Ctrl-A: Control-Driven Online Data Augmentation

📅 2026-03-23
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work proposes an online data augmentation method grounded in control theory to address the limitations of handcrafted, non-adaptive augmentation strategies commonly used in visual recognition tasks. By constructing a control-loop architecture that leverages operation-specific response curves, the approach dynamically adjusts the intensity distribution of individual augmentation operations during training—eliminating the need for preset parameters and automatically suppressing augmentations detrimental to model performance. Experimental results demonstrate that, when applied with WideResNet-28-10 on CIFAR-10, CIFAR-100, and SVHN-core, the method achieves performance on par with state-of-the-art data augmentation techniques, offering a task-adaptive and fully automated dynamic augmentation mechanism without manual intervention.

Technology Category

Application Category

📝 Abstract
We introduce ControlAugment (Ctrl-A), an automated data augmentation algorithm for image-vision tasks, which incorporates principles from control theory for online adjustment of augmentation strength distributions during model training. Ctrl-A eliminates the need for initialization of individual augmentation strengths. Instead, augmentation strength distributions are dynamically, and individually, adapted during training based on a control-loop architecture and what we define as relative operation response curves. Using an operation-dependent update procedure provides Ctrl-A with the potential to suppress augmentation styles that negatively impact model performance, alleviating the need for manually engineering augmentation policies for new image-vision tasks. Experiments on the CIFAR-10, CIFAR-100, and SVHN-core benchmark datasets using the common WideResNet-28-10 architecture demonstrate that Ctrl-A is highly competitive with existing state-of-the-art data augmentation strategies.
Problem

Research questions and friction points this paper is trying to address.

data augmentation
image-vision tasks
augmentation strength
online adjustment
manual policy engineering
Innovation

Methods, ideas, or system contributions that make the work stand out.

data augmentation
control theory
online adaptation
image-vision tasks
automated machine learning
💼 Related Jobs
No related jobs found.
J
Jesper B. Christensen
Danish Fundamental Metrology (DFM), Kogle Allé 5, DK-2970 Hørsholm, Denmark
C
Ciaran Bench
National Physical Laboratory (NPL), Teddington, United Kingdom
S
Spencer A. Thomas
National Physical Laboratory (NPL), Teddington, United Kingdom
H
Hüsnü Aslan
Danish Fundamental Metrology (DFM), Kogle Allé 5, DK-2970 Hørsholm, Denmark
D
David Balslev-Harder
Danish Fundamental Metrology (DFM), Kogle Allé 5, DK-2970 Hørsholm, Denmark
N
Nadia A. S. Smith
TÜV SÜD, Warrington, United Kingdom; Royal Surrey NHS Foundation Trust, Guildford, United Kingdom
A
Alessandra Manzin
Istituto Nazionale di Ricerca Metrologica (INRiM), Strada delle Cacce, 91, 10135 Torino, Italy