Oren Freifeld

Senior Academic

Trainable Highly-Expressive Activation Functions

Irit Chelly, Shahaf E. Finder, Shira Ifergane, Oren Freifeld

Nonlinear activation functions are pivotal to the success of deep neural nets, and choosing the appropriate activation function can significantly affect their performance. Most networks use fixed activation functions (e.g., ReLU, GELU, etc.), and this choice might limit their expressiveness. Furthermore, different layers may benefit from diverse activation functions. Consequently, there has been a growing interest in trainable activation functions. In this paper, we introduce DiTAC, a trainable highly-expressive activation function based on an efficient diffeomorphic transformation (called CPAB). Despite introducing only a negligible number of trainable parameters, DiTAC enhances model expressiveness and performance, often yielding substantial improvements. It also outperforms existing activation functions (regardless whether the latter are fixed or trainable) in tasks such as semantic segmentation, image generation, regression problems, and image classification. Our code is available at https://github.com/BGU-CS-VIL/DiTAC.

Publication language English
Pages 200-217
Publication status Published - 01.01.2025

Keywords

Deep Learning
Diffeomorphisms
Trainable Activation functions

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science