CALICO: Confident Active Learning with Integrated Calibration

TL;DR

CALICO introduces a novel active learning framework that self-calibrates confidence estimates during training by jointly training a classifier and an energy-based model, enhancing sample selection and classification accuracy in data-scarce, safety-critical applications.

Contribution

It presents a new active learning approach that integrates calibration into the training process using energy-based models, eliminating the need for extra labeled data.

Findings

Improved classification performance with fewer labeled samples.

Enhanced calibration stability depending on class distribution.

Joint training of classifier and energy model benefits active learning.

Abstract

The growing use of deep learning in safety-critical applications, such as medical imaging, has raised concerns about limited labeled data, where this demand is amplified as model complexity increases, posing hurdles for domain experts to annotate data. In response to this, active learning (AL) is used to efficiently train models with limited annotation costs. In the context of deep neural networks (DNNs), AL often uses confidence or probability outputs as a score for selecting the most informative samples. However, modern DNNs exhibit unreliable confidence outputs, making calibration essential. We propose an AL framework that self-calibrates the confidence used for sample selection during the training process, referred to as Confident Active Learning with Integrated CalibratiOn (CALICO). CALICO incorporates the joint training of a classifier and an energy-based model, instead of the standard softmax-based classifier. This approach allows for simultaneous estimation of the input data distribution and the class probabilities during training, improving calibration without needing an additional labeled dataset. Experimental results showcase improved classification performance compared to a softmax-based classifier with fewer labeled samples. Furthermore, the calibration stability of the model is observed to depend on the prior class distribution of the data.