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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detection
Secure On-Device Video OOD Detection Without Backpropagation
Structural Entropy Guided Unsupervised Graph Out-Of-Distribution Detection
HALO: Robust Out-of-Distribution Detection via Joint Optimisation
DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories
Advancing Out-of-Distribution Detection via Local Neuroplasticity
Enhancing Out-of-Distribution Detection in Medical Imaging with Normalizing Flows
Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning
A Bayesian Nonparametric Perspective on Mahalanobis Distance for Out of Distribution Detection
Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimation
A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models
Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection
Score Combining for Contrastive OOD Detection
Hypercone Assisted Contour Generation for Out-of-Distribution Detection
A Closer Look at the Learnability of Out-of-Distribution (OOD) Detection
DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection
FARE: A Deep Learning-Based Framework for Radar-based Face Recognition and Out-of-distribution Detection
ARES: Auxiliary Range Expansion for Outlier Synthesis
Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection
Probabilistic Skip Connections for Deterministic Uncertainty Quantification in Deep Neural Networks
Multi-layer Radial Basis Function Networks for Out-of-distribution Detection
Enhancing Reconstruction-Based Out-of-Distribution Detection in Brain MRI with Model and Metric Ensembles
Out-of-Distribution Detection with Prototypical Outlier Proxy
Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observation
Boosting LLM-based Relevance Modeling with Distribution-Aware Robust Learning
ITP: Instance-Aware Test Pruning for Out-of-Distribution Detection
Mining In-distribution Attributes in Outliers for Out-of-distribution Detection
Taylor Outlier Exposure
EDGE: Unknown-aware Multi-label Learning by Energy Distribution Gap Expansion
Out-of-Distribution Detection with Overlap Index
Revisiting Energy-Based Model for Out-of-Distribution Detection
Learning Structured Representations with Hyperbolic Embeddings
NCDD: Nearest Centroid Distance Deficit for Out-Of-Distribution Detection in Gastrointestinal Vision
Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization
Out-Of-Distribution Detection with Diversification (Provably)
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.