English
Related papers

Related papers: Few to Big: Prototype Expansion Network via Diffus…

200 papers

Recent approaches for few-shot 3D point cloud semantic segmentation typically require a two-stage learning process, i.e., a pre-training stage followed by a few-shot training stage. While effective, these methods face overreliance on…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Jiahui Wang , Haiyue Zhu , Haoren Guo , Abdullah Al Mamun , Cheng Xiang , Tong Heng Lee

Few-shot 3D point cloud semantic segmentation (FS-3DSeg) aims to segment novel classes with only a few labeled samples. However, existing metric-based prototype learning methods generate prototypes solely from the support set, without…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 YiLin Zhou , Lili Wei , Zheming Xu , Ziyi Chen , Congyan Lang

While originally designed for image generation, diffusion models have recently shown to provide excellent pretrained feature representations for semantic segmentation. Intrigued by this result, we set out to explore how well…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Rui Gong , Martin Danelljan , Han Sun , Julio Delgado Mangas , Luc Van Gool

Few-shot Semantic Segmentation (FSS) aims to adapt a pretrained model to new classes with as few as a single labelled training sample per class. Despite the prototype based approaches have achieved substantial success, existing models are…

Computer Vision and Pattern Recognition · Computer Science 2024-06-27 Song Tang , Shaxu Yan , Xiaozhi Qi , Jianxin Gao , Mao Ye , Jianwei Zhang , Xiatian Zhu

Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, a new model called SnapshotNet is proposed as a self-supervised feature learning approach, which directly works…

Computer Vision and Pattern Recognition · Computer Science 2022-01-14 Xingye Li , Ling Zhang , Zhigang Zhu

Few-shot learning aims to recognize novel classes with few examples. Pre-training based methods effectively tackle the problem by pre-training a feature extractor and then fine-tuning it through the nearest centroid based meta-learning.…

Computer Vision and Pattern Recognition · Computer Science 2021-08-21 Baoquan Zhang , Xutao Li , Yunming Ye , Shanshan Feng

Diffusion models have demonstrated excellent performance in image generation. Although various few-shot semantic segmentation (FSS) models with different network structures have been proposed, performance improvement has reached a…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Weimin Tan , Siyuan Chen , Bo Yan

We tackle a novel few-shot learning challenge, which we call few-shot semantic edge detection, aiming to localize crisp boundaries of novel categories using only a few labeled samples. We also present a Class-Agnostic Few-shot Edge…

Computer Vision and Pattern Recognition · Computer Science 2020-03-19 Young-Hyun Park , Jun Seo , Jaekyun Moon

Semantic segmentation models have two fundamental weaknesses: i) they require large training sets with costly pixel-level annotations, and ii) they have a static output space, constrained to the classes of the training set. Toward…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Fabio Cermelli , Massimiliano Mancini , Yongqin Xian , Zeynep Akata , Barbara Caputo

Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets. However, data labeling for pixel-wise segmentation is tedious and costly. Moreover, a trained model can only…

Computer Vision and Pattern Recognition · Computer Science 2019-03-07 Chi Zhang , Guosheng Lin , Fayao Liu , Rui Yao , Chunhua Shen

The deep CNNs in image semantic segmentation typically require a large number of densely-annotated images for training and have difficulties in generalizing to unseen object categories. Therefore, few-shot segmentation has been developed to…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Henghui Ding , Hui Zhang , Xudong Jiang

3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding. Due to the complex structure, point sets are distributed off balance and diversely, which appears as both category imbalance and…

Computer Vision and Pattern Recognition · Computer Science 2020-01-07 Tong He , Dong Gong , Zhi Tian , Chunhua Shen

Point cloud segmentation is one of the most important tasks in computer vision with widespread scientific, industrial, and commercial applications. The research thereof has resulted in many breakthroughs in 3D object and scene…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Dening Lu , Jun Zhou , Kyle Yilin Gao , Dilong Li , Jing Du , Linlin Xu , Jonathan Li

Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images. The current correlation-based methods construct pair-wise feature correlations to…

Computer Vision and Pattern Recognition · Computer Science 2023-01-20 Huafeng Liu , Pai Peng , Tao Chen , Qiong Wang , Yazhou Yao , Xian-Sheng Hua

Few-shot segmentation is a task to segment objects or regions of novel classes within an image given only a few annotated examples. In the generalized setting, the task extends to segment both the base and the novel classes. The main…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Steve Andreas Immanuel , Hagai Raja Sinulingga

In the domain of 3D object classification, a fundamental challenge lies in addressing the scarcity of labeled data, which limits the applicability of traditional data-intensive learning paradigms. This challenge is particularly pronounced…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Haosheng Zhang , Hao Huang

While massively scaling both data and models have become central in NLP and 2D vision, their benefits for 3D point cloud understanding remain limited. We study the initial step of scaling 3D point cloud understanding under a realistic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Xuweiyi Chen , Wentao Zhou , Aruni RoyChowdhury , Zezhou Cheng

Most existing 3D point cloud object detection approaches heavily rely on large amounts of labeled training data. However, the labeling process is costly and time-consuming. This paper considers few-shot 3D point cloud object detection,…

Computer Vision and Pattern Recognition · Computer Science 2022-12-22 Shizhen Zhao , Xiaojuan Qi

Few-shot learning aims to recognize novel concepts by leveraging prior knowledge learned from a few samples. However, for visually intensive tasks such as few-shot semantic segmentation, pixel-level annotations are time-consuming and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Jiaqi Ma , Guo-Sen Xie , Fang Zhao , Zechao Li

Few-shot learning deals with problems such as image classification using very few training examples. Recent vision foundation models show excellent few-shot transfer abilities, but are large and slow at inference. Using knowledge…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Erik Landolsi , Fredrik Kahl