Search Results for author: Bartosz Krawczyk

Found 16 papers, 10 papers with code

Class-Incremental Mixture of Gaussians for Deep Continual Learning

no code implementations9 Jul 2023 Lukasz Korycki, Bartosz Krawczyk

Continual learning models for stationary data focus on learning and retaining concepts coming to them in a sequential manner.

Continual Learning Image Classification

Interpretable ML for Imbalanced Data

1 code implementation15 Dec 2022 Damien A. Dablain, Colin Bellinger, Bartosz Krawczyk, David W. Aha, Nitesh V. Chawla

We propose a set of techniques that can be used by both deep learning model users to identify, visualize and understand class prototypes, sub-concepts and outlier instances; and by imbalanced learning algorithm developers to detect features and class exemplars that are key to model performance.

Autonomous Driving Binary Classification +2

Efficient Augmentation for Imbalanced Deep Learning

1 code implementation13 Jul 2022 Damien Dablain, Colin Bellinger, Bartosz Krawczyk, Nitesh Chawla

We empirically study a convolutional neural network's internal representation of imbalanced image data and measure the generalization gap between a model's feature embeddings in the training and test sets, showing that the gap is wider for minority classes.

Data Augmentation

Towards A Holistic View of Bias in Machine Learning: Bridging Algorithmic Fairness and Imbalanced Learning

1 code implementation13 Jul 2022 Damien Dablain, Bartosz Krawczyk, Nitesh Chawla

A key element in achieving algorithmic fairness with respect to protected groups is the simultaneous reduction of class and protected group imbalance in the underlying training data, which facilitates increases in both model accuracy and fairness.

Fairness

A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework

1 code implementation7 Apr 2022 Gabriel Aguiar, Bartosz Krawczyk, Alberto Cano

This leads to a large-scale experimental study comparing state-of-the-art classifiers in the data stream mining domain.

On the combined effect of class imbalance and concept complexity in deep learning

1 code implementation29 Jul 2021 Kushankur Ghosh, Colin Bellinger, Roberto Corizzo, Bartosz Krawczyk, Nathalie Japkowicz

Structural concept complexity, class overlap, and data scarcity are some of the most important factors influencing the performance of classifiers under class imbalance conditions.

Imbalanced Big Data Oversampling: Taxonomy, Algorithms, Software, Guidelines and Future Directions

1 code implementation24 Jul 2021 William C. Sleeman IV, Bartosz Krawczyk

This allows us to gain insight into the usefulness of specific components of oversampling algorithms for big data, as well as formulate guidelines and recommendations for designing future resampling approaches for massive imbalanced data.

DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data

1 code implementation5 May 2021 Damien Dablain, Bartosz Krawczyk, Nitesh V. Chawla

An important advantage of DeepSMOTE over GAN-based oversampling is that DeepSMOTE does not require a discriminator, and it generates high-quality artificial images that are both information-rich and suitable for visual inspection.

Class-Incremental Experience Replay for Continual Learning under Concept Drift

1 code implementation24 Apr 2021 Łukasz Korycki, Bartosz Krawczyk

Data stream mining focuses on adaptation to concept drift and discarding outdated information, assuming that only the most recent data is relevant.

Continual Learning valid

Concept Drift Detection from Multi-Class Imbalanced Data Streams

no code implementations20 Apr 2021 Łukasz Korycki, Bartosz Krawczyk

Due to its trainable nature, it is capable of following changes in a stream and evolving class roles, as well as it can deal with local concept drift occurring in minority classes.

Continual Learning

Adaptive Deep Forest for Online Learning from Drifting Data Streams

1 code implementation14 Oct 2020 Łukasz Korycki, Bartosz Krawczyk

The conducted experiments show that the deep forest approach can be effectively transformed into an online algorithm, forming a model that outperforms all state-of-the-art shallow adaptive classifiers, especially for high-dimensional complex streams.

Instance exploitation for learning temporary concepts from sparsely labeled drifting data streams

1 code implementation20 Sep 2020 Łukasz Korycki, Bartosz Krawczyk

Continual learning from streaming data sources becomes more and more popular due to the increasing number of online tools and systems.

Continual Learning

Adversarial Concept Drift Detection under Poisoning Attacks for Robust Data Stream Mining

no code implementations20 Sep 2020 Łukasz Korycki, Bartosz Krawczyk

In this paper, we propose a framework for robust concept drift detection in the presence of adversarial and poisoning attacks.

Combined Cleaning and Resampling Algorithm for Multi-Class Imbalanced Data with Label Noise

no code implementations7 Apr 2020 Michał Koziarski, Michał Woźniak, Bartosz Krawczyk

The proposed method utilizes an energy-based approach to modeling the regions suitable for oversampling, less affected by small disjuncts and outliers than SMOTE.

Binary Classification General Classification

Towards Highly Accurate Coral Texture Images Classification Using Deep Convolutional Neural Networks and Data Augmentation

no code implementations27 Mar 2018 Anabel Gómez-Ríos, Siham Tabik, Julián Luengo, ASM Shihavuddin, Bartosz Krawczyk, Francisco Herrera

The recognition of coral species based on underwater texture images pose a significant difficulty for machine learning algorithms, due to the three following challenges embedded in the nature of this data: 1) datasets do not include information about the global structure of the coral; 2) several species of coral have very similar characteristics; and 3) defining the spatial borders between classes is difficult as many corals tend to appear together in groups.

Data Augmentation General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.