Object Detection Networks on Convolutional Feature Maps

by   Shaoqing Ren, et al.

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.


page 2

page 5


Feature Pyramid Networks for Object Detection

Feature pyramids are a basic component in recognition systems for detect...

Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection

R-CNN style methods are sorts of the state-of-the-art object detection m...

Do More Dropouts in Pool5 Feature Maps for Better Object Detection

Deep Convolutional Neural Networks (CNNs) have gained great success in i...

Learning from Adversarial Features for Few-Shot Classification

Many recent few-shot learning methods concentrate on designing novel mod...

CondenseNet V2: Sparse Feature Reactivation for Deep Networks

Reusing features in deep networks through dense connectivity is an effec...

Recognition Of Surface Defects On Steel Sheet Using Transfer Learning

Automatic defect recognition is one of the research hotspots in steel pr...

Half-CNN: A General Framework for Whole-Image Regression

The Convolutional Neural Network (CNN) has achieved great success in ima...

Please sign up or login with your details

Forgot password? Click here to reset