Published on:
2 May 2024
Primary Category:
Machine Learning
Paper Authors:
Luciano Dyballa,
Evan Gerritz,
Steven W. Zucker
Proposes method to quantify model generalization ability using unseen data
Evaluates latent spaces of intermediate layers with cluster separation metrics
High accuracy on seen classes does not mean good generalization
Generalization ability varies across layers and architectures
Approach reveals intrinsic model properties useful for compression
Quantifying model generalization capability
This paper introduces a method to evaluate how well deep learning image classifiers can generalize to related but unseen data. After training models on one dataset, their intermediate layers are tested on a different dataset from the same domain. A metric quantifies the degree to which unseen classes form separable clusters in the latent space. This reveals which layers have the most intrinsic generalization ability, with implications for model compression. Surprisingly, high accuracy on seen classes does not imply good generalization. The approach is validated across datasets and metrics.
Learning hybrid feature representations for image classification
Assessing model performance on unseen data
Review of Deep Learning Generalization for Medical Imaging
Comparing images based on object identity
Using training dynamics to enhance compositional generalization
Validity of machine learning models using indirect labeling
No comments yet, be the first to start the conversation...
Sign up to comment on this paper