Object Proposal Generation using Two-Stage Cascade SVMs

TL;DR

This paper introduces a two-stage cascade SVM approach for object proposal generation that achieves high recall and efficiency, suitable for both class-specific and generic detection tasks.

Contribution

It presents a novel two-stage cascade SVM method with scale/aspect-ratio quantization and regularizer analysis, improving object proposal speed and accuracy.

Findings

Achieves state-of-the-art recall on VOC2007 dataset.

Demonstrates high computational efficiency in proposal generation.

Effective for both class-specific and generic object proposals.

Abstract

Object proposal algorithms have shown great promise as a first step for object recognition and detection. Good object proposal generation algorithms require high object recall rate as well as low computational cost, because generating object proposals is usually utilized as a preprocessing step. The problem of how to accelerate the object proposal generation and evaluation process without decreasing recall is thus of great interest. In this paper, we propose a new object proposal generation method using two-stage cascade SVMs, where in the first stage linear filters are learned for predefined quantized scales/aspect-ratios independently, and in the second stage a global linear classifier is learned across all the quantized scales/aspect-ratios for calibration, so that all the proposals can be compared properly. The proposals with highest scores are our final output. Specifically, we explain our scale/aspect-ratio quantization scheme, and investigate the effects of combinations of $\ell_1$ and $\ell_2$ regularizers in cascade SVMs with/without ranking constraints in learning. Comprehensive experiments on VOC2007 dataset are conducted, and our results achieve the state-of-the-art performance with high object recall rate and high computational efficiency. Besides, our method has been demonstrated to be suitable for not only class-specific but also generic object proposal generation.