paper-with-me

홈 › Papers

SHADE: Information Based Regularization for Deep Learning

2018-04-29 · Michael Blot, Thomas Robert, Nicolas Thome, Matthieu Cord

Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define a prior based on conditional entropy, which explicitly decouples the learning of invariant representations in the regularizer and the learning of correlations between inputs and labels in the data fitting term. Our second contribution is to derive a stochastic version of the regularizer compatible with deep learning, resulting in a tractable training scheme. We empirically validate the efficiency of our approach to improve classification performances compared to common regularization schemes on several standard architectures.

📄 PDF Abstract BibTeX arXiv:1804.10988

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningGeneral Classification

Similar Papers 제목 키워드 기반

SHADE: SHAnnon DEcay Information-Based Regularization for Deep Learning

2018-01-01 · ICLR 2018 1 · Michael Blot, Thomas Robert, Nicolas Thome, Matthieu Cord

Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define …

Deep LearningGeneral Classification

SHADE: Information-Based Regularization for Deep Learning

2018-05-14 · Michael Blot, Thomas Robert, Nicolas Thome, Matthieu Cord

Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define …

Deep LearningGeneral Classification

DeepShade: Enable Shade Simulation by Text-conditioned Image Generation

2025-07-16 · Longchao Da, Xiangrui Liu, Mithun Shivakoti, Thirulogasankar Pranav Kutralingam 외 arxiv

Heatwaves pose a significant threat to public health, especially as global warming intensifies. However, current routing systems (e.g., online maps) fail to incorporate shade information due to the difficulty of estimati…

Contrastive LearningImage Generation

ShadeBench: A Benchmark Dataset for Building Shade Simulation in Sustainable Society

2026-05-19 · Longchao Da, Mithun Shivakoti, Xiangrui Liu, T Pranav Kutralingam 외 arxiv

Urban heat exposure is becoming an increasingly critical challenge due to the intensifying urban heat island effect. Fine-grained shade patterns, especially those induced by urban buildings, strongly influence pedestrian…

A Tool for the Procedural Generation of Shaders using Interactive Evolutionary Algorithms

2023-12-29 · Elio Sasso, Daniele Loiacono, Pier Luca Lanzi

We present a tool for exploring the design space of shaders using an interactive evolutionary algorithm integrated with the Unity editor, a well-known commercial tool for video game development. Our framework leverages t…

Evolutionary AlgorithmsUnity