1 code implementation • 4 Nov 2024 • Teng Bin, Jianming Yao, Tin Lun Lam, Tianwei Zhang
We present a novel algorithm for real-time planar semantic mapping tailored for humanoid robots navigating complex terrains such as staircases.
1 code implementation • 28 Mar 2023 • Mingjian Liang, Junjie Hu, Chenyu Bao, Hua Feng, Fuqin Deng, Tin Lun Lam
Specifically, we consider the following cases: i) both RGB data and thermal data, ii) only one of the types of data, and iii) none of them generate discriminative features.
Ranked #2 on
Thermal Image Segmentation
on Noisy RS RGB-T Dataset
1 code implementation • 9 Mar 2023 • Junjie Hu, Chenyou Fan, Liguang Zhou, Qing Gao, Honghai Liu, Tin Lun Lam
With the rapid advancements in autonomous driving and robot navigation, there is a growing demand for lifelong learning models capable of estimating metric (absolute) depth.
no code implementations • 31 Dec 2022 • Liguang Zhou, Yuhongze Zhou, Xiaonan Qi, Junjie Hu, Tin Lun Lam, Yangsheng Xu
Then, to build multi-scale hierarchical information of input features, we utilize an attention fusion mechanism to aggregate features from multiple layers of the backbone network.
no code implementations • 31 Dec 2022 • Liguang Zhou, Junjie Hu, Yuhongze Zhou, Tin Lun Lam, Yangsheng Xu
Unbiased scene graph generation (USGG) is a challenging task that requires predicting diverse and heavily imbalanced predicates between objects in an image.
1 code implementation • 29 Aug 2022 • Junjie Hu, Chenyou Fan, Mete Ozay, Hua Feng, Yuan Gao, Tin Lun Lam
In this paper, we introduce the ground-to-aerial perception knowledge transfer and propose a progressive semi-supervised learning framework that enables drone perception using only labeled data of ground viewpoint and unlabeled data of flying viewpoints.
no code implementations • 26 Aug 2022 • Junjie Hu, Chenyou Fan, Mete Ozay, Hualie Jiang, Tin Lun Lam
We study data-free knowledge distillation (KD) for monocular depth estimation (MDE), which learns a lightweight model for real-world depth perception tasks by compressing it from a trained teacher model while lacking training data in the target domain.
no code implementations • 15 Aug 2022 • Liguang Zhou, Yuhongze Zhou, Tin Lun Lam, Yangsheng Xu
Specifically, we propose to integrate the mixture of experts with a divide and ensemble strategy to remedy the severely long-tailed distribution of predicate classes, which is applicable to the majority of unbiased scene graph generators.
no code implementations • 5 Aug 2022 • Jingtao Tang, Yuan Gao, Tin Lun Lam
In this paper, we focus on the multi-robot coverage path planning (mCPP) problem in large-scale planar areas with random dynamic interferers in the environment, where the robots have limited resources.
no code implementations • 11 May 2022 • Junjie Hu, Chenyu Bao, Mete Ozay, Chenyou Fan, Qing Gao, Honghai Liu, Tin Lun Lam
Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map captured from a depth sensor, e. g., LiDARs.
1 code implementation • 18 Oct 2021 • Fuqin Deng, Hua Feng, Mingjian Liang, Hongmin Wang, Yong Yang, Yuan Gao, Junfeng Chen, Junjie Hu, Xiyue Guo, Tin Lun Lam
To better extract detail spatial information, we propose a two-stage Feature-Enhanced Attention Network (FEANet) for the RGB-T semantic segmentation task.
