DeepBox: Learning Objectness with Convolutional Networks

TL;DR

DeepBox employs a CNN-based approach to rerank object proposals, significantly enhancing recall and detection accuracy while maintaining high speed, thus advancing objectness evaluation in computer vision.

Contribution

The paper introduces DeepBox, a CNN-based reranking framework that improves object proposal ranking efficiency and accuracy over traditional bottom-up methods.

Findings

Achieves the same recall with 500 proposals as bottom-up methods with 2000.

Generalizes well to unseen categories, improving detection mAP by 4.5 points.

Runs at 260 ms per image, suitable for real-time applications.

Abstract

Existing object proposal approaches use primarily bottom-up cues to rank proposals, while we believe that objectness is in fact a high level construct. We argue for a data-driven, semantic approach for ranking object proposals. Our framework, which we call DeepBox, uses convolutional neural networks (CNNs) to rerank proposals from a bottom-up method. We use a novel four-layer CNN architecture that is as good as much larger networks on the task of evaluating objectness while being much faster. We show that DeepBox significantly improves over the bottom-up ranking, achieving the same recall with 500 proposals as achieved by bottom-up methods with 2000. This improvement generalizes to categories the CNN has never seen before and leads to a 4.5-point gain in detection mAP. Our implementation achieves this performance while running at 260 ms per image.