Augmentation Pipeline

Data augmentation pipelines are designed to enhance the performance of machine learning models, particularly when training data is limited or imbalanced. Current research focuses on optimizing these pipelines through automated search algorithms, leveraging generative models like GANs and Stable Diffusion to synthesize new data, and employing techniques like counterfactual learning to create more robust representations. These advancements are significantly impacting various fields, improving the accuracy and efficiency of models in medical image analysis, natural language processing, and other applications where data scarcity is a major challenge. The development of efficient and effective augmentation strategies is crucial for advancing the capabilities of machine learning across diverse domains.

Papers

October 17, 2024

Augmentation Policy Generation for Image Classification Using Large Language Models
Ant Duru, Alptekin Temizel
Large Language Model Language Model Deep Learning Model Image Classification Data Augmentation Method Augmentation Pipeline Augmentation Policy

September 15, 2024

Enhancing Lesion Segmentation in PET/CT Imaging with Deep Learning and Advanced Data Preprocessing Techniques
Jiayi Liu, Qiaoyi Xue, Youdan Feng, Tianming Xu, Kaixin Shen, Chuyun Shen, Yuhang Shi
Deep Learning Computed Tomography Whole Body Data Preprocessing Preprocessing Method PET Dog Augmentation Pipeline

June 13, 2024

Enhancing Psychotherapy Counseling: A Data Augmentation Pipeline Leveraging Large Language Models for Counseling Conversations
Jun-Woo Kim, Ji-Eun Han, Jun-Seok Koh, Hyeon-Tae Seo, Du-Seong Chang
Augmentation Pipeline Psychotherapy Model Counseling Conversation

May 9, 2024

Continuous max-flow augmentation of self-supervised few-shot learning on SPECT left ventricles
Ádám István Szűcs, Béla Kári, Oszkár Pártos
Augmentation Pipeline Left Ventricular

March 25, 2024

MEDDAP: Medical Dataset Enhancement via Diversified Augmentation Pipeline
Yasamin Medghalchi, Niloufar Zakariaei, Arman Rahmim, Ilker Hacihaliloglu
Medical Image Low Rank Adaptation Ultrasound Image Augmentation Pipeline Dataset Diversity Dataset Refinement

March 14, 2024

Counterfactual contrastive learning: robust representations via causal image synthesis
Melanie Roschewitz, Fabio De Sousa Ribeiro, Tian Xia, Galvin Khara, Ben Glocker
Robust Representation Counterfactual Inference Counterfactual Image Contrastive Pretraining Augmentation Pipeline Counterfactual Contrastive

March 12, 2024

Efficient Post-Training Augmentation for Adaptive Inference in Heterogeneous and Distributed IoT Environments
Max Sponner, Lorenzo Servadei, Bernd Waschneck, Robert Wille, Akash Kumar
Neural Network Deep Learning Application Internet of Thing Environment Post Training Heterogeneous Setting Augmentation Pipeline Adaptive Inference SNN Architecture Early Exit Neural Network

March 8, 2024

A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GAN
Cristiana Tiago, Andrew Gilbert, Ahmed S. Beela, Svein Arne Aase, Sten Roar Snare, Jurica Sprem
Generative Adversarial Network Synthetic Image Synthesized Image Echocardiography Dataset Augmentation Pipeline

January 8, 2024

NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation
Casimir Feldmann, Niall Siegenheim, Nikolas Hars, Lovro Rabuzin, Mert Ertugrul, Luca Wolfart, Marc Pollefeys, Zuria Bauer, Martin R. Oswald
Autonomous Driving Monocular Depth Estimation Self Augmentation Synthetic RGB Augmentation Pipeline NeRF Transformation

December 9, 2023

Augmenty: A Python Library for Structured Text Augmentation
Kenneth Enevoldsen
Python Library Text Augmentation Augmentation Pipeline Language Augmentation

October 5, 2023

Beyond Random Augmentations: Pretraining with Hard Views
Fabio Ferreira, Ivo Rapant, Jörg K. H. Franke, Frank Hutter
Pre Trained Image Augmentation Augmentation Pipeline View Generation Dissimilar View

