359 citations · 1k across the 68 of their papers we have counts for
24 papers · 1 filter
CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation
Weibin Liao, Xuhong Li, Qingzhong Wang +3
While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on ma…
MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts
Weibin Liao, Haoyi Xiong, Qingzhong Wang +6
While self-supervised learning (SSL) algorithms have been widely used to pre-train deep models, few efforts [11] have been done to improve representation learning of X-ray image an…
TiC: Exploring Vision Transformer in Convolution
Song Zhang, Qingzhong Wang, Jiang Bian +1
While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the…
Robust Cross-Modal Knowledge Distillation for Unconstrained Videos
Wenke Xia, Xingjian Li, Andong Deng +3
Cross-modal distillation has been widely used to transfer knowledge across different modalities, enriching the representation of the target unimodal one. Recent studies highly rela…
Video4MRI: An Empirical Study on Brain Magnetic Resonance Image Analytics with CNN-based Video Classification Frameworks
Yuxuan Zhang, Qingzhong Wang, Jiang Bian +4
To address the problem of medical image recognition, computer vision techniques like convolutional neural networks (CNN) are frequently used. Recently, 3D CNN-based models dominate…
Temporal Output Discrepancy for Loss Estimation-based Active Learning
Siyu Huang, Tianyang Wang, Haoyi Xiong +3
While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of dat…
Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features
Qingrui Jia, Xuhong Li, Lei Yu +5
While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled sample…
ExpNet: A unified network for Expert-Level Classification
Junde Wu, Huihui Fang, Yehui Yang +4
Different from the general visual classification, some classification tasks are more challenging as they need the professional categories of the images. In the paper, we call them…
MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model
Junde Wu, Rao Fu, Huihui Fang +5
Diffusion probabilistic model (DPM) recently becomes one of the hottest topic in computer vision. Its image generation application such as Imagen, Latent Diffusion Models and Stabl…
RAIS: Robust and Accurate Interactive Segmentation via Continual Learning
Yuying Hao, Yi Liu, Juncai Peng +5
Interactive image segmentation aims at segmenting a target region through a way of human-computer interaction. Recent works based on deep learning have achieved excellent performan…
GLARE: A Dataset for Traffic Sign Detection in Sun Glare
Nicholas Gray, Megan Moraes, Jiang Bian +6
Real-time machine learning object detection algorithms are often found within autonomous vehicle technology and depend on quality datasets. It is essential that these algorithms wo…
Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models
Xuhong Li, Haoyi Xiong, Yi Liu +4
While fine-tuning pre-trained networks has become a popular way to train image segmentation models, such backbone networks for image segmentation are frequently pre-trained using i…
P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
Jiang Bian, Xuhong Li, Tao Wang +7
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos…
A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications
Fei Wu, Qingzhong Wang, Jian Bian +5
To understand human behaviors, action recognition based on videos is a common approach. Compared with image-based action recognition, videos provide much more information. Reducing…
Towards Inadequately Pre-trained Models in Transfer Learning
Andong Deng, Xingjian Li, Di Hu +3
Pre-training has been a popular learning paradigm in deep learning era, especially in annotation-insufficient scenario. Better ImageNet pre-trained models have been demonstrated, f…
PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset
Lutao Chu, Yi Liu, Zewu Wu +8
As the COVID-19 pandemic rampages across the world, the demands of video conferencing surge. To this end, real-time portrait segmentation becomes a popular feature to replace backg…
Semi-Supervised Active Learning with Temporal Output Discrepancy
Siyu Huang, Tianyang Wang, Haoyi Xiong +2
While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of dat…
Face.evoLVe: A High-Performance Face Recognition Library
Qingzhong Wang, Pengfei Zhang, Haoyi Xiong +1
In this paper, we develop face.evoLVe -- a comprehensive library that collects and implements a wide range of popular deep learning-based methods for face recognition. First of all…
Generating Person Images with Appearance-aware Pose Stylizer
Siyu Huang, Haoyi Xiong, Zhi-Qi Cheng +5
Generation of high-quality person images is challenging, due to the sophisticated entanglements among image factors, e.g., appearance, pose, foreground, background, local details,…
Parameter-Free Style Projection for Arbitrary Style Transfer
Siyu Huang, Haoyi Xiong, Tianyang Wang +5
Arbitrary image style transfer is a challenging task which aims to stylize a content image conditioned on arbitrary style images. In this task the feature-level content-style trans…
Curriculum Audiovisual Learning
Di Hu, Zheng Wang, Haoyi Xiong +3
Associating sound and its producer in complex audiovisual scene is a challenging task, especially when we are lack of annotated training data. In this paper, we present a flexible…
Ultrafast Photorealistic Style Transfer via Neural Architecture Search
Jie An, Haoyi Xiong, Jun Huan +1
The key challenge in photorealistic style transfer is that an algorithm should faithfully transfer the style of a reference photo to a content photo while the generated image shoul…
Fast Universal Style Transfer for Artistic and Photorealistic Rendering
Jie An, Haoyi Xiong, Jiebo Luo +2
Universal style transfer is an image editing task that renders an input content image using the visual style of arbitrary reference images, including both artistic and photorealist…
StyleNAS: An Empirical Study of Neural Architecture Search to Uncover Surprisingly Fast End-to-End Universal Style Transfer Networks
Jie An, Haoyi Xiong, Jinwen Ma +2
Neural Architecture Search (NAS) has been widely studied for designing discriminative deep learning models such as image classification, object detection, and semantic segmentation…