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-trainin…
Low-latency Space-time Supersampling for Real-time Rendering
Ruian He, Shili Zhou, Yuqi Sun +3
With the rise of real-time rendering and the evolution of display devices, there is a growing demand for post-processing methods that offer high-resolution content in a high frame…
A Generative Framework for Self-Supervised Facial Representation Learning
Ruian He, Zhen Xing, Weimin Tan +1
Self-supervised representation learning has gained increasing attention for strong generalization ability without relying on paired datasets. However, it has not been explored suff…
MVFlow: Deep Optical Flow Estimation of Compressed Videos with Motion Vector Prior
Shili Zhou, Xuhao Jiang, Weimin Tan +2
In recent years, many deep learning-based methods have been proposed to tackle the problem of optical flow estimation and achieved promising results. However, they hardly consider…
SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model
Shili Zhou, Ruian He, Weimin Tan +1
Optical Flow Estimation aims to find the 2D dense motion field between two frames. Due to the limitation of model structures and training datasets, existing methods often rely too…
Uncertainty-Guided Spatial Pruning Architecture for Efficient Frame Interpolation
Ri Cheng, Xuhao Jiang, Ruian He +3
The video frame interpolation (VFI) model applies the convolution operation to all locations, leading to redundant computations in regions with easy motion. We can use dynamic spat…
DifFSS: Diffusion Model for Few-Shot Semantic Segmentation
Weimin Tan, Siyuan Chen, Bo Yan
Diffusion models have demonstrated excellent performance in image generation. Although various few-shot semantic segmentation (FSS) models with different network structures have be…
Instruct-NeuralTalker: Editing Audio-Driven Talking Radiance Fields with Instructions
Yuqi Sun, Ruian He, Weimin Tan +1
Recent neural talking radiance field methods have shown great success in photorealistic audio-driven talking face synthesis. In this paper, we propose a novel interactive framework…
Learning Survival Distribution with Implicit Survival Function
Yu Ling, Weimin Tan, Bo Yan
Survival analysis aims at modeling the relationship between covariates and event occurrence with some untracked (censored) samples. In implementation, existing methods model the su…
Multi-Modality Deep Network for JPEG Artifacts Reduction
Xuhao Jiang, Weimin Tan, Qing Lin +3
In recent years, many convolutional neural network-based models are designed for JPEG artifacts reduction, and have achieved notable progress. However, few methods are suitable for…
Multi-Modality Deep Network for Extreme Learned Image Compression
Xuhao Jiang, Weimin Tan, Tian Tan +2
Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur…
Geometry-Aware Reference Synthesis for Multi-View Image Super-Resolution
Ri Cheng, Yuqi Sun, Bo Yan +2
Recent multi-view multimedia applications struggle between high-resolution (HR) visual experience and storage or bandwidth constraints. Therefore, this paper proposes a Multi-View…
Learning Parallax Transformer Network for Stereo Image JPEG Artifacts Removal
Xuhao Jiang, Weimin Tan, Ri Cheng +2
Under stereo settings, the performance of image JPEG artifacts removal can be further improved by exploiting the additional information provided by a second view. However, incorpor…
Perception-Oriented Stereo Image Super-Resolution
Chenxi Ma, Bo Yan, Weimin Tan +1
Recent studies of deep learning based stereo image super-resolution (StereoSR) have promoted the development of StereoSR. However, existing StereoSR models mainly concentrate on im…
Rethinking Super-Resolution as Text-Guided Details Generation
Chenxi Ma, Bo Yan, Qing Lin +2
Deep neural networks have greatly promoted the performance of single image super-resolution (SISR). Conventional methods still resort to restoring the single high-resolution (HR) s…
Feature Pyramid Network for Multi-task Affective Analysis
Ruian He, Zhen Xing, Weimin Tan +1
Affective Analysis is not a single task, and the valence-arousal value, expression class, and action unit can be predicted at the same time. Previous researches did not pay enough…