DeepAI AI Chat
Log In Sign Up

Transferability Estimation using Bhattacharyya Class Separability

by   Michal Pándy, et al.

Transfer learning has become a popular method for leveraging pre-trained models in computer vision. However, without performing computationally expensive fine-tuning, it is difficult to quantify which pre-trained source models are suitable for a specific target task, or, conversely, to which tasks a pre-trained source model can be easily adapted to. In this work, we propose Gaussian Bhattacharyya Coefficient (GBC), a novel method for quantifying transferability between a source model and a target dataset. In a first step we embed all target images in the feature space defined by the source model, and represent them with per-class Gaussians. Then, we estimate their pairwise class separability using the Bhattacharyya coefficient, yielding a simple and effective measure of how well the source model transfers to the target task. We evaluate GBC on image classification tasks in the context of dataset and architecture selection. Further, we also perform experiments on the more complex semantic segmentation transferability estimation task. We demonstrate that GBC outperforms state-of-the-art transferability metrics on most evaluation criteria in the semantic segmentation settings, matches the performance of top methods for dataset transferability in image classification, and performs best on architecture selection problems for image classification.


page 1

page 2

page 3

page 4


Building a Winning Team: Selecting Source Model Ensembles using a Submodular Transferability Estimation Approach

Estimating the transferability of publicly available pretrained models t...

Towards Estimating Transferability using Hard Subsets

As transfer learning techniques are increasingly used to transfer knowle...

Evidence > Intuition: Transferability Estimation for Encoder Selection

With the increase in availability of large pre-trained language models (...

Transferability and Hardness of Supervised Classification Tasks

We propose a novel approach for estimating the difficulty and transferab...

Classification in Histopathology: A unique deep embeddings extractor for multiple classification tasks

In biomedical imaging, deep learning-based methods are state-of-the-art ...

Transferability Metrics for Object Detection

Transfer learning aims to make the most of existing pre-trained models t...

Transferability Estimation Based On Principal Gradient Expectation

Deep transfer learning has been widely used for knowledge transmission i...