Evaluating Zero-cost Active Learning for Object Detection
This work addresses the challenge of efficient labeling for object detection practitioners, but it is incremental as it focuses on evaluating existing zero-cost techniques rather than introducing new methods.
The paper tackles the problem of reducing labeling effort in object detection by evaluating zero-cost active learning methods, showing that effective score aggregation techniques are crucial for ranking images and improving selection.
Object detection requires substantial labeling effort for learning robust models. Active learning can reduce this effort by intelligently selecting relevant examples to be annotated. However, selecting these examples properly without introducing a sampling bias with a negative impact on the generalization performance is not straightforward and most active learning techniques can not hold their promises on real-world benchmarks. In our evaluation paper, we focus on active learning techniques without a computational overhead besides inference, something we refer to as zero-cost active learning. In particular, we show that a key ingredient is not only the score on a bounding box level but also the technique used for aggregating the scores for ranking images. We outline our experimental setup and also discuss practical considerations when using active learning for object detection.