COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation

2022-10-04 · Rong Li, Anh-Quan Cao, Raoul de Charette

Annotation of large-scale 3D data is notoriously cumbersome and costly. As an alternative, weakly-supervised learning alleviates such a need by reducing the annotation by several order of magnitudes. We propose COARSE3D, a novel architecture-agnostic contrastive learning strategy for 3D segmentation. Since contrastive learning requires rich and diverse examples as keys and anchors, we leverage a prototype memory bank capturing class-wise global dataset information efficiently into a small number of prototypes acting as keys. An entropy-driven sampling technique then allows us to select good pixels from predictions as anchors. Experiments on three projection-based backbones show we outperform baselines on three challenging real-world outdoor datasets, working with as low as 0.001% annotations.

📄 PDF Abstract BibTeX arXiv:2210.01784

Code (1)

cv-rits/coarse3d 공식 구현 pytorch

Tasks

3D Semantic Segmentation Contrastive Learning LIDAR Semantic Segmentation Point Cloud Segmentation Semi-Supervised Semantic SegmentationWeakly Supervised 3D Point Cloud SegmentationWeakly-supervised LearningWeakly supervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning

2023-01-01 · CVPR 2023 1 · Anurag Das, Yongqin Xian, Dengxin Dai, Bernt Schiele

There has been a lot of effort in improving the performance of unsupervised domain adaptation for semantic segmentation task, however there is still a huge gap in performance when compared with supervised learning. I…

Contrastive Learning Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation

Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph

2019-05-10 · Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang 외

A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning ad…

Few-Shot Learning General Classification Meta-Learning

Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment

2025-11-13 · Wenti Yin, Huaxin Zhang, Xiang Wang, Yuqing Lu 외 arxiv

Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight an…

Weakly-supervised Video Anomaly Detection Multiple Instance Learning Contrastive Learning

Negative Prototypes Guided Contrastive Learning for WSOD

2024-06-04 · Yu Zhang, Chuang Zhu, Guoqing Yang, Siqi Chen

Weakly Supervised Object Detection (WSOD) with only image-level annotation has recently attracted wide attention. Many existing methods ignore the inter-image relationship of instances which share similar characteristics…

Contrastive Learning object-detection Object Detection Pseudo Label+1

Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP

2024-12-27 · Zhongxing Xu, Feilong Tang, Zhe Chen, Yingxue Su 외

The application of Contrastive Language-Image Pre-training (CLIP) in Weakly Supervised Semantic Segmentation (WSSS) research powerful cross-modal semantic understanding capabilities. Existing methods attempt to optimize …

Semantic Segmentation Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation