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/vgtomahawk/LR_GC_OOD
공식 코드https://github.com/victor-yifanwu/Outlier-Exposure-by-Simple-Transformations
공식 코드Revisiting Energy-Based Model for Out-of-Distribution Detection
https://github.com/visual-ai/dissect-ood-osr
공식 코드https://github.com/vlievin/biva-pytorch
공식 코드https://github.com/vrkh1996/Generalization-in-OOD-Detection
공식 코드https://github.com/vuno/kirby
공식 코드Key Feature Replacement of In-Distribution Samples for Out-of-Distribution Detection
https://github.com/walline/prohoc
공식 코드ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks
https://github.com/wentianzhang-ml/adaptivemix
공식 코드https://github.com/wenxichen2746/Perturbation-Rectified-OOD-Detection
공식 코드Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection
https://github.com/windstormer/mecam-ood
공식 코드https://github.com/wiseodd/bayesian_ood_training
공식 코드https://github.com/wjun0830/localizable-rotation
공식 코드https://github.com/wyn430/wood
공식 코드https://github.com/wzhouad/Contra-OOD
공식 코드Contrastive Out-of-Distribution Detection for Pretrained Transformers
https://github.com/xbyym/dlsr
공식 코드Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
https://github.com/xiaoyuanguo/cvad
공식 코드CVAD: A generic medical anomaly detector based on Cascade VAE
https://github.com/xmed-lab/clipn
공식 코드https://github.com/ybzh/lapt
공식 코드LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models
https://github.com/ycfate/id-like
공식 코드ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
https://github.com/yellowmessenger/ood-detection
공식 코드BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detection
https://github.com/yixinliu233/g-ood-d
공식 코드https://github.com/yupei-wang/uninl
공식 코드https://github.com/yuxiaoleemarks/cma
공식 코드Concept Matching with Agent for Out-of-Distribution Detection
https://github.com/yyliu01/rpl
공식 코드Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
https://github.com/zaharah/ood_audio
공식 코드On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors
https://github.com/zheminzhang96/hand_mammo
공식 코드Unsupervised Hybrid framework for ANomaly Detection (HAND) -- applied to Screening Mammogram
https://github.com/zhengtaoyao/lego
공식 코드https://github.com/zjlab-ammi/vae4ood
공식 코드Unsupervised Out-of-Distribution Detection by Restoring Lossy Inputs with Variational Autoencoder
https://github.com/zjysteven/mixoe
공식 코드Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments
https://github.com/zmtomorrow/nelloc
공식 코드On the Out-of-distribution Generalization of Probabilistic Image Modelling
https://github.com/zxj32/uncertainty-GNN
공식 코드https://github.com/zxk1212/OODD
공식 코드OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary
https://gitlab.com/Bitterwolf/GOOD
공식 코드Certifiably Adversarially Robust Detection of Out-of-Distribution Data
https://github.com/2023-MindSpore-1/ms-code-223/tree/main/SSD
SSD: A Unified Framework for Self-Supervised Outlier Detection
https://github.com/2023-MindSpore-4/Code13/tree/main/zhangchangqing/TMC_MS-main
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.