paper-with-me

홈 › Papers

Towards Estimating Transferability using Hard Subsets

2023-01-17 · Tarun Ram Menta, Surgan Jandial, Akash Patil, Vimal KB, Saketh Bachu, Balaji Krishnamurthy, Vineeth N. Balasubramanian, Chirag Agarwal, Mausoom Sarkar

As transfer learning techniques are increasingly used to transfer knowledge from the source model to the target task, it becomes important to quantify which source models are suitable for a given target task without performing computationally expensive fine tuning. In this work, we propose HASTE (HArd Subset TransfErability), a new strategy to estimate the transferability of a source model to a particular target task using only a harder subset of target data. By leveraging the internal and output representations of model, we introduce two techniques, one class agnostic and another class specific, to identify harder subsets and show that HASTE can be used with any existing transferability metric to improve their reliability. We further analyze the relation between HASTE and the optimal average log likelihood as well as negative conditional entropy and empirically validate our theoretical bounds. Our experimental results across multiple source model architectures, target datasets, and transfer learning tasks show that HASTE modified metrics are consistently better or on par with the state of the art transferability metrics.

📄 PDF Abstract BibTeX arXiv:2301.06928

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Transferability and Hardness of Supervised Classification Tasks

2019-08-21 · ICCV 2019 10 · Anh T. Tran, Cuong V. Nguyen, Tal Hassner

We propose a novel approach for estimating the difficulty and transferability of supervised classification tasks. Unlike previous work, our approach is solution agnostic and does not require or assume trained models. Ins…

AttributeClassificationFace RecognitionGeneral Classification

A Generalized Argmax Theorem with Applications

2022-09-19 · Gregory Cox

The argmax theorem is a useful result for deriving the limiting distribution of estimators in many applications. The conclusion of the argmax theorem states that the argmax of a sequence of stochastic processes converges…

Towards Transferable Adversarial Attacks on Vision Transformers

2021-09-09 · Zhipeng Wei, Jingjing Chen, Micah Goldblum, Zuxuan Wu 외

Vision transformers (ViTs) have demonstrated impressive performance on a series of computer vision tasks, yet they still suffer from adversarial examples. % crafted in a similar fashion as CNNs. In this paper, we posit t…

Simple Transferability Estimation for Regression Tasks

2023-12-01 · Cuong N. Nguyen, Phong Tran, Lam Si Tung Ho, Vu Dinh 외

We consider transferability estimation, the problem of estimating how well deep learning models transfer from a source to a target task. We focus on regression tasks, which received little previous attention, and propose…

regressionTransfer Learning

SOAK: Same/Other/All K-fold cross-validation for estimating similarity of patterns in data subsets

2024-10-11 · Toby Dylan Hocking, Gabrielle Thibault, Cameron Scott Bodine, Paul Nelson Arellano 외

In many real-world applications of machine learning, we are interested to know if it is possible to train on the data that we have gathered so far, and obtain accurate predictions on a new test data subset that is qualit…

All