June 14, 2023

A Simple Data Augmentation for Feature Distribution Skewed Federated Learning
Yunlu Yan, Lei Zhu
Data Augmentation Feature Distribution Effective Data Augmentation Augmentation Pipeline

May 25, 2023

Dynamic Data Augmentation via MCTS for Prostate MRI Segmentation
Xinyue Xu, Yuhan Hsi, Haonan Wang, Xiaomeng Li
Data Augmentation Prostate Segmentation Effective Augmentation Augmentation Pipeline Minimax McTs State of the Art Data

February 28, 2023

An Effective Crop-Paste Pipeline for Few-shot Object Detection
Shaobo Lin, Kun Wang, Xingyu Zeng, Rui Zhao
Ground Truth Object Detector Shot Object Detection Augmentation Pipeline Image Structure End to End Pipeline

August 30, 2022

Augraphy: A Data Augmentation Library for Document Images
Alexander Groleau, Kok Wei Chee, Stefan Larson, Samay Maini, Jonathan Boarman
Data Augmentation Augmented Reality Image Modeling Document Image Augmentation Pipeline

August 25, 2022

TEP-GNN: Accurate Execution Time Prediction of Functional Tests using Graph Neural Networks
Hazem Peter Samoaa, Antonio Longa, Mazen Mohamad, Morteza Haghir Chehreghani, Philipp Leitner
Graph Neural Network Graph Based Performance Prediction Timing Analysis Augmentation Pipeline

August 3, 2022

Augmentation Learning for Semi-Supervised Classification
Tim Frommknecht, Pedro Alves Zipf, Quanfu Fan, Nina Shvetsova, Hilde Kuehne
Data Augmentation Semi Supervised Learning Semi Supervised Supervised ImageNet Semi Supervised Classification Augmentation Pipeline Data Augmentation Policy

May 24, 2022

Multi-Augmentation for Efficient Visual Representation Learning for Self-supervised Pre-training
Van-Nhiem Tran, Chi-En Huang, Shen-Hsuan Liu, Kai-Lin Yang, Timothy Ko, Yung-Hui Li
Self Supervised Learning Representation Learning Self Supervised Representation Learning Self Supervised Pre Training Augmentation Pipeline Augmentation Composition

March 11, 2022

Deep AutoAugment
Yu Zheng, Zhi Zhang, Shen Yan, Mi Zhang
Data Augmentation Strategy Augmentation Pipeline Data Augmentation Policy

February 7, 2022

Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study
Daniel Tompkins, Kshitiz Kumar, Jian Wu
Data Augmentation Knowledge Transfer MAESTRO Dataset Event Detection Small Datasets Ablation Study Augmentation Pipeline Xception Model

Augmentation Pipeline

Papers

Augmentation Policy Generation for Image Classification Using Large Language Models

Enhancing Lesion Segmentation in PET/CT Imaging with Deep Learning and Advanced Data Preprocessing Techniques

Enhancing Psychotherapy Counseling: A Data Augmentation Pipeline Leveraging Large Language Models for Counseling Conversations

Continuous max-flow augmentation of self-supervised few-shot learning on SPECT left ventricles

MEDDAP: Medical Dataset Enhancement via Diversified Augmentation Pipeline

Counterfactual contrastive learning: robust representations via causal image synthesis

Efficient Post-Training Augmentation for Adaptive Inference in Heterogeneous and Distributed IoT Environments

A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GAN

NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation

Augmenty: A Python Library for Structured Text Augmentation

Beyond Random Augmentations: Pretraining with Hard Views

A Simple Data Augmentation for Feature Distribution Skewed Federated Learning

Dynamic Data Augmentation via MCTS for Prostate MRI Segmentation

An Effective Crop-Paste Pipeline for Few-shot Object Detection

Augraphy: A Data Augmentation Library for Document Images

TEP-GNN: Accurate Execution Time Prediction of Functional Tests using Graph Neural Networks

Augmentation Learning for Semi-Supervised Classification

Multi-Augmentation for Efficient Visual Representation Learning for Self-supervised Pre-training

Deep AutoAugment

Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study