Log In Sign Up

What makes for effective detection proposals?

by   Jan Hosang, et al.

Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the popularity and widespread use of detection proposals, it is unclear which trade-offs are made when using them during object detection. We provide an in-depth analysis of twelve proposal methods along with four baselines regarding proposal repeatability, ground truth annotation recall on PASCAL, ImageNet, and MS COCO, and their impact on DPM, R-CNN, and Fast R-CNN detection performance. Our analysis shows that for object detection improving proposal localisation accuracy is as important as improving recall. We introduce a novel metric, the average recall (AR), which rewards both high recall and good localisation and correlates surprisingly well with detection performance. Our findings show common strengths and weaknesses of existing methods, and provide insights and metrics for selecting and tuning proposal methods.


page 1

page 5

page 7

page 10


How good are detection proposals, really?

Current top performing Pascal VOC object detectors employ detection prop...

What leads to generalization of object proposals?

Object proposal generation is often the first step in many detection mod...

Diagnosing State-Of-The-Art Object Proposal Methods

Object proposal has become a popular paradigm to replace exhaustive slid...

Scalable, High-Quality Object Detection

Current high-quality object detection approaches use the scheme of salie...

BIHL:A Fast and High Performance Object Proposals based on Binarized HL Frequency

In recent years, the use of object proposal as a preprocessing step for ...

ME R-CNN: Multi-Expert R-CNN for Object Detection

We introduce Multi-Expert Region-based CNN (ME R-CNN) which is equipped ...

DeepBox: Learning Objectness with Convolutional Networks

Existing object proposal approaches use primarily bottom-up cues to rank...