paper-with-me

Novel Class Discovery

3개 벤치마크 · 논문 74편 · 이 태스크의 논문 보기 →

Benchmarks

SVHN

결과 2개

cifar10

결과 2개

cifar100

결과 2개

Most implemented

Papers

Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation

2026-06-05 · Zihao Zhang, Aming Wu, Yang Li, Yahong Han 외 arxiv

Novel class discovery in point cloud segmentation aims to transfer knowledge from known classes to automatically identify and segment unlabeled novel classes in point clouds. Existing methods mainly rely on pairwise asso…

Point Cloud SegmentationNovel Class DiscoverySemantic SegmentationPoint Clouds

GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery

2026-02-23 · Jizhou Han, Chenhao Ding, SongLin Dong, Yuhang He 외 arxiv

Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamical…

Novel Class Discovery

VLM-NCD:Novel Class Discovery with Vision-Based Large Language Models

2025-12-11 · Yuetong Su, Baoguo Wei, Xinyu Wang, Xu Li 외 arxiv

Novel Class Discovery aims to utilise prior knowledge of known classes to classify and discover unknown classes from unlabelled data. Existing NCD methods for images primarily rely on visual features, which suffer from l…

Novel Class Discovery

Image-Intrinsic Priors for Integrated Circuit Defect Detection and Novel Class Discovery via Self-Supervised Learning

2025-11-05 · Botong. Zhao, Xubin. Wang, Shujing. Lyu, Yue. Lu arxiv

Integrated circuit manufacturing is highly complex, comprising hundreds of process steps. Defects can arise at any stage, causing yield loss and ultimately degrading product reliability. Supervised methods require extens…

Self-Supervised LearningNovel Class Discovery

Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning

2025-10-15 · Yang Li, Aming Wu, Zihao Zhang, Yahong Han arxiv

In this paper, we focus on Novel Class Discovery for Point Cloud Segmentation (3D-NCD), aiming to learn a model that can segment unlabeled (novel) 3D classes using only the supervision from labeled (base) 3D classes. The…

Point Cloud SegmentationNovel Class DiscoverySemantic Segmentation

How many classes do we need to see for novel class discovery?

2025-09-19 · Akanksha Sarkar, Been Kim, Jennifer J. Sun arxiv

Novel class discovery is essential for ML models to adapt to evolving real-world data, with applications ranging from scientific discovery to robotics. However, these datasets contain complex and entangled factors of var…

Novel Class Discovery

전체 74편 보기 →