Influence Selection for Active Learning

TL;DR

This paper introduces Influence Selection for Active Learning (ISAL), a method that selects unlabeled samples based on their positive influence on model performance, reducing annotation costs across various datasets.

Contribution

The paper proposes UUIC, a task- and model-agnostic influence estimation method, and demonstrates ISAL's state-of-the-art performance in active learning tasks.

Findings

ISAL reduces annotation costs by at least 12-16% across datasets.

UUIC effectively estimates influence using model gradients.

ISAL achieves superior performance in multiple active learning scenarios.

Abstract

The existing active learning methods select the samples by evaluating the sample's uncertainty or its effect on the diversity of labeled datasets based on different task-specific or model-specific criteria. In this paper, we propose the Influence Selection for Active Learning(ISAL) which selects the unlabeled samples that can provide the most positive Influence on model performance. To obtain the Influence of the unlabeled sample in the active learning scenario, we design the Untrained Unlabeled sample Influence Calculation(UUIC) to estimate the unlabeled sample's expected gradient with which we calculate its Influence. To prove the effectiveness of UUIC, we provide both theoretical and experimental analyses. Since the UUIC just depends on the model gradients, which can be obtained easily from any neural network, our active learning algorithm is task-agnostic and model-agnostic. ISAL achieves state-of-the-art performance in different active learning settings for different tasks with different datasets. Compared with previous methods, our method decreases the annotation cost at least by 12%, 13% and 16% on CIFAR10, VOC2012 and COCO, respectively.