SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

Abstract

Convolutional neural networks typically encode an input image into a series of intermediate features with decreasing resolutions. While this structure is suited to classification tasks, it does not perform well for tasks requiring simultaneous recognition and localization (e.g., object detection). The encoder-decoder architectures are proposed to resolve this by applying a decoder network onto a backbone model designed for classification tasks. In this paper, we argue encoder-decoder architecture is ineffective in generating strong multi-scale features because of the scale-decreased backbone. We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search. Using similar building blocks, SpineNet models outperform ResNet-FPN models by ~3% AP at various scales while using 10-20% fewer FLOPs. In particular, SpineNet-190 achieves 52.5% AP with a MaskR-CNN detector and achieves 52.1% AP with a RetinaNet detector on COCO for a single model without test-time augmentation, significantly outperforms prior art of detectors. SpineNet can transfer to classification tasks, achieving 5% top-1 accuracy improvement on a challenging iNaturalist fine-grained dataset. Code is at: https://github.com/tensorflow/tpu/tree/master/models/official/detection.

arXiv commentCVPR 2020

References in corpus (7)

• YOLOv3: An Incremental Improvement
• Neural Architecture Search with Reinforcement Learning
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• DARTS: Differentiable Architecture Search
• Searching for Activation Functions
• DropBlock: A regularization method for convolutional networks
• Deep High-Resolution Representation Learning for Visual Recognition

Cited by in corpus (8)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• A Simple Semi-Supervised Learning Framework for Object Detection
• DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
• Scaled-YOLOv4: Scaling Cross Stage Partial Network
• Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
• Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
• Uniform Priors for Data-Efficient Transfer
• Efficient Scale-Permuted Backbone with Learned Resource Distribution