Published on:
8 May 2024
Primary Category:
Machine Learning
Paper Authors:
Hengyue Liang,
Le Peng,
Ju Sun
Proposes generalized selective classification to handle multiple data shifts
Identifies scale sensitivity issues of softmax-based confidence scores
Develops two effective margin-based confidence scores
Shows superior reliability of margins for selectivity
Analyzes favorable rejection patterns of margin scores
Selective classification to enable reliable deep learning deployment
This paper proposes a selective classification framework that allows for distribution shifts between training and deployment. It focuses on developing non-training-based confidence scores to reject likely-incorrect predictions on deep learning models. The key ideas are margin-based scores that are more reliable than existing methods under label/covariance shifts.
Detecting distribution shift in model-based optimization
Guiding language model fine-tuning with external confidence scores
Simplified Title Focusing on Key Contributions
Detecting out-of-distribution images
Improving classifiers through soft labels
Efficient adaptation of machine learning models for changing data
No comments yet, be the first to start the conversation...
Sign up to comment on this paper