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/hewell0/projood
공식 코드https://github.com/hoshi23/ood-x-banchmarks
공식 코드A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models
https://github.com/hoshi23/ood-x-benchmarks
공식 코드A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models
https://github.com/huawei-noah/noah-research
공식 코드Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection
https://github.com/hugo0076/halo
공식 코드HALO: Robust Out-of-Distribution Detection via Joint Optimisation
https://github.com/hyunjunChhoi/Balanced_Energy
공식 코드Balanced Energy Regularization Loss for Out-of-distribution Detection
https://github.com/hyunsoocho77/lacl-official
공식 코드https://github.com/ifiaposto/distance_aware_bottleneck
공식 코드https://github.com/ika-rwth-aachen/occuq
공식 코드OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction
https://github.com/inar-design/patt
공식 코드Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail
https://github.com/inimah/protoinfomax
공식 코드ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection
https://github.com/inspire-group/SSD
공식 코드SSD: A Unified Framework for Self-Supervised Outlier Detection
https://github.com/irom-lab/Task_Relevant_OOD_Detection
공식 코드Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning
https://github.com/ividja/Probabilistic-PII
공식 코드Confidence-Aware and Self-Supervised Image Anomaly Localisation
https://github.com/j-cb/breaking_down_ood_detection
공식 코드https://github.com/j-cb/ninco
공식 코드In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation
https://github.com/jayjaynandy/maximize-representation-gap
공식 코드Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples
https://github.com/jeff024/palm
공식 코드Learning with Mixture of Prototypes for Out-of-Distribution Detection
https://github.com/jfc43/informative-outlier-mining
공식 코드ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining
https://github.com/jfc43/robust-ood-detection
공식 코드https://github.com/jhornauer/heatmap_ood
공식 코드https://github.com/jihyechoi77/concepts-for-ood
공식 코드Concept-based Explanations for Out-Of-Distribution Detectors
https://github.com/jimzai/mode-ood
공식 코드From Global to Local: Multi-scale Out-of-distribution Detection
https://github.com/jingkang50/oodsurvey
공식 코드https://github.com/jingkang50/openood
공식 코드https://github.com/jkatzsam/woods_ood
공식 코드https://github.com/jylins/hood
공식 코드Out-of-Distribution Detection with Hilbert-Schmidt Independence Optimization
https://github.com/k-gyuhak/clom
공식 코드https://github.com/k-gyuhak/clood
공식 코드https://github.com/k-gyuhak/more
공식 코드A Multi-Head Model for Continual Learning via Out-of-Distribution Replay
https://github.com/k-gyuhak/wptp
공식 코드https://github.com/kai422/scale
공식 코드Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement
https://github.com/kaustubhsridhar/time-series-ood
공식 코드CODiT: Conformal Out-of-Distribution Detection in Time-Series Data
https://github.com/kding1225/VLPT-OOD
공식 코드Weak Distribution Detectors Lead to Stronger Generalizability of Vision-Language Prompt Tuning
https://github.com/kingjamessong/rankfeat
공식 코드RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.