Neural Information Processing Systems http://nips.cc/

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection. It is non-trivial because detection training typically needs ImageNetpre-training while NAS systems require accuracies on the target detection task as supervisory signals. Based on the technique of one-shot supernet, which contains all possible networks in the search space, we propose a framework for backbone search on object detection.

Neural Information Processing Systems http://nips.cc/

This paper proposes a neural network search strategy for object detection task. The problem is interesting and useful for many real applications. This paper gives a three stage solution that can search pre-training based detectors effectively and efficiently. Experiments on both COCO and VOC are conducted to show the effectiveness of the proposed solution, and detection based models are superior than classification based models. The idea of searching network structure for detection with pre-training stage is novel and interesting.

We believe this is a valuable contribution to NeurIPS. The main contribution on backbone search for object detection is of interest. This paper is clear, with interesting insights and applicability. We appreciate the extensive experimental evaluation. As areas of improvement, we strongly recommend the incorporation of the insights in the author feedback into the camera-ready version of the paper.

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection. It is non-trivial because detection training typically needs ImageNetpre-training while NAS systems require accuracies on the target detection task as supervisory signals. Based on the technique of one-shot supernet, which contains all possible networks in the search space, we propose a framework for backbone search on object detection.

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection. It is non-trivial because detection training typically needs ImageNetpre-training while NAS systems require accuracies on the target detection task as supervisory signals. Based on the technique of one-shot supernet, which contains all possible networks in the search space, we propose a framework for backbone search on object detection.