👽 Out-of-Distribution Detection with PyTorch

[NeurIPS 2023] RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

[ECCV'22 Oral] Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes

ICCV 2023: CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No

Official PyTorch implementation of MOOD series: (1) MOODv1: Rethinking Out-of-distributionDetection: Masked Image Modeling Is All You Need. (2) MOODv2: Masked Image Modeling for Out-of-Distribution Detection.

[ICCV 2021 Oral] Deep Evidential Action Recognition

[ICCV'23] Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation

A project to add scalable state-of-the-art out-of-distribution detection (open set recognition) support by changing two lines of code! Perform efficient inferences (i.e., do not increase inference time) and detection without classification accuracy drop, hyperparameter tuning, or collecting additional data.

[SafeAI'21] Feature Space Singularity for Out-of-Distribution Detection.

Robust Out-of-distribution Detection in Neural Networks

The Official Implementation of the ICCV-2021 Paper: Semantically Coherent Out-of-Distribution Detection.

[ICCV'23 Oral] Unmasking Anomalies in Road-Scene Segmentation

We propose a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness of OOD detection to various types of adversarial OOD inputs and establishes state-of-the-art performance.

[ICRA2025] OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction

A project to improve out-of-distribution detection (open set recognition) and uncertainty estimation by changing a few lines of code in your project! Perform efficient inferences (i.e., do not increase inference time) without repetitive model training, hyperparameter tuning, or collecting additional data.

[ICLR 2024 Spotlight] R-EDL: Relaxing Nonessential Settings of Evidential Deep Learning

[NeurIPS 2024] Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models

[CVPR 2025] Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving

Code for Paper: Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data

Code for "BayesAdapter: Being Bayesian, Inexpensively and Robustly, via Bayeisan Fine-tuning"