English
Related papers

Related papers: From Points to Clouds: Learning Robust Semantic Di…

200 papers

Modern supervised semantic segmentation methods are usually finetuned based on the supervised or self-supervised models pre-trained on ImageNet. Recent work shows that transferring the knowledge from CLIP to semantic segmentation via prompt…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Chaohui Yu , Qiang Zhou , Zhibin Wang , Fan Wang

Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Haotian Liu , Mu Cai , Yong Jae Lee

Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Ao Li , Zongfang Liu , Xinhua Li , Jinghui Zhang , Pengwei Wang , Hu Wang

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

Computation and Language · Computer Science 2024-10-15 Jian Gu , Aldeida Aleti , Chunyang Chen , Hongyu Zhang

Prompt learning is a powerful technique for transferring Vision-Language Models (VLMs) such as CLIP to downstream tasks. However, the prompt-based methods that are fine-tuned solely with base classes may struggle to generalize to novel…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Mushui Liu , Weijie He , Ziqian Lu , Yunlong Yu

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

3D point clouds acquired by scanning real-world objects or scenes have found a wide range of applications including immersive telepresence, autonomous driving, surveillance, etc. They are often perturbed by noise or suffer from low density,…

Computer Vision and Pattern Recognition · Computer Science 2021-11-04 Haolan Chen , Bi'an Du , Shitong Luo , Wei Hu

Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set, which limits their application in real-world scenarios due to the lack of generalization ability. Large-scale visual-language…

Computer Vision and Pattern Recognition · Computer Science 2023-12-13 Yuanbin Wang , Shaofei Huang , Yulu Gao , Zhen Wang , Rui Wang , Kehua Sheng , Bo Zhang , Si Liu

Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning. Existing approaches mainly focus on exploiting manifold and pseudo-labeling to make use of large unlabeled data…

Computer Vision and Pattern Recognition · Computer Science 2022-05-09 Yongyi Su , Xun Xu , Kui Jia

Large pre-trained vision-language models, such as CLIP, have shown remarkable generalization capabilities across various tasks when appropriate text prompts are provided. However, adapting these models to specific domains, like remote…

Computer Vision and Pattern Recognition · Computer Science 2023-12-13 Qinglong Cao , Zhengqin Xu , Yuntian Chen , Chao Ma , Xiaokang Yang

With the rapid progress of multimodal foundation models and predictive pre-training, an important open question is how to equip 3D point clouds with a pre-training paradigm that is better aligned with next-token and next-embedding learning.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yumeng Yao , Jingzhi Dong , Haowen Gu , Tao Chen , Zonghan Wu , Xiaoshui Huang , Yazhou Yao

Many existing approaches for 3D point cloud semantic segmentation are fully supervised. These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Na Zhao , Tat-Seng Chua , Gim Hee Lee

Raw point clouds data inevitably contains outliers or noise through acquisition from 3D sensors or reconstruction algorithms. In this paper, we present a novel end-to-end network for robust point clouds processing, named PointASNL, which…

Computer Vision and Pattern Recognition · Computer Science 2020-05-06 Xu Yan , Chaoda Zheng , Zhen Li , Sheng Wang , Shuguang Cui

Multi-view multi-label classification (MvMLC) is indispensable for modern web applications aggregating information from diverse sources. However, real-world web-scale settings are rife with missing views and continuously emerging classes,…

Machine Learning · Computer Science 2026-01-27 Jiajun Chen , Yue Wu , Kai Huang , Wen Xi , Yangyang Wu , Xiaoye Miao , Mengying Zhu , Meng Xi , Guanjie Cheng

Point cloud, as a 3D representation, is widely used in autonomous driving, virtual reality (VR), and augmented reality (AR). However, traditional communication systems think that the point cloud's semantic information is irrelevant to…

Multimedia · Computer Science 2023-07-13 Xiaoyi Liu , Haotai Liang , Zhicheng Bao , Chen Dong , Xiaodong Xu

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Muhammad Uzair Khattak , Hanoona Rasheed , Muhammad Maaz , Salman Khan , Fahad Shahbaz Khan

We propose a novel framework to learn 3D point cloud semantics from 2D multi-view image observations containing pose error. On the one hand, directly learning from the massive, unstructured and unordered 3D point cloud is computationally…

Computer Vision and Pattern Recognition · Computer Science 2022-04-28 Yuhang He , Lin Chen , Junkun Xie , Long Chen

In-context learning (ICL) is now a common method for teaching large language models (LLMs) new tasks: given labeled examples in the input context, the LLM learns to perform the task without weight updates. Do models guided via ICL infer the…

Computation and Language · Computer Science 2024-04-11 Aaron Mueller , Albert Webson , Jackson Petty , Tal Linzen

Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D annotations, making labeled samples difficult to obtain. Beyond annotation scarcity,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Thenukan Pathmanathan , Kanchan Keisham , Thangarajah Akilan

Point clouds are a basic data type that is increasingly of interest as 3D content becomes more ubiquitous. Applications using point clouds include virtual, augmented, and mixed reality and autonomous driving. We propose a more efficient…

Computer Vision and Pattern Recognition · Computer Science 2021-06-04 Ryan Killea , Yun Li , Saeed Bastani , Paul McLachlan