Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction

by   Petru Soviany, et al.

There are mainly two types