How to train your draGAN: A task oriented solution to imbalanced
classification
- URL: http://arxiv.org/abs/2211.10065v1
- Date: Fri, 18 Nov 2022 07:37:34 GMT
- Title: How to train your draGAN: A task oriented solution to imbalanced
classification
- Authors: Leon O. Guertler, Andri Ashfahani, Anh Tuan Luu
- Abstract summary: This paper proposes a unique, performance-oriented, data-generating strategy that utilizes a new architecture, coined draGAN.
The samples are generated with the objective of optimizing the classification model's performance, rather than similarity to the real data.
Empirically we show the superiority of draGAN, but also highlight some of its shortcomings.
- Score: 15.893327571516016
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The long-standing challenge of building effective classification models for
small and imbalanced datasets has seen little improvement since the creation of
the Synthetic Minority Over-sampling Technique (SMOTE) over 20 years ago.
Though GAN based models seem promising, there has been a lack of purpose built
architectures for solving the aforementioned problem, as most previous studies
focus on applying already existing models. This paper proposes a unique,
performance-oriented, data-generating strategy that utilizes a new
architecture, coined draGAN, to generate both minority and majority samples.
The samples are generated with the objective of optimizing the classification
model's performance, rather than similarity to the real data. We benchmark our
approach against state-of-the-art methods from the SMOTE family and competitive
GAN based approaches on 94 tabular datasets with varying degrees of imbalance
and linearity. Empirically we show the superiority of draGAN, but also
highlight some of its shortcomings. All code is available on:
https://github.com/LeonGuertler/draGAN.
Related papers
- Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild [84.57103623507082]
This paper introduces Model-GLUE, a holistic Large Language Models scaling guideline.
Our work starts with a benchmarking of existing LLM scaling techniques, especially selective merging, and variants of mixture.
Our methodology involves the clustering of mergeable models and optimal merging strategy selection, and the integration of clusters through a model mixture.
arXiv Detail & Related papers (2024-10-07T15:55:55Z) - FissionFusion: Fast Geometric Generation and Hierarchical Souping for Medical Image Analysis [0.7751705157998379]
The scarcity of well-annotated medical datasets requires leveraging transfer learning from broader datasets like ImageNet or pre-trained models like CLIP.
Model soups averages multiple fine-tuned models aiming to improve performance on In-Domain (ID) tasks and enhance robustness against Out-of-Distribution (OOD) datasets.
We propose a hierarchical merging approach that involves local and global aggregation of models at various levels.
arXiv Detail & Related papers (2024-03-20T06:48:48Z) - Self-Supervised Dataset Distillation for Transfer Learning [77.4714995131992]
We propose a novel problem of distilling an unlabeled dataset into a set of small synthetic samples for efficient self-supervised learning (SSL)
We first prove that a gradient of synthetic samples with respect to a SSL objective in naive bilevel optimization is textitbiased due to randomness originating from data augmentations or masking.
We empirically validate the effectiveness of our method on various applications involving transfer learning.
arXiv Detail & Related papers (2023-10-10T10:48:52Z) - Target-Aware Generative Augmentations for Single-Shot Adaptation [21.840653627684855]
We propose a new approach to adapting models from a source domain to a target domain.
SiSTA fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data.
We find that SiSTA produces significantly improved generalization over existing baselines in face detection and multi-class object recognition.
arXiv Detail & Related papers (2023-05-22T17:46:26Z) - Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
We make empirical studies of state-of-the-art UniDA methods using foundation models.
We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models.
Although simple, our method outperforms previous approaches in most benchmark tasks.
arXiv Detail & Related papers (2023-05-18T16:28:29Z) - Data Summarization via Bilevel Optimization [48.89977988203108]
A simple yet powerful approach is to operate on small subsets of data.
In this work, we propose a generic coreset framework that formulates the coreset selection as a cardinality-constrained bilevel optimization problem.
arXiv Detail & Related papers (2021-09-26T09:08:38Z) - Enhanced Balancing GAN: Minority-class Image Generation [0.7310043452300734]
Generative adversarial networks (GANs) are one of the most powerful generative models.
Balancing GAN (BAGAN) is proposed to mitigate this problem, but it is unstable when images in different classes look similar.
In this work, we propose a supervised autoencoder with an intermediate embedding model to disperse the labeled latent vectors.
Our proposed model overcomes the unstable issue in original BAGAN and converges faster to high quality generations.
arXiv Detail & Related papers (2020-10-31T05:03:47Z) - Conditional Wasserstein GAN-based Oversampling of Tabular Data for
Imbalanced Learning [10.051309746913512]
We propose an oversampling method based on a conditional Wasserstein GAN.
We benchmark our method against standard oversampling methods and the imbalanced baseline on seven real-world datasets.
arXiv Detail & Related papers (2020-08-20T20:33:56Z) - Prior Guided Feature Enrichment Network for Few-Shot Segmentation [64.91560451900125]
State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results.
Few-shot segmentation is proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples.
Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information.
arXiv Detail & Related papers (2020-08-04T10:41:32Z) - The Devil is in Classification: A Simple Framework for Long-tail Object
Detection and Instance Segmentation [93.17367076148348]
We investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset.
We unveil that a major cause is the inaccurate classification of object proposals.
We propose a simple calibration framework to more effectively alleviate classification head bias with a bi-level class balanced sampling approach.
arXiv Detail & Related papers (2020-07-23T12:49:07Z)
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.