Project Page (ObjectDR)
-
Updated
Mar 22, 2024 - JavaScript
Project Page (ObjectDR)
I'm now interested in Learning to Adapt to Domain Shift
Deep neural networks have garnered tremendous excitement in recent years thanks to their superior learning capacity in the presence of abundant data resources. However, collecting an exhaustive dataset covering all possible scenarios is often slow, expensive, and even impractical. The goal of this project is to devise a new learning framework th…
Prudent Response Surface Models combine predictions with confidence scores and uncertainty levels, allowing their use in downstream analysis even for high-uncertainty or out-of-distribution inputs.
Out of Distribution Performance of State of Art Vision Model - Robustness evaluation
[WSDM 2023] "Alleviating Structrual Distribution Shift in Graph Anomaly Detection" by Yuan Gao, Xiang Wang, Xiangnan He, Zhenguang Liu, Huamin Feng, Yongdong Zhang
[NeurIPS 2023] "Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift" by Yongduo Sui, Qitian Wu, Jiancan Wu, Qing Cui, Longfei Li, Jun Zhou, Xiang Wang, Xiangnan He.
Intuitive evaluation of out-of-distribution detectors using simple toy examples.
Code for the ICLR 2021 Paper "In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness"
This work is a analysis of representations acquired for standard, OOD and Biased data on numerous objective functions.
Implementation of the algorithms from "Learning Invariant Representations under General Interventions on the Response"
Nearest Category Generalization
[NeurIPS 2023 (Spotlight)] Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts
[IV 2024] Official code for "Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detection"
The Limits of Fair Medical Imaging AI In The Wild
Project Page (PromptStyler, ICCV 2023)
Official code and data for NeurIPS 2023 paper "ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification"
Masking Strategies for Background Bias Removal in Computer Vision Models (ICCVW OODCV 2023 paper)
Replication package of the paper "On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Languages Models of Code" (FSE 2023)
Add a description, image, and links to the out-of-distribution topic page so that developers can more easily learn about it.
To associate your repository with the out-of-distribution topic, visit your repo's landing page and select "manage topics."