DenseBox: Unifying Landmark Localization with End to End Object Detection
This provides a unified, efficient solution for object detection tasks, particularly for faces and cars, though it appears incremental as it builds on existing FCN approaches.
The authors tackled object detection by introducing DenseBox, a single fully convolutional neural network framework that directly predicts bounding boxes and class confidences, achieving state-of-the-art results on challenging datasets like MALF face detection and KITTI car detection.
How can a single fully convolutional neural network (FCN) perform on object detection? We introduce DenseBox, a unified end-to-end FCN framework that directly predicts bounding boxes and object class confidences through all locations and scales of an image. Our contribution is two-fold. First, we show that a single FCN, if designed and optimized carefully, can detect multiple different objects extremely accurately and efficiently. Second, we show that when incorporating with landmark localization during multi-task learning, DenseBox further improves object detection accuray. We present experimental results on public benchmark datasets including MALF face detection and KITTI car detection, that indicate our DenseBox is the state-of-the-art system for detecting challenging objects such as faces and cars.