Deep learning for class-generic object detection
arXiv:1312.6885v14 citations
Originality Synthesis-oriented
AI Analysis
This work addresses the problem of detecting objects without class-specific labels for computer vision applications, but it appears incremental.
The paper tackled class-generic object detection using deep neural networks, achieving a 1% performance increase on ImageNet recognition by leveraging bounding box labels.
We investigate the use of deep neural networks for the novel task of class generic object detection. We show that neural networks originally designed for image recognition can be trained to detect objects within images, regardless of their class, including objects for which no bounding box labels have been provided. In addition, we show that bounding box labels yield a 1% performance increase on the ImageNet recognition challenge.