Cover Image

Leaky ReLUs That Differ in Forward and Backward Pass Facilitate Activation Maximization in Deep Neural Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Linse, Christoph, Barth, Erhardt, Martinetz, Thomas
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Convolutional Neural Networks Do Work with Pre-Defined Filters
by: Linse, Christoph, et al.
Published: (2024)

Enhancing Generalization in Convolutional Neural Networks through Regularization with Edge and Line Features
by: Linse, Christoph, et al.
Published: (2024)

Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes
by: Martinetz, Julius, et al.
Published: (2024)

ReLUs Are Sufficient for Learning Implicit Neural Representations
by: Shenouda, Joseph, et al.
Published: (2024)

Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations
by: Anderson, Kathleen, et al.
Published: (2025)

Nearest-Neighbor Density Estimation for Dependency Suppression
by: Anderson, Kathleen, et al.
Published: (2026)

Complexity of Linear Regions in Self-supervised Deep ReLU Networks
by: Muthivhi, Mufhumudzi, et al.
Published: (2026)

Deep ReLU Networks Have Surprisingly Simple Polytopes
by: Fan, Feng-Lei, et al.
Published: (2023)

Lifelong Person Re-Identification with Backward-Compatibility
by: Oh, Minyoung, et al.
Published: (2024)

Forward-Backward Knowledge Distillation for Continual Clustering
by: Sadeghi, Mohammadreza, et al.
Published: (2024)

Blind Image Deblurring with FFT-ReLU Sparsity Prior
by: Radi, Abdul Mohaimen Al, et al.
Published: (2024)

Deep Learning using Rectified Linear Units (ReLU)
by: Agarap, Abien Fred
Published: (2018)

The effect of Leaky ReLUs on the training and generalization of overparameterized networks
by: Guo, Yinglong, et al.
Published: (2024)

Training Convolutional Neural Networks with the Forward-Forward algorithm
by: Scodellaro, Riccardo, et al.
Published: (2023)

From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
by: Liu, Wei, et al.
Published: (2026)

Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Models
by: Dong, Songlin, et al.
Published: (2025)

UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass
by: Li, Mengfei, et al.
Published: (2026)

Comparison of Different Deep Neural Network Models in the Cultural Heritage Domain
by: Boyadzhiev, Teodor, et al.
Published: (2025)

FFGAF-SNN: The Forward-Forward Based Gradient Approximation Free Training Framework for Spiking Neural Networks
by: Xu, Changqing, et al.
Published: (2025)

DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations
by: Hu, Wenhao, et al.
Published: (2024)

ChannelDropBack: Forward-Consistent Stochastic Regularization for Deep Networks
by: Neiterman, Evgeny Hershkovitch, et al.
Published: (2024)

A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill Recognition
by: Zhang, Jinghua, et al.
Published: (2023)

A Significantly Better Class of Activation Functions Than ReLU Like Activation Functions
by: Noel, Mathew Mithra, et al.
Published: (2024)

Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging
by: Zhu, Zhilin, et al.
Published: (2026)

DAM: Diffusion Activation Maximization for 3D Global Explanations
by: Tan, Hanxiao
Published: (2024)

Imaging Signal Recovery Using Neural Network Priors Under Uncertain Forward Model Parameters
by: Chen, Xiwen, et al.
Published: (2024)

XOResNet: Exclusive-OR Meta-Residuals Facilitate Deep Spiking Neural Networks Learning
by: Wu, Jianfang, et al.
Published: (2026)

ReCoSplat: Autoregressive Feed-Forward Gaussian Splatting Using Render-and-Compare
by: Cheng, Freeman, et al.
Published: (2026)

Incremental Online Learning of Randomized Neural Network with Forward Regularization
by: Wang, Junda, et al.
Published: (2024)

Image Clustering using an Augmented Generative Adversarial Network and Information Maximization
by: Ntelemis, Foivos, et al.
Published: (2020)

Representation Understanding via Activation Maximization
by: Zhu, Hongbo, et al.
Published: (2025)

ReLoop: "Seeing Twice and Thinking Backwards" via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding
by: Yang, Jianjiang, et al.
Published: (2025)

Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations
by: Tartaglini, Alexa R., et al.
Published: (2023)

Rapid Salient Object Detection with Difference Convolutional Neural Networks
by: Su, Zhuo, et al.
Published: (2025)

Offline Writer Identification Using Convolutional Neural Network Activation Features
by: Christlein, Vincent, et al.
Published: (2024)

You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
by: Yang, Yinuo, et al.
Published: (2026)

Implicit Neural Representation Facilitates Unified Universal Vision Encoding
by: Gwilliam, Matthew, et al.
Published: (2026)

Energy Backdoor Attack to Deep Neural Networks
by: Meftah, Hanene F. Z. Brachemi, et al.
Published: (2025)

Scaling Backwards: Minimal Synthetic Pre-training?
by: Nakamura, Ryo, et al.
Published: (2024)

Re-Activating Frozen Primitives for 3D Gaussian Splatting
by: Cheng, Yuxin, et al.
Published: (2025)