2.2k citations · 2.8k across the 16 of their papers we have counts for
18 papers
Pseudo-label Alignment for Semi-supervised Instance Segmentation
Jie Hu, Chen Chen, Liujuan Cao +4
Pseudo-labeling is significant for semi-supervised instance segmentation, which generates instance masks and classes from unannotated images for subsequent training. However, in ex…
You Only Segment Once: Towards Real-Time Panoptic Segmentation
Jie Hu, Linyan Huang, Tianhe Ren +3
In this paper, we propose YOSO, a real-time panoptic segmentation framework. YOSO predicts masks via dynamic convolutions between panoptic kernels and image feature maps, in which…
DistilPose: Tokenized Pose Regression with Heatmap Distillation
Suhang Ye, Yingyi Zhang, Jie Hu +6
In the field of human pose estimation, regression-based methods have been dominated in terms of speed, while heatmap-based methods are far ahead in terms of performance. How to tak…
Bag of Tricks with Quantized Convolutional Neural Networks for image classification
Jie Hu, Mengze Zeng, Enhua Wu
Deep neural networks have been proven effective in a wide range of tasks. However, their high computational and memory costs make them impractical to deploy on resource-constrained…
Deep Machine Learning Reconstructing Lattice Topology with Strong Thermal Fluctuations
Xiao-Han Wang, Pei Shi, Bin Xi +2
Applying artificial intelligence to scientific problems (namely AI for science) is currently under hot debate. However, the scientific problems differ much from the conventional on…
Elastic-Link for Binarized Neural Network
Jie Hu, Ziheng Wu, Vince Tan +3
Recent work has shown that Binarized Neural Networks (BNNs) are able to greatly reduce computational costs and memory footprints, facilitating model deployment on resource-constrai…
LODE: Deep Local Deblurring and A New Benchmark
Zerun Wang, Liuyu Xiang, Fan Yang +6
While recent deep deblurring algorithms have achieved remarkable progress, most existing methods focus on the global deblurring problem, where the image blur mostly arises from sev…
Unifying Nonlocal Blocks for Neural Networks
Lei Zhu, Qi She, Duo Li +4
The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks. Although having shown excellent performance, they still lack…
ISTR: End-to-End Instance Segmentation with Transformers
Jie Hu, Liujuan Cao, Yao Lu +6
End-to-end paradigms significantly improve the accuracy of various deep-learning-based computer vision models. To this end, tasks like object detection have been upgraded by replac…
Learning the Superpixel in a Non-iterative and Lifelong Manner
Lei Zhu, Qi She, Bin Zhang +4
Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent c…
Involution: Inverting the Inherence of Convolution for Visual Recognition
Duo Li, Jie Hu, Changhu Wang +5
Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision. In this work, we rethink the inherent principles of standard co…
Image-to-image Translation via Hierarchical Style Disentanglement
Xinyang Li, Shengchuan Zhang, Jie Hu +6
Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation…
Architecture Disentanglement for Deep Neural Networks
Jie Hu, Liujuan Cao, Qixiang Ye +6
Understanding the inner workings of deep neural networks (DNNs) is essential to provide trustworthy artificial intelligence techniques for practical applications. Existing studies…
Information Competing Process for Learning Diversified Representations
Jie Hu, Rongrong Ji, ShengChuan Zhang +4
Learning representations with diversified information remains as an open problem. Towards learning diversified representations, a new approach, termed Information Competing Process…
Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning
Xinyang Li, Jie Hu, Shengchuan Zhang +4
Unpaired Image-to-Image Translation (UIT) focuses on translating images among different domains by using unpaired data, which has received increasing research focus due to its prac…
Towards Visual Feature Translation
Jie Hu, Rongrong Ji, Hong Liu +3
Most existing visual search systems are deployed based upon fixed kinds of visual features, which prohibits the feature reusing across different systems or when upgrading systems w…
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
Jie Hu, Li Shen, Samuel Albanie +2
While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from captu…
Squeeze-and-Excitation Networks
Jie Hu, Li Shen, Samuel Albanie +2
The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and…