LayerAct: Advanced activation mechanism utilizing layer-direction normalization for CNNs with BatchNorm

• URL: http://arxiv.org/abs/2306.04940v3
• Date: Sun, 4 Feb 2024 10:34:10 GMT
• Title: LayerAct: Advanced activation mechanism utilizing layer-direction normalization for CNNs with BatchNorm
• Authors: Kihyuk Yoon and Chiehyeon Lim
• Abstract summary: LayerAct functions are designed to be more noise-robust compared to existing element-level activation functions. We show that LayerAct functions exhibit superior noise-robustness compared to element-level activation functions.
• Score: 3.413632819633068
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we propose a novel activation mechanism aimed at establishing layer-level activation (LayerAct) functions for CNNs with BatchNorm. These functions are designed to be more noise-robust compared to existing element-level activation functions by reducing the layer-level fluctuation of the activation outputs due to shift in inputs. Moreover, the LayerAct functions achieve this noise-robustness independent of the activation's saturation state, which limits the activation output space and complicates efficient training. We present an analysis and experiments demonstrating that LayerAct functions exhibit superior noise-robustness compared to element-level activation functions, and empirically show that these functions have a zero-like mean activation. Experimental results with three clean and three out-of-distribution benchmark datasets for image classification tasks show that LayerAct functions excel in handling noisy datasets, outperforming element-level activation functions, while the performance on clean datasets is also superior in most cases.

Related papers

• Improving Quaternion Neural Networks with Quaternionic Activation Functions [3.8750364147156247]
  We propose novel quaternion activation functions where we modify either the quaternion magnitude or the phase. The proposed activation functions can be incorporated in arbitrary quaternion valued neural networks trained with gradient descent techniques.
  arXiv  Detail & Related papers  (2024-06-24T09:36:58Z)
• ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models [74.59731375779934]
  Activation sparsity refers to the existence of weakly-contributed elements among activation outputs. This paper introduces a simple and effective sparsification method named "ProSparse" to push LLMs for higher activation sparsity.
  arXiv  Detail & Related papers  (2024-02-21T03:58:49Z)
• ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs [91.31204876440765]
  We introduce a general method that defines neuron activation through neuron output magnitudes and a tailored magnitude threshold. To find the most efficient activation function for sparse computation, we propose a systematic framework. We conduct thorough experiments on LLMs utilizing different activation functions, including ReLU, SwiGLU, ReGLU, and ReLU$2$.
  arXiv  Detail & Related papers  (2024-02-06T08:45:51Z)
• Saturated Non-Monotonic Activation Functions [21.16866749728754]
  We present three new activation functions built with our proposed method: SGELU, SSiLU, and SMish, which are composed of the negative portion of GELU, SiLU, and Mish, respectively, and ReLU's positive portion. The results of image classification experiments on CIFAR-100 indicate that our proposed activation functions are highly effective and outperform state-of-the-art baselines across multiple deep learning architectures.
  arXiv  Detail & Related papers  (2023-05-12T15:01:06Z)
• Efficient Activation Function Optimization through Surrogate Modeling [15.219959721479835]
  This paper aims to improve the state of the art through three steps. First, the benchmark Act-Bench-CNN, Act-Bench-ResNet, and Act-Bench-ViT were created by training convolutional, residual, and vision transformer architectures. Second, a characterization of the benchmark space was developed, leading to a new surrogate-based method for optimization.
  arXiv  Detail & Related papers  (2023-01-13T23:11:14Z)
• Evaluating CNN with Oscillatory Activation Function [0.0]
  CNNs capability to learn high-dimensional complex features from the images is the non-linearity introduced by the activation function. This paper explores the performance of one of the CNN architecture ALexNet on MNIST and CIFAR10 datasets using oscillating activation function (GCU) and some other commonly used activation functions like ReLu, PReLu, and Mish.
  arXiv  Detail & Related papers  (2022-11-13T11:17:13Z)
• Transformers with Learnable Activation Functions [63.98696070245065]
  We use Rational Activation Function (RAF) to learn optimal activation functions during training according to input data. RAF opens a new research direction for analyzing and interpreting pre-trained models according to the learned activation functions.
  arXiv  Detail & Related papers  (2022-08-30T09:47:31Z)
• Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization [74.74339878286935]
  Action features and co-occurrence features often dominate the actual action content in videos. We develop a novel auxiliary task by decoupling these two types of features within a video snippet. We term our method RefactorNet, which first explicitly factorizes the action content and regularizes its co-occurrence features.
  arXiv  Detail & Related papers  (2022-06-23T06:30:08Z)
• Activation Functions: Dive into an optimal activation function [1.52292571922932]
  We find an optimal activation function by defining it as a weighted sum of existing activation functions. The study uses three activation functions, ReLU, tanh, and sin, over three popular image datasets.
  arXiv  Detail & Related papers  (2022-02-24T12:44:11Z)
• Evolving Normalization-Activation Layers [100.82879448303805]
  We develop efficient rejection protocols to quickly filter out candidate layers that do not work well. Our method leads to the discovery of EvoNorms, a set of new normalization-activation layers with novel, and sometimes surprising structures. Our experiments show that EvoNorms work well on image classification models including ResNets, MobileNets and EfficientNets.
  arXiv  Detail & Related papers  (2020-04-06T19:52:48Z)
• Global Context-Aware Progressive Aggregation Network for Salient Object Detection [117.943116761278]
  We propose a novel network named GCPANet to integrate low-level appearance features, high-level semantic features, and global context features. We show that the proposed approach outperforms the state-of-the-art methods both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2020-03-02T04:26:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.