https://github.com/ClancyZhou/P_Net_Anomaly_Detection
공식 코드Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images
Papers with Code 아카이브
Novel Class Discovery
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 3
The goal of Novel Class Discovery (NCD) is to identify new classes in unlabeled data, by exploiting prior knowledge from known classes. In this specific setup, the data is split in two sets. The first is a labeled set containing known classes and the second is an unlabeled set containing unknown classes that must be discovered.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/HeliosZhao/NCDSS
공식 코드https://github.com/MalekSnous/hNCD-scRNAseq
공식 코드Hierarchical novel class discovery for single-cell transcriptomic profiles
https://github.com/RikkiXu/NCD_PC
공식 코드Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation
https://github.com/averyfallson/rmffn
공식 코드Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery
https://github.com/cemos-is/text3daug-augmentation
공식 코드Text3DAug -- Prompted Instance Augmentation for LiDAR Perception
https://github.com/colintr/interactiveclustering
공식 코드An Interactive Interface for Novel Class Discovery in Tabular Data
https://github.com/colintr/tabularncd
공식 코드https://github.com/cvmi-lab/simgcd
공식 코드Parametric Classification for Generalized Category Discovery: A Baseline Study
https://github.com/deeplearning-wisc/nscl
공식 코드https://github.com/fanzhichen/ncd-iic
공식 코드Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery
https://github.com/haoang97/medi
공식 코드Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
https://github.com/hust-slow/anomalyncd
공식 코드AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios
https://github.com/j-l-o/sk-hurt-ncd
공식 코드Supervised Knowledge May Hurt Novel Class Discovery Performance
https://github.com/josephkj/awesome-novel-class-discovery
공식 코드https://github.com/k-han/AutoNovel
공식 코드AutoNovel: Automatically Discovering and Learning Novel Visual Categories
https://github.com/kleinzcy/cr-kd-ncd
공식 코드Class-relation Knowledge Distillation for Novel Class Discovery
https://github.com/kleinzcy/ncdlr
공식 코드https://github.com/liujmzzz/openncd
공식 코드https://github.com/luigiriz/nops
공식 코드Novel Class Discovery for 3D Point Cloud Semantic Segmentation
https://github.com/name-is-what/nc2d
공식 코드https://github.com/naver/pandas
공식 코드https://github.com/nayeemrizve/trssl
공식 코드https://github.com/oatmealliu/class-incd
공식 코드https://github.com/oatmealliu/msc-incd
공식 코드Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
https://github.com/orange-opensource/practicalncd
공식 코드A Practical Approach to Novel Class Discovery in Tabular Data
https://github.com/rohit901/cooperative-foundational-models
공식 코드Enhancing Novel Object Detection via Cooperative Foundational Models
https://github.com/ssdut-caiyq/ufg-ncd
공식 코드Novel Class Discovery for Ultra-Fine-Grained Visual Categorization
https://github.com/vlfom/rncdl
공식 코드https://github.com/yebo0216best/lps-main
공식 코드Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning
https://github.com/ynanwu/metagcd
공식 코드MetaGCD: Learning to Continually Learn in Generalized Category Discovery
https://github.com/zhenyuw16/uni3detr
공식 코드OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation
https://github.com/zhunzhong07/NCL
공식 코드https://github.com/DonkeyShot21/UNO
https://github.com/mashijie1028/activegcd
Parametric Classification for Generalized Category Discovery: A Baseline Study
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.