Search Results for author:
Found 20 papers, 4 papers with code
Color Constancy Convolutional Autoencoder
In this paper, we study the importance of pre-training for the generalization capability in the color constancy problem.
Bag of Color Features For Color Constancy
To further improve the illumination estimation accuracy, we propose a novel attention mechanism for the BoCF model with two variants based on self-attention.
INTEL-TAU: A Color Constancy Dataset
In this paper, we describe a new large dataset for illumination estimation.
Few-Shot Camera-Adaptive Color Constancy
Image Declipping
+1
Probabilistic Color Constancy
In this paper, we propose a novel unsupervised color constancy method, called Probabilistic Color Constancy (PCC).
Monte Carlo Dropout Ensembles for Robust Illumination Estimation
Computational color constancy is a preprocessing step used in many camera systems.
Graph Embedding with Data Uncertainty
spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines.
ON NEURAL NETWORK GENERALIZATION VIA PROMOTING WITHIN-LAYER ACTIVATION DIVERSITY
During the last decade, neural networks have been intensively used to tackle various problems and they have often led to state-of-the-art results.
Learning distinct features helps, provably
We study the diversity of the features learned by a two-layer neural network trained with the least squares loss.
Improving Neural Network Generalization via Promoting Within-Layer Diversity
Neural networks are composed of multiple layers arranged in a hierarchical structure jointly trained with a gradient-based optimization, where the errors are back-propagated from the last layer back to the first one.
Robust channel-wise illumination estimation
We test this approach on the proposed method and show that it can indeed be used to avoid several extreme error cases and, thus, improves the practicality of the proposed technique.
Learning to ignore: rethinking attention in CNNs
Based on this idea, we propose to reformulate the attention mechanism in CNNs to learn to ignore instead of learning to attend.
Non-Linear Spectral Dimensionality Reduction Under Uncertainty
In this paper, we consider the problem of non-linear dimensionality reduction under uncertainty, both from a theoretical and algorithmic perspectives.
Reducing Redundancy in the Bottleneck Representation of the Autoencoders
We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
Efficient CNN with uncorrelated Bag of Features pooling
In this paper, we propose an approach that builds on top of BoF pooling to boost its efficiency by ensuring that the items of the learned dictionary are non-redundant.
WLD-Reg: A Data-dependent Within-layer Diversity Regularizer
At each optimization step, neurons at a given layer receive feedback from neurons belonging to higher layers of the hierarchy.
On Feature Diversity in Energy-based Models
Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches.
Convolutional autoencoder-based multimodal one-class classification
We show that such regularizers improve performance.
Newton Method-based Subspace Support Vector Data Description
The objective of S-SVDD is to map the original data to a subspace optimized for one-class classification, and the iterative optimization process of data mapping and description in S-SVDD relies on gradient descent.
Class-wise Generalization Error: an Information-Theoretic Analysis
Existing generalization theories of supervised learning typically take a holistic approach and provide bounds for the expected generalization over the whole data distribution, which implicitly assumes that the model generalizes similarly for all the classes.
Pixel-Wise Color Constancy via Smoothness Techniques in Multi-Illuminant Scenes
Motivated by this, we propose a novel multi-illuminant color constancy method, by learning pixel-wise illumination maps caused by multiple light sources.
