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.
Boosting Out-of-Distribution Detection with Multiple Pre-trained Models
Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data
Solving Sample-Level Out-of-Distribution Detection on 3D Medical Images
YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection
Block Selection Method for Using Feature Norm in Out-of-distribution Detection
Improving Training and Inference of Face Recognition Models via Random Temperature Scaling
Rethinking Out-of-Distribution Detection From a Human-Centric Perspective
Out-Of-Distribution Detection Is Not All You Need
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
TrustGAN: Training safe and trustworthy deep learning models through generative adversarial networks
Beyond Mahalanobis-Based Scores for Textual OOD Detection
Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection
Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text
Towards Realistic Out-of-Distribution Detection: A Novel Evaluation Framework for Improving Generalization in OOD Detection
Heatmap-based Out-of-Distribution Detection
Demo Abstract: Real-Time Out-of-Distribution Detection on a Mobile Robot
A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation
Estimating Soft Labels for Out-of-Domain Intent Detection
GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection
Interpreting deep learning output for out-of-distribution detection
Understanding the properties and limitations of contrastive learning for Out-of-Distribution detection
A Theoretical Study on Solving Continual Learning
Exploring Structure-Wise Uncertainty for 3D Medical Image Segmentation
On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors
Uncertainty-based Meta-Reinforcement Learning for Robust Radar Tracking
Is Out-of-Distribution Detection Learnable?
Falsehoods that ML researchers believe about OOD detection
Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble
UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning
Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel
Out of Distribution Reasoning by Weakly-Supervised Disentangled Logic Variational Autoencoder
An out-of-distribution discriminator based on Bayesian neural network epistemic uncertainty
Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning
Pseudo-OOD training for robust language models
Holistic Sentence Embeddings for Better Out-of-Distribution Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.