Recurrent Scale Approximation for Object Detection in CNN

by   Yu Liu, et al.

Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multi-scale object detection, which has the bottleneck of computational cost in practice. To address this, we devise a recurrent scale approximation (RSA) to compute feature map once only, and only through this map can we approximate the rest maps on other levels. At the core of RSA is the recursive rolling out mechanism: given an initial map on a particular scale, it generates the prediction on a smaller scale that is half the size of input. To further increase efficiency and accuracy, we (a): design a scale-forecast network to globally predict potential scales in the image since there is no need to compute maps on all levels of the pyramid. (b): propose a landmark retracing network (LRN) to retrace back locations of the regressed landmarks and generate a confidence score for each landmark; LRN can effectively alleviate false positives due to the accumulated error in RSA. The whole system could be trained end-to-end in a unified CNN framework. Experiments demonstrate that our proposed algorithm is superior against state-of-the-arts on face detection benchmarks and achieves comparable results for generic proposal generation. The source code of RSA is available at


A Fast Face Detection Method via Convolutional Neural Network

Current face or object detection methods via convolutional neural networ...

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

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

Scale Optimization for Full-Image-CNN Vehicle Detection

Many state-of-the-art general object detection methods make use of share...

Feature Agglomeration Networks for Single Stage Face Detection

Recent years have witnessed promising results of face detection using de...

Deep Regionlets for Object Detection

A key challenge in generic object detection is being to handle large var...

Multi-Scale Gradual Integration CNN for False Positive Reduction in Pulmonary Nodule Detection

Lung cancer is a global and dangerous disease, and its early detection i...

Please sign up or login with your details

Forgot password? Click here to reset