13 skills found
huytransformer / Awesome Out Of Distribution DetectionOut-of-distribution detection, robustness, and generalization resources. The repository contains a curated list of papers, tutorials, books, videos, articles and open-source libraries etc
worldbench / Robo3D[ICCV 2023] Robo3D: Towards Robust and Reliable 3D Perception against Corruptions
YyzHarry / SubpopBench[ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift
Intellindust-AI-Lab / SURE“SURE: SUrvey REcipes for building reliable and robust deep networks” (CVPR 2024) & (ECCV 2024 OOD-CV Challenge Winner)
shyam671 / Mask2Anomaly Unmasking Anomalies In Road Scene Segmentation[ICCV'23 Oral] Unmasking Anomalies in Road-Scene Segmentation
jfc43 / Informative Outlier MiningWe 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.
LINs-lab / FedTHE[ICLR 2023] Test-time Robust Personalization for Federated Learning
LinLLLL / CRoFTThe official implementation of CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection (ICML2024).
acforvs / Dhc Robust MapfLearnable MAPF. “Distributed Heuristic Multi-Agent Path Finding with Communication” (DHC) algorithm from ICRA 2021 is implemented and benchmarked in out-of-distribution (OOD) scenarios. A new robust training loop to handle communication failures is introduced.
IBM / AutoVP[ICLR24] AutoVP: An Automated Visual Prompting Framework and Benchmark
likuanppd / GOOD ATThe code of ICLR 2024 paper: Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective
stvsd1314 / PPGN Physics Preserved Graph NetworksThe increasing number of variable renewable energy (solar and wind power) causes power grids to have more abnormal conditions or faults. Faults may further trigger power blackouts or wildfires without timely monitoring and control strategy. Machine learning is a promising technology to accelerate the automation and intelligence of power grid monitoring systems. Unfortunately, the black-box machine learning methods are weak to the realistic challenges in power grids: low observation, insufficient labels, and stochastic environments. To overcome the vulnerability of black-box machine learning, we preserve the physics of power grids through graph networks to efficiently and accurately locate the faults even with limited observability and low label rates. We first calculate the graph embedding of power grid infrastructure by establishing a reduced graph network with the observed nodes, then efficiently locate the fault on the node level using the low-dimensional graph embedding. To augment the location accuracy at low label rates, we build another graph network representing the physical similarity of labeled and unlabeled data samples. Importantly, we provide the physical interpretations of the benefits of the graph design through a random walk equivalence. We conduct comprehensive numerical experiments in the IEEE 123-node. Our proposed method shows superior performance than three baseline classifiers for different fault types, label rates, and robustness to out-of-distribution (OOD) data. Additionally, we extend the proposed method to the IEEE 37-node benchmark system and validate the effectiveness of the proposed training strategy.
MaybeLizzy / Diffusion OOD RobustnessNo description available
