Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks
This work addresses the challenge of efficiently leveraging past knowledge for future tasks in image classification, offering a novel approach that reduces human annotation costs.
The paper tackles the problem of reusing existing datasets for new, unrelated image classification tasks by framing it as an active learning problem, using zero-shot classifiers to guide sample selection and achieving state-of-the-art results with minimal labeling effort in experiments on two challenging datasets.
How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a first contribution to answer this question in the context of image classification. We frame this quest as an active learning problem and use zero-shot classifiers to guide the learning process by linking the new task to the existing classifiers. By revisiting the dual formulation of adaptive SVM, we reveal two basic conditions to choose greedily only the most relevant samples to be annotated. On this basis we propose an effective active learning algorithm which learns the best possible target classification model with minimum human labeling effort. Extensive experiments on two challenging datasets show the value of our approach compared to the state-of-the-art active learning methodologies, as well as its potential to reuse past datasets with minimal effort for future tasks.