AttentionNet: Aggregating Weak Directions for Accurate Object Detection
This provides a unified method for object detection that eliminates separate proposal and regression models, potentially benefiting computer vision applications, though it appears incremental as it builds on existing CNN-based detection approaches.
The paper tackles object detection by framing it as an iterative classification problem using a deep CNN called AttentionNet, which aggregates weak directions to converge on accurate bounding boxes, achieving state-of-the-art performance of 65% AP on PASCAL VOC 2007/12 for human detection with an 8-layer architecture.
We present a novel detection method using a deep convolutional neural network (CNN), named AttentionNet. We cast an object detection problem as an iterative classification problem, which is the most suitable form of a CNN. AttentionNet provides quantized weak directions pointing a target object and the ensemble of iterative predictions from AttentionNet converges to an accurate object boundary box. Since AttentionNet is a unified network for object detection, it detects objects without any separated models from the object proposal to the post bounding-box regression. We evaluate AttentionNet by a human detection task and achieve the state-of-the-art performance of 65% (AP) on PASCAL VOC 2007/2012 with an 8-layered architecture only.