AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects
This addresses the challenge of detecting small objects in computer vision, which are often missed by existing models, offering significant improvements in speed and recall for applications like object detection.
The paper tackles the problem of generating class-agnostic object proposals efficiently, with a focus on detecting small objects, resulting in a system that is 33% faster than state-of-the-art and improves average recall for small objects by about 53%.
We propose a novel approach for class-agnostic object proposal generation, which is efficient and especially well-suited to detect small objects. Efficiency is achieved by scale-specific objectness attention maps which focus the processing on promising parts of the image and reduce the amount of sampled windows strongly. This leads to a system, which is $33\%$ faster than the state-of-the-art and clearly outperforming state-of-the-art in terms of average recall. Secondly, we add a module for detecting small objects, which are often missed by recent models. We show that this module improves the average recall for small objects by about $53\%$.