https://github.com/sesmae/zoc
공식 코드Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP
Papers with Code 아카이브
Out of Distribution (OOD) Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 4
- 보존된 평가 기록
- 4
Out of Distribution (OOD) Detection is the task of detecting instances that do not belong to the distribution the classifier has been trained on. OOD data is often referred to as "unseen" data, as the model has not encountered it during training.
OOD detection is typically performed by training a model to distinguish between in-distribution (ID) data, which the model has seen during training, and OOD data, which it has not seen. This can be done using a variety of techniques, such as training a separate OOD detector, or modifying the model's architecture or loss function to make it more sensitive to OOD data.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/sharpenb/Posterior-Network
공식 코드Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
https://github.com/shinypond/ood_detection
공식 코드Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
https://github.com/shuolucs/awesome-out-of-distribution-detection
공식 코드https://github.com/silverriver/ood4nlu
공식 코드Out-of-domain Detection for Natural Language Understanding in Dialog Systems
https://github.com/snowood1/BERT-ENN
공식 코드https://github.com/snowood1/wenn
공식 코드Multidimensional Uncertainty-Aware Evidential Neural Networks
https://github.com/snu-mllab/neural-relation-graph
공식 코드Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
https://github.com/somepago/AMA
공식 코드Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
https://github.com/stanislavfort/adversaries_to_ood_detection
공식 코드Adversarial vulnerability of powerful near out-of-distribution detection
https://github.com/stomach-ache/long-tailed-ood-detection
공식 코드https://github.com/sudarshanregmi/AdaSCALE
공식 코드https://github.com/sudarshanregmi/T2FNorm
공식 코드T2FNorm: Extremely Simple Scaled Train-time Feature Normalization for OOD Detection
https://github.com/sudarshanregmi/ascood
공식 코드https://github.com/sungjinl/icassp2019-ood-dataset
공식 코드Contextual Out-of-Domain Utterance Handling With Counterfeit Data Augmentation
https://github.com/sunnan191/evisec
공식 코드Evidential Spectrum-Aware Contrastive Learning for OOD Detection in Dynamic Graphs
https://github.com/sverneka/ConfidentClassifierICLR19
공식 코드Analysis of Confident-Classifiers for Out-of-distribution Detection
https://github.com/sverneka/OODGen
공식 코드https://github.com/tahabelkhouja/srs
공식 코드Out-of-Distribution Detection in Time-Series Domain: A Novel Seasonal Ratio Scoring Approach
https://github.com/tajwarfahim/dcm
공식 코드Conservative Prediction via Data-Driven Confidence Minimization
https://github.com/tajwarfahim/ood_detection_inconsistency
공식 코드No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets
https://github.com/taralloc/st-rkm-ood
공식 코드Unsupervised Energy-based Out-of-distribution Detection using Stiefel-Restricted Kernel Machine
https://github.com/tgargiani/adaptive-boundary
공식 코드Metric Learning and Adaptive Boundary for Out-of-Domain Detection
https://github.com/thalesgroup/trustgan
공식 코드TrustGAN: Training safe and trustworthy deep learning models through generative adversarial networks
https://github.com/thwjoy/adats
공식 코드Sample-dependent Adaptive Temperature Scaling for Improved Calibration
https://github.com/tmlr-group/atol
공식 코드Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
https://github.com/tmlr-group/cover
공식 코드https://github.com/tmlr-group/neglabel
공식 코드Negative Label Guided OOD Detection with Pretrained Vision-Language Models
https://github.com/tmlr-group/sct
공식 코드Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
https://github.com/ub-gold/ub-gold
공식 코드Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark
https://github.com/uditarora/ood-text-emnlp
공식 코드https://github.com/uestc-nnlab/mvol
공식 코드Mining In-distribution Attributes in Outliers for Out-of-distribution Detection
https://github.com/uiuctml/HypStructure
공식 코드Learning Structured Representations with Hyperbolic Embeddings
https://github.com/um-dsp/morphence
공식 코드Morphence-2.0: Evasion-Resilient Moving Target Defense Powered by Out-of-Distribution Detection
https://github.com/uppaal/lm-ood
공식 코드Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection
https://github.com/valeoai/genval
공식 코드Reliability in Semantic Segmentation: Can We Use Synthetic Data?
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.