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/dlotfi/medoodflow
공식 코드Enhancing Out-of-Distribution Detection in Medical Imaging with Normalizing Flows
https://github.com/dvlab-research/logits-based-finetuning
공식 코드https://github.com/dystopians/secdood
공식 코드Secure On-Device Video OOD Detection Without Backpropagation
https://github.com/edadaltocg/detectors
공식 코드Combine and Conquer: A Meta-Analysis on Data Shift and Out-of-Distribution Detection
https://github.com/edadaltocg/igeood
공식 코드Igeood: An Information Geometry Approach to Out-of-Distribution Detection
https://github.com/edadaltocg/ood-trajectory-projection
공식 코드A Functional Data Perspective and Baseline On Multi-Layer Out-of-Distribution Detection
https://github.com/edw2n/imagenet-es
공식 코드https://github.com/eerdil/task_agnostic_ood
공식 코드Task-agnostic Out-of-Distribution Detection Using Kernel Density Estimation
https://github.com/ericjang/odin
공식 코드WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
https://github.com/ericpts/reto
공식 코드Semi-supervised novelty detection using ensembles with regularized disagreement
https://github.com/evihuijben/ood_detection_mri
공식 코드https://github.com/falesiani/gib
공식 코드Gated Information Bottleneck for Generalization in Sequential Environments
https://github.com/fanghenshaometeor/ood-kernel-pca
공식 코드https://github.com/fanghenshaometeor/ood-kpca-extension
공식 코드Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selections and Approximations
https://github.com/fanghenshaometeor/ood-mode-ensemble
공식 코드Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective
https://github.com/fir-lat/hamos_ood
공식 코드Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection
https://github.com/fjelenic/between-layer-ood
공식 코드Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness
https://github.com/frejberglind/xood
공식 코드XOOD: Extreme Value Based Out-Of-Distribution Detection For Image Classification
https://github.com/fukuchan41/tayloroe
공식 코드https://github.com/gaozhitong/multishiftseg
공식 코드Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts
https://github.com/giovannicina/selecting_ood_detector
공식 코드Out-of-Distribution Detection for Medical Applications: Guidelines for Practical Evaluation
https://github.com/gist-ailab/block-selection-for-ood-detection
공식 코드Block Selection Method for Using Feature Norm in Out-of-distribution Detection
https://github.com/glhr/beyond-auroc
공식 코드Beyond AUROC & co. for evaluating out-of-distribution detection performance
https://github.com/glhr/ood-labelnoise
공식 코드A noisy elephant in the room: Is your out-of-distribution detector robust to label noise?
https://github.com/gmr523/pop
공식 코드Out-of-Distribution Detection with Prototypical Outlier Proxy
https://github.com/google-research/google-research
공식 코드https://github.com/google/uncertainty-baselines
공식 코드A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection
https://github.com/guoxoug/ens-div-ood-detect
공식 코드On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection
https://github.com/guoxoug/sirc
공식 코드Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data
https://github.com/guyAmit/GLOD
공식 코드https://github.com/haiyunyao/diversemix
공식 코드Out-Of-Distribution Detection with Diversification (Provably)
https://github.com/haoliangwang86/la-ood
공식 코드Layer Adaptive Deep Neural Networks for Out-of-distribution Detection
https://github.com/haozheliu-st/dynamicfeatureaggregation
공식 코드https://github.com/harryanthony/mahalanobis-ood-detection
공식 코드https://github.com/hendrycks/outlier-exposure
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.