Ranked #13 on
Semantic Segmentation
on FMB Dataset
1 code implementation • 18 Oct 2021 • Fuqin Deng, Hua Feng, Mingjian Liang, Qi Feng, Ningbo Yi, Yong Yang, Yuan Gao, Junfeng Chen, Tin Lun Lam
The occupancy grid map is a critical component of autonomous positioning and navigation in the mobile robotic system, as many other systems' performance depends heavily on it.
no code implementations • 10 Sep 2021 • Yuhongze Zhou, Liguang Zhou, Tin Lun Lam, Yangsheng Xu
Our MGRConv can be regarded as soft partial convolution and find a trade-off among partial convolution, learnable attention maps, and gated convolution.
no code implementations • 8 Sep 2021 • Chongyang Wang, Yuan Gao, Chenyou Fan, Junjie Hu, Tin Lun Lam, Nicholas D. Lane, Nadia Bianchi-Berthouze
For such issues, we propose a novel Learning to Agreement (Learn2Agree) framework to tackle the challenge of learning from multiple annotators without objective ground truth.
no code implementations • 3 Aug 2021 • Tianwei Zhang, Huayan Zhang, Xiaofei Li, Junfeng Chen, Tin Lun Lam, Sethu Vijayakumar
Dynamic objects in the environment, such as people and other agents, lead to challenges for existing simultaneous localization and mapping (SLAM) approaches.
no code implementations • 2 Aug 2021 • Huayan Zhang, Tianwei Zhang, Tin Lun Lam, Sethu Vijayakumar
Dynamic environments that include unstructured moving objects pose a hard problem for Simultaneous Localization and Mapping (SLAM) performance.
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.
1 code implementation • 1 Aug 2021 • Bo Miao, Liguang Zhou, Ajmal Mian, Tin Lun Lam, Yangsheng Xu
The final results in this work show that OTS successfully extracts object features and learns object relations from the segmentation network.
2 code implementations • 13 May 2021 • Junjie Hu, Chenyou Fan, Hualie Jiang, Xiyue Guo, Yuan Gao, Xiangyong Lu, Tin Lun Lam
However, this KD process can be challenging and insufficient due to the large model capacity gap between the teacher and the student.
no code implementations • 31 Mar 2021 • Yuhongze Zhou, Liguang Zhou, Tin Lun Lam, Yangsheng Xu
This paper presents a semantic-guided automatic natural image matting pipeline with Trimap Generation Network and light-weight non-local attention, which does not need trimap and background as input.
2 code implementations • 30 Nov 2020 • Shuai Zhao, Liguang Zhou, Wenxiao Wang, Deng Cai, Tin Lun Lam, Yangsheng Xu
Each of these small networks has a fraction of the original one's parameters.
Ranked #31 on
Image Classification
on CIFAR-100
(using extra training data)
no code implementations • 19 Oct 2020 • Junjie Hu, Xiyue Guo, Junfeng Chen, Guanqi Liang, Fuqin Deng, Tin Lun Lam
However, most of them suffer from the following problems: 1) the need of pairs of low light and normal light images for training, 2) the poor performance for dark images, 3) the amplification of noise.
Low-Light Image Enhancement
Simultaneous Localization and Mapping
+1
3 code implementations • 19 Oct 2020 • Xiyue Guo, Junjie Hu, Junfeng Chen, Fuqin Deng, Tin Lun Lam
The core problem of visual multi-robot simultaneous localization and mapping (MR-SLAM) is how to efficiently and accurately perform multi-robot global localization (MR-GL).
no code implementations • 26 Apr 2020 • Qi She, Fan Feng, Qi Liu, Rosa H. M. Chan, Xinyue Hao, Chuanlin Lan, Qihan Yang, Vincenzo Lomonaco, German I. Parisi, Heechul Bae, Eoin Brophy, Baoquan Chen, Gabriele Graffieti, Vidit Goel, Hyonyoung Han, Sathursan Kanagarajah, Somesh Kumar, Siew-Kei Lam, Tin Lun Lam, Liang Ma, Davide Maltoni, Lorenzo Pellegrini, Duvindu Piyasena, ShiLiang Pu, Debdoot Sheet, Soonyong Song, Youngsung Son, Zhengwei Wang, Tomas E. Ward, Jianwen Wu, Meiqing Wu, Di Xie, Yangsheng Xu, Lin Yang, Qiaoyong Zhong, Liguang Zhou
This report summarizes IROS 2019-Lifelong Robotic Vision Competition (Lifelong Object Recognition Challenge) with methods and results from the top $8$ finalists (out of over~$150$ teams).