1 code implementation • 25 Mar 2024 • Lingdong Kong, Xiang Xu, Jun Cen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu
Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models.
1 code implementation • 20 Mar 2024 • Kewei Wang, Yizheng Wu, Jun Cen, Zhiyu Pan, Xingyi Li, Zhe Wang, Zhiguo Cao, Guosheng Lin
To this end, we explore the feasibility of self-supervised motion prediction with only unlabeled LiDAR point clouds.
1 code implementation • 13 Mar 2024 • Zhanxin Gao, Jun Cen, Xiaobin Chang
Specifically, all existing classifiers are exposed to prompt training, resulting in classifier consistency learning.
no code implementations • 16 Feb 2024 • Jun Cen, Chenfei Wu, Xiao Liu, Shengming Yin, Yixuan Pei, Jinglong Yang, Qifeng Chen, Nan Duan, JianGuo Zhang
Large Language Models (LLMs) and Large Multi-modality Models (LMMs) have demonstrated remarkable decision masking capabilities on a variety of tasks.
no code implementations • 20 Nov 2023 • Jiuqing Dong, Yongbin Gao, Heng Zhou, Jun Cen, Yifan Yao, Sook Yoon, Park Dong Sun
Out-of-distribution (OOD) detection is critical for ensuring the reliability of open-world intelligent systems.
1 code implementation • 9 Jul 2023 • Jun Cen, Shiwei Zhang, Yixuan Pei, Kun Li, Hang Zheng, Maochun Luo, Yingya Zhang, Qifeng Chen
In this way, RGB images are not required during inference anymore since the 2D knowledge branch provides 2D information according to the 3D LIDAR input.
2 code implementations • NeurIPS 2023 • Youquan Liu, Lingdong Kong, Jun Cen, Runnan Chen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu
Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception.
1 code implementation • 23 May 2023 • Jun Cen, Yizheng Wu, Kewei Wang, Xingyi Li, Jingkang Yang, Yixuan Pei, Lingdong Kong, Ziwei Liu, Qifeng Chen
The Segment Anything Model (SAM) has demonstrated its effectiveness in segmenting any part of 2D RGB images.
Open Vocabulary Semantic Segmentation Panoptic Segmentation +1
1 code implementation • CVPR 2023 • Jun Cen, Shiwei Zhang, Xiang Wang, Yixuan Pei, Zhiwu Qing, Yingya Zhang, Qifeng Chen
In this paper, we begin with analyzing the feature representation behavior in the open-set action recognition (OSAR) problem based on the information bottleneck (IB) theory, and propose to enlarge the instance-specific (IS) and class-specific (CS) information contained in the feature for better performance.
1 code implementation • 6 Mar 2023 • Xiang Wang, Shiwei Zhang, Jun Cen, Changxin Gao, Yingya Zhang, Deli Zhao, Nong Sang
Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under-explored on the challenging few-shot action recognition (FSAR) task.
1 code implementation • 8 Feb 2023 • Jun Cen, Di Luan, Shiwei Zhang, Yixuan Pei, Yingya Zhang, Deli Zhao, Shaojie Shen, Qifeng Chen
Recently, Unified Open-set Recognition (UOSR) has been proposed to reject not only unknown samples but also known but wrongly classified samples, which tends to be more practical in real-world applications.
no code implementations • 2 Nov 2022 • Yixuan Pei, Zhiwu Qing, Jun Cen, Xiang Wang, Shiwei Zhang, Yaxiong Wang, Mingqian Tang, Nong Sang, Xueming Qian
The former is to reduce the memory cost by preserving only one condensed frame instead of the whole video, while the latter aims to compensate the lost spatio-temporal details in the Frame Condensing stage.
1 code implementation • 5 Jul 2022 • Yuhan Lin, Han Sun, Ningzhong Liu, Yetong Bian, Jun Cen, Huiyu Zhou
Specifically, the position enhancement stage consists of a semantic attention module and a contextual attention module to accurately describe the approximate location of salient objects.
1 code implementation • 4 Jul 2022 • Jun Cen, Peng Yun, Shiwei Zhang, Junhao Cai, Di Luan, Michael Yu Wang, Ming Liu, Mingqian Tang
Current methods for LIDAR semantic segmentation are not robust enough for real-world applications, e. g., autonomous driving, since it is closed-set and static.
1 code implementation • 18 May 2022 • Yuhan Lin, Han Sun, Ningzhong Liu, Yetong Bian, Jun Cen, Huiyu Zhou
Meanwhile, in order to accurately detect complete salient objects in complex backgrounds, we design an attention-based pyramid feature aggregation mechanism for gradually aggregating and refining the salient regions from the multi-scale context extraction module.
no code implementations • 2 Dec 2021 • Jun Cen, Peng Yun, Junhao Cai, Michael Yu Wang, Ming Liu
The first step is solved by the finding that unknown objects are often classified as known objects with low confidence, and we show that the Euclidean distance sum based on metric learning is a better confidence score than the naive softmax probability to differentiate unknown objects from known objects.
1 code implementation • ICCV 2021 • Jun Cen, Peng Yun, Junhao Cai, Michael Yu Wang, Ming Liu
Incrementally learning these OOD objects with few annotations is an ideal way to enlarge the knowledge base of the deep learning models.
1 code implementation • 8 Aug 2021 • Han Sun, Jun Cen, Ningzhong Liu, Dong Liang, Huiyu Zhou
The semantic representation of deep features is essential for image context understanding, and effective fusion of features with different semantic representations can significantly improve the model's performance on salient object detection.
1 code implementation • 1 Aug 2021 • Liguang Zhou, Jun Cen, Xingchao Wang, Zhenglong Sun, Tin Lun Lam, Yangsheng Xu
First, we utilize an improved object model (IOM) as a baseline that enriches the object knowledge by introducing a scene parsing algorithm pretrained on the ADE20K dataset with rich object categories related to the indoor scene.