paper-with-me

Papers

Trainable Highly-expressive Activation Functions

2024-07-10 · 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.

📄 PDF Abstract BibTeX arXiv:2407.07564

Code (1)

bgu-cs-vil/ditac 공식 구현 pytorch

Tasks

image-classificationImage ClassificationImage GenerationSemantic Segmentation

Similar Papers 제목 키워드 기반

ENN: A Neural Network with DCT Adaptive Activation Functions

2023-07-02 · Marc Martinez-Gost, Ana Pérez-Neira, Miguel Ángel Lagunas

The expressiveness of neural networks highly depends on the nature of the activation function, although these are usually assumed predefined and fixed during the training stage. Under a signal processing perspective, in …

A Family of Adaptive Activation Functions for Mitigating Failure Modes in Physics-Informed Neural Networks

2026-03-18 · Krishna Murari arxiv

Physics-Informed Neural Networks(PINNs) are a powerful and flexible learning framework that has gained significant attention in recent years. It has demonstrated strong performance across a wide range of scientific and e…

Trainable Activations for Image Classification

2023-01-26 · Preprints 2023 1 · Evgenii Pishchik

Non-linear activation functions are one of the main parts of deep neural network architectures. The choice of the activation function can affect model speed, performance and convergence. Most popular activation functions…

image-classificationImage Classification

A survey on modern trainable activation functions

2020-05-02 · Andrea Apicella, Francesco Donnarumma, Francesco Isgrò, Roberto Prevete

In neural networks literature, there is a strong interest in identifying and defining activation functions which can improve neural network performance. In recent years there has been a renovated interest of the scientif…

Survey

A Logical View of GNN-Style Computation and the Role of Activation Functions

2025-12-22 · Pablo Barceló, Floris Geerts, Matthias Lanzinger, Klara Pakhomenko 외 arxiv

We study the numerical and Boolean expressiveness of MPLang, a declarative language that captures the computation of graph neural networks (GNNs) through linear message passing and activation functions. We begin with A-M…