English
Related papers

Related papers: Continual Learning for LiDAR Semantic Segmentation…

200 papers

Advances in medical imaging and deep learning have propelled progress in whole slide image (WSI) analysis, with multiple instance learning (MIL) showing promise for efficient and accurate diagnostics. However, conventional MIL models often…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Xianrui Li , Yufei Cui , Jun Li , Antoni B. Chan

Panoptic segmentation aims to address semantic and instance segmentation simultaneously in a unified framework. However, an efficient solution of panoptic segmentation in applications like autonomous driving is still an open research…

Computer Vision and Pattern Recognition · Computer Science 2021-09-01 Enxu Li , Ryan Razani , Yixuan Xu , Liu Bingbing

In the past, continual learning (CL) was mostly concerned with the problem of catastrophic forgetting in neural networks, that arises when incrementally learning a sequence of tasks. Current CL methods function within the confines of…

Machine Learning · Computer Science 2025-07-29 Shishir Muralidhara , Didier Stricker , René Schuster

Place recognition is an essential and challenging task in loop closing and global localization for robotics and autonomous driving applications. Benefiting from the recent advances in deep learning techniques, the performance of LiDAR place…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Jiafeng Cui , Xieyuanli Chen

To train a well performing neural network for semantic segmentation, it is crucial to have a large dataset with available ground truth for the network to generalize on unseen data. In this paper we present novel point cloud augmentation…

Computer Vision and Pattern Recognition · Computer Science 2022-12-20 Frederik Hasecke , Martin Alsfasser , Anton Kummert

Continual Learning (CL) methods usually learn from all available data. However, this is not the case in human cognition which efficiently focuses on key experiences while disregarding the redundant information. Similarly, not all data…

Machine Learning · Computer Science 2024-10-24 Elif Ceren Gok Yildirim , Murat Onur Yildirim , Joaquin Vanschoren

We tackle the novel class discovery in point cloud segmentation, which discovers novel classes based on the semantic knowledge of seen classes. Existing work proposes an online point-wise clustering method with a simplified equal class-size…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Ruijie Xu , Chuyu Zhang , Hui Ren , Xuming He

With the increasing reliance of self-driving and similar robotic systems on robust 3D vision, the processing of LiDAR scans with deep convolutional neural networks has become a trend in academia and industry alike. Prior attempts on the…

Computer Vision and Pattern Recognition · Computer Science 2023-11-20 Ran Cheng , Christopher Agia , Yuan Ren , Xinhai Li , Liu Bingbing

Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 Chao Wu , Xiaobin Chang , Ruixuan Wang

Diffusion models have achieved remarkable success in generating high-quality images thanks to their novel training procedures applied to unprecedented amounts of data. However, training a diffusion model from scratch is computationally…

Machine Learning · Computer Science 2023-03-28 Michał Zając , Kamil Deja , Anna Kuzina , Jakub M. Tomczak , Tomasz Trzciński , Florian Shkurti , Piotr Miłoś

A main bottleneck of learning-based robotic scene understanding methods is the heavy reliance on extensive annotated training data, which often limits their generalization ability. In LiDAR panoptic segmentation, this challenge becomes even…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Ahmet Selim Çanakçı , Niclas Vödisch , Kürsat Petek , Wolfram Burgard , Abhinav Valada

Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Da-Wei Zhou , Qi-Wei Wang , Zhi-Hong Qi , Han-Jia Ye , De-Chuan Zhan , Ziwei Liu

Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks without incurring forgetting. CL settings proposed in literature assume that every incoming example is paired with ground-truth annotations. However, this…

Machine Learning · Statistics 2022-08-30 Matteo Boschini , Pietro Buzzega , Lorenzo Bonicelli , Angelo Porrello , Simone Calderara

Semantic segmentation is the pixel-wise labelling of an image. Since the problem is defined at the pixel level, determining image class labels only is not acceptable, but localising them at the original image pixel resolution is necessary.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Irem Ulku , Erdem Akagunduz

Modern lidar systems can produce not only dense point clouds but also 360 degrees low-resolution images. This advancement facilitates the application of deep learning (DL) techniques initially developed for conventional RGB cameras and…

Robotics · Computer Science 2025-04-18 Sier Ha , Honghao Du , Xianjia Yu , Jian Song , Tomi Westerlund

Critical research about camera-and-LiDAR-based semantic object segmentation for autonomous driving significantly benefited from the recent development of deep learning. Specifically, the vision transformer is the novel ground-breaker that…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Junyi Gu , Mauro Bellone , Tomáš Pivoňka , Raivo Sell

Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner. Due to the limited number of examples for training, the techniques…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Ali Cheraghian , Shafin Rahman , Pengfei Fang , Soumava Kumar Roy , Lars Petersson , Mehrtash Harandi

The goal of continual learning (CL) is to efficiently update a machine learning model with new data without forgetting previously-learned knowledge. Most widely-used CL methods rely on a rehearsal memory of data points to be reused while…

Machine Learning · Computer Science 2022-03-29 Lukas Balles , Giovanni Zappella , Cédric Archambeau

As camera and LiDAR sensors capture complementary information used in autonomous driving, great efforts have been made to develop semantic segmentation algorithms through multi-modality data fusion. However, fusion-based approaches require…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Xu Yan , Jiantao Gao , Chaoda Zheng , Chao Zheng , Ruimao Zhang , Shenghui Cui , Zhen Li

Deep learning (DL) models for segmenting various anatomical structures have achieved great success via a static DL model that is trained in a single source domain. Yet, the static DL model is likely to perform poorly in a continually…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Xiaofeng Liu , Helen A. Shih , Fangxu Xing , Emiliano Santarnecchi , Georges El Fakhri , Jonghye Woo