1 code implementation • CVPR 2023 • Ziqin Wang, Bowen Cheng, Lichen Zhao, Dong Xu, Yang Tang, Lu Sheng
Since 2D images provide rich semantics and scene graphs are in nature coped with languages, in this study, we propose Visual-Linguistic Semantics Assisted Training (VL-SAT) scheme that can significantly empower 3DSSG prediction models with discrimination about long-tailed and ambiguous semantic relations.
Ranked #1 on 3d scene graph generation on 3DSSG (using extra training data)
no code implementations • ICCV 2023 • Yan Fang, Feng Zhu, Bowen Cheng, Luoqi Liu, Yao Zhao, Yunchao Wei
This work shows that locating the patch-wise noisy region is a better way to deal with noise.
5 code implementations • 20 Dec 2021 • Bowen Cheng, Anwesa Choudhuri, Ishan Misra, Alexander Kirillov, Rohit Girdhar, Alexander G. Schwing
We find Mask2Former also achieves state-of-the-art performance on video instance segmentation without modifying the architecture, the loss or even the training pipeline.
Ranked #14 on Video Instance Segmentation on YouTube-VIS validation
6 code implementations • CVPR 2022 • Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar
While only the semantics of each task differ, current research focuses on designing specialized architectures for each task.
Ranked #3 on Semantic Segmentation on Mapillary val
3 code implementations • NeurIPS 2021 • Bowen Cheng, Alexander G. Schwing, Alexander Kirillov
Overall, the proposed mask classification-based method simplifies the landscape of effective approaches to semantic and panoptic segmentation tasks and shows excellent empirical results.
Ranked #4 on Semantic Segmentation on Mapillary val
1 code implementation • 29 Apr 2021 • Jiachen Li, Bowen Cheng, Rogerio Feris, JinJun Xiong, Thomas S. Huang, Wen-mei Hwu, Humphrey Shi
Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment methods based on the Intersection-over-Union~(IoU) metric.
2 code implementations • CVPR 2022 • Bowen Cheng, Omkar Parkhi, Alexander Kirillov
Our experiments show that the new module is more suitable for the point-based supervision.
1 code implementation • CVPR 2021 • Bowen Cheng, Lu Sheng, Shaoshuai Shi, Ming Yang, Dong Xu
Inspired by the back-tracing strategy in the conventional Hough voting methods, in this work, we introduce a new 3D object detection method, named as Back-tracing Representative Points Network (BRNet), which generatively back-traces the representative points from the vote centers and also revisits complementary seed points around these generated points, so as to better capture the fine local structural features surrounding the potential objects from the raw point clouds.
Ranked #17 on 3D Object Detection on ScanNetV2
2 code implementations • CVPR 2021 • Bowen Cheng, Ross Girshick, Piotr Dollár, Alexander C. Berg, Alexander Kirillov
We perform an extensive analysis across different error types and object sizes and show that Boundary IoU is significantly more sensitive than the standard Mask IoU measure to boundary errors for large objects and does not over-penalize errors on smaller objects.
no code implementations • 30 Nov 2020 • Hsin-Pai Cheng, Feng Liang, Meng Li, Bowen Cheng, Feng Yan, Hai Li, Vikas Chandra, Yiran Chen
We use ScaleNAS to create high-resolution models for two different tasks, ScaleNet-P for human pose estimation and ScaleNet-S for semantic segmentation.
Ranked #5 on Multi-Person Pose Estimation on COCO test-dev
1 code implementation • ECCV 2020 • Liang-Chieh Chen, Raphael Gontijo Lopes, Bowen Cheng, Maxwell D. Collins, Ekin D. Cubuk, Barret Zoph, Hartwig Adam, Jonathon Shlens
We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences and extra images to surpass state-of-the-art performance on core computer vision tasks.
