|
ISTR: Mask-Embedding-Based Instance Segmentation Transformer
Jie Hu,
Yao Lu,
Shengchuan Zhang,
Liujuan Cao,
IEEE Transactions on Image Processing (TIP), 2024
This paper proposes a transformer-based instance segmentation framework, which encodes masks into embeddings to regress them.
|
|
Pseudo-label Alignment for Semi-supervised Instance Segmentation
Jie Hu*,
Chen Chen*,
Liujuan Cao
Shengchuan Zhang,
Annan Shu,
Guannan Jiang,
Rongrong Ji (*Equal Contribution)
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
This paper proposes a novel framework, PAIS, that aligns the pseudo-labels of unannotated images with varying class and mask quality for semi-supervised instance segmentation, achieving state-of-the-art results on COCO and Cityscapes datasets.
|
|
You Only Segment Once: Towards Real-Time Panoptic Segmentation
Jie Hu,
Linyan Huang,
Tianhe Ren,
Shengchuan Zhang,
Rongrong Ji,
Liujuan Cao
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
In this paper, we show the complex task of panoptic segmentation can run over 30 FPS with competitive PQ performance, which is achieved by the proposed YOSO with a feature pyramid aggregator and a separable dynamic decoder.
|
|
DistilPose: Tokenized Pose Regression with Heatmap Distillation
Suhang Ye*,
Yingyi Zhang*,
Jie Hu*,
Liujuan Cao,
Shengchuan Zhang,
Lei Shen,
Jun Wang,
Shouhong Ding,
Rongrong Ji (*Equal Contribution)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
This paper proposes DistilPose that distills heatmap-based human pose estimation models into regression-based ones to speed up the pipeline.
|
|
Architecture Disentanglement for Deep Neural Networks
Jie Hu,
Liujuan Cao,
Qixiang Ye,
Tong Tong,
Shengchuan Zhang,
Ke Li,
Feiyue Huang,
Rongrong Ji,
Ling Shao
IEEE/CVF International Conference on Computer Vision (ICCV), oral, 2021
This paper proposes to disentangle deep neural networks via information bottleneck to understand the inner workings of them.
|
|
Image-to-image Translation via Hierarchical Style Disentanglement
Xinyang Li,
Shengchuan Zhang,
Jie Hu,
Liujuan Cao,
Xiaopeng Hong,
Xudong Mao,
Feiyue Huang,
Yongjian Wu,
Rongrong Ji
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), oral, 2021
This paper presents a novel method for image-to-image translation that uses a hierarchical tree to re-arrange the image attributes and achieve style disentanglement.
|
|
Information Competing Process for Learning Diversified Representations
Jie Hu,
Rongrong Ji,
Shengchuan Zhang,
Xiaoshuai Sun,
Qixiang Ye,
Chia-Wen Lin,
Qi Tian
Neural Information Processing Systems (NeurIPS), 2019
This paper proposes a new approach that separates a representation into two parts with different mutual information constraints.
|
|
Towards Visual Feature Translation
Jie Hu,
Rongrong Ji,
Hong Liu,
Shengchuan Zhang,
Cheng Deng,
Qi Tian
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
This paper proposes to break through the barrier of using features across different visual search systems.
|
|