Why do classifier accuracies show linear trends under distribution shift?

31 December 2020

Papers citing "Why do classifier accuracies show linear trends under distribution shift?"

7 / 7 papers shown

Title
Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data Florian E. Dorner Vivian Y. Nastl Moritz Hardt ELM ALM 42 5 0 17 Oct 2024
A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking Chang-Shu Liu Yinpeng Dong Wenzhao Xiang X. Yang Hang Su Junyi Zhu YueFeng Chen Yuan He H. Xue Shibao Zheng OOD VLM AAML 27 72 0 28 Feb 2023
DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Models Vivian Lin Kuk Jin Jang Souradeep Dutta Michele Caprio O. Sokolsky Insup Lee OOD 26 6 0 20 Feb 2023
Pathologies of Predictive Diversity in Deep Ensembles Taiga Abe E. Kelly Buchanan Geoff Pleiss John P. Cunningham UQCV 38 13 0 01 Feb 2023
Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization Daniel LeJeune Jiayu Liu Reinhard Heckel 18 0 0 20 Oct 2022
When does dough become a bagel? Analyzing the remaining mistakes on ImageNet Vijay Vasudevan Benjamin Caine Raphael Gontijo-Lopes Sara Fridovich-Keil Rebecca Roelofs VLM UQCV 33 57 0 09 May 2022
The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning Anders Andreassen Yasaman Bahri Behnam Neyshabur Rebecca Roelofs OOD OODD 22 78 0 30 Jun 2021