9 code implementations • CVPR 2020 • Bowen Cheng, Maxwell D. Collins, Yukun Zhu, Ting Liu, Thomas S. Huang, Hartwig Adam, Liang-Chieh Chen
In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve comparable performance of two-stage methods while yielding fast inference speed.
Ranked #6 on Panoptic Segmentation on Cityscapes test (using extra training data)
2 code implementations • 10 Oct 2019 • Bowen Cheng, Maxwell D. Collins, Yukun Zhu, Ting Liu, Thomas S. Huang, Hartwig Adam, Liang-Chieh Chen
The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e. g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression.
2 code implementations • 20 Sep 2019 • Xiaofan Zhang, Haoming Lu, Cong Hao, Jiachen Li, Bowen Cheng, Yuhong Li, Kyle Rupnow, JinJun Xiong, Thomas Huang, Honghui Shi, Wen-mei Hwu, Deming Chen
Object detection and tracking are challenging tasks for resource-constrained embedded systems.
20 code implementations • CVPR 2020 • Bowen Cheng, Bin Xiao, Jingdong Wang, Honghui Shi, Thomas S. Huang, Lei Zhang
HigherHRNet even surpasses all top-down methods on CrowdPose test (67. 6% AP), suggesting its robustness in crowded scene.
Ranked #2 on Pose Estimation on UAV-Human
no code implementations • ICCV 2019 • Bowen Cheng, Liang-Chieh Chen, Yunchao Wei, Yukun Zhu, Zilong Huang, JinJun Xiong, Thomas Huang, Wen-mei Hwu, Honghui Shi
The multi-scale context module refers to the operations to aggregate feature responses from a large spatial extent, while the single-stage encoder-decoder structure encodes the high-level semantic information in the encoder path and recovers the boundary information in the decoder path.
no code implementations • 7 May 2019 • Bowen Cheng, Rong Xiao, Jian-Feng Wang, Thomas Huang, Lei Zhang
We present a novel high frequency residual learning framework, which leads to a highly efficient multi-scale network (MSNet) architecture for mobile and embedded vision problems.
no code implementations • 23 Nov 2018 • Bowen Cheng, Yunchao Wei, Jiahui Yu, Shiyu Chang, JinJun Xiong, Wen-mei Hwu, Thomas S. Huang, Humphrey Shi
While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in an easy-to-hard manner and on the selected examples progressively.
3 code implementations • 5 Oct 2018 • Bowen Cheng, Yunchao Wei, Rogerio Feris, JinJun Xiong, Wen-mei Hwu, Thomas Huang, Humphrey Shi
In particular, DCR places a separate classification network in parallel with the localization network (base detector).
no code implementations • 17 Sep 2018 • Bowen Cheng, Rong Xiao, Yandong Guo, Yuxiao Hu, Jian-Feng Wang, Lei Zhang
We study in this paper how to initialize the parameters of multinomial logistic regression (a fully connected layer followed with softmax and cross entropy loss), which is widely used in deep neural network (DNN) models for classification problems.
no code implementations • ECCV 2018 • Yunchao Wei, Zhiqiang Shen, Bowen Cheng, Honghui Shi, JinJun Xiong, Jiashi Feng, Thomas Huang
This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C).
7 code implementations • ECCV 2018 • Bowen Cheng, Yunchao Wei, Honghui Shi, Rogerio Feris, JinJun Xiong, Thomas Huang
Recent region-based object detectors are usually built with separate classification and localization branches on top of shared feature extraction networks.
no code implementations • 20 Dec 2017 • Ding Liu, Bowen Cheng, Zhangyang Wang, Haichao Zhang, Thomas S. Huang
Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image acquisition, transmission, or storage.
no code implementations • 10 Sep 2017 • Bowen Cheng, Zhangyang Wang, Zhaobin Zhang, Zhu Li, Ding Liu, Jianchao Yang, Shuai Huang, Thomas S. Huang
Emotion recognition from facial expressions is tremendously useful, especially when coupled with smart devices and wireless multimedia applications.