Liang-Chieh (Jay) Chen- Home Page
 |
Liang-Chieh Chen Email: lcchen at cs dot ucla dot edu |
About me
Since February 2016, I have been working at Google, Los Angeles.
I finished my Ph.D. in Computer Science at UCLA under the supervision of Alan L. Yuille.
My research interests include Computer Vision, Graphical Models, and Machine Learning.
News
02/24/2021: Check out our STEP, Segmenting and Tracking Every Pixel, which tackles Video Panoptic Segmentation from the pixel-centric perspective, accompanied by two new datasets (KITTI-STEP and MOTChallenge-STEP) and a new metric (Segmentation and Tracking Quality, STQ).
12/10/2020: Check out our ViP-DeepLab (video demo), learning Visual Perception with Depth-aware Video Panoptic Segmentation. ViP-DeepLab achieves state-of-the-art results on Cityscapes-VPS, KITTI monocular depth estimation, and KITTI MOTS pedestrian.
12/02/2020: Check out our MaX-DeepLab, extending Axial-DeepLab with a Mask Xformer. MaX-DeepLab directly predicts class-labeled masks for panoptic segmentation and sets new state-of-the-art 51.3% PQ on COCO test-dev set.
11/24/2020: Check out our SWideRNets, which significantly advance state-of-the-art performance on panoptic segmentation datasets in both the fast model regime and strong model regime.
09/25/2020: Panoptic-DeepLab have been supported by Detectron2, thanks to Bowen Cheng. Note that this is NOT our official open-source. Please check the original paper for speed or accuracy comparison.
08/27/2020: Google AI blog about Axial-DeepLab.
08/08/2020: A PyTorch re-implementation of Axial-DeepLab by Huaijin Pi and Huiyu Wang is open-source! Note that this is NOT our original TensorFlow implementation. Also, check out the video about Axial-DeepLab.
07/26/2020: DeepLabv3 and DeepLabv3+ have been reproduced in Detectron2, thanks to Bowen Cheng.
07/21/2020: Google AI blog about Panoptic-DeepLab.
07/02/2020: Three papers accepted to ECCV 2020.
06/11/2020: A PyTorch re-implementation of Panoptic-DeepLab by Bowen Cheng is open-source! Note that this is NOT our original TensorFlow implementation. Please check the original paper for comparison.
06/03/2020: Check out our DetectoRS, which sets new state-of-the-art results at COCO: 54.7% box AP, 47.1% mask AP, and 49.6% PQ. A PyTorch implementation of DetectoRS by Siyuan Qiao is open-source!
05/21/2020: Check out our Naive-Student which adopts iterative semi-supervised leanring with Panoptic-DeepLab, setting new state-of-the-art results at Cityscapes all three tasks: 67.8% PQ, 42.6% AP, and 85.2% mIOU.
03/17/2020: Check out our Axial-DeepLab, a Stand-Alone Axial-Attention model for dense prediction tasks.
03/11/2020: Panoptic-DeepLab is accepted to CVPR 2020.
Activities
Area Chair for ICCV 2019, CVPR 2020, ECCV 2020.
Reviewer for CVPR, ECCV, ICCV, NeurIPS.
Papers
 |
STEP: Segmenting and Tracking Every Pixel |
 |
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation |
 |
MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers |
 |
Scaling Wide Residual Networks for Panoptic Segmentation |
 |
View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose |
 |
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution |
 |
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation |
 |
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation (spotlight) |
 |
View-Invariant Probabilistic Embedding for Human Pose (spotlight) |
 |
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation |
 |
Panoptic-DeepLab |
 |
SegSort: Segmentation by Discriminative Sorting of Segments |
 |
SPGNet: Semantic Prediction Guidance for Scene Parsing |
 |
Searching for MobileNetV3 (oral) |
 |
FEELVOS: Fast End-to-End Embedding Learning for Video Object
Segmentation |
 |
DeeperLab: Single-Shot Image Parser |
 |
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation (oral) |
 |
The Devil is in the Decoder: Classification, Regression and GANs |
 |
Searching for Efficient Multi-Scale Architectures for Dense Image
Prediction |
 |
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model |
 |
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation |
 |
MobileNetV2: Inverted Residuals and Linear Bottlenecks |
 |
MaskLab: Instance Segmentation by Refining Object Detection with Semantic
and Direction Features |
 |
The Devil is in the Decoder |
 |
Rethinking Atrous Convolution for Semantic Image Segmentation |
 |
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs |
 |
Zoom Better to See Clearer: Human Part Segmentation with Auto Zoom Net |
 |
Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform |
 |
Attention to Scale: Scale-aware Semantic Image Segmentation |
 |
ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering |
 |
Weakly- and Semi-Supervised Learning of a Deep Convolutional Network for
Semantic Image Segmentation |
 |
Learning Deep Structured Models (oral) |
 |
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs |
 |
Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision |
 |
Modeling Image Patches with a Generic Dictionary of Mini-Epitomes |
 |
Learning a Dictionary of Shape Epitomes with Applications to Image Labeling |
US Patents
Neural Architecture Search for Dense Image Prediction Tasks, 2018
Liang-Chieh Chen, Maxwell D. Collins, Yukun Zhu, George Papandreou, Barret Zoph, Florian Schroff, Hartwig Adam, and Jonathon Shlens.
Instance Segmentation, 2018
Liang-Chieh Chen, Alexander Hermans, George Papandreou, Florian Schroff, Peng Wang, and Hartwig Adam.
Highly Efficient Convolutional Neural Networks, 2018
Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen.
Systems and Methods for Data Page Management of NAND Flash Memory Arrangements, November 2008
Liang-Chieh Chen and Xueshi Yang
Multi-Mode Encoding for Data Compression, February 2009
Liang-Chieh Chen and Xueshi Yang