Object Detection Networks on Convolutional Feature Maps

Abstract

Most object detectors contain two important components: a feature extractor and an object classifier. The feature extractor has rapidly evolved with significant research efforts leading to better deep convolutional architectures. The object classifier, however, has not received much attention and many recent systems (like SPPnet and Fast/Faster R-CNN) use simple multi-layer perceptrons. This paper demonstrates that carefully designing deep networks for object classification is just as important. We experiment with region-wise classifier networks that use shared, region-independent convolutional features. We call them "Networks on Convolutional feature maps" (NoCs). We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier. We show by experiments that despite the effective ResNets and Faster R-CNN systems, the design of NoCs is an essential element for the 1st-place winning entries in ImageNet and MS COCO challenges 2015.

To appear in TPAMI; substantial re-writing over the original post at arXiv of April 2015. COCO competition results included

References in corpus (7)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Improving neural networks by preventing co-adaptation of feature detectors
• Going Deeper with Convolutions
• CNN: Single-label to Multi-label
• Convolutional Feature Masking for Joint Object and Stuff Segmentation
• Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
• Computational Baby Learning

Cited by in corpus (11)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Deep Residual Learning for Image Recognition
• Feature Pyramid Networks for Object Detection
• Action Recognition using Visual Attention
• Systematic evaluation of CNN advances on the ImageNet
• A Review of Object Detection Models based on Convolutional Neural Network
• Accelerating Very Deep Convolutional Networks for Classification and Detection
• Objectness Scoring and Detection Proposals in Forward-Looking Sonar Images with Convolutional Neural Networks
• Reversible Recursive Instance-level Object Segmentation
• Pushing the Limits of Deep CNNs for Pedestrian Detection
• Feature Selective Networks for Object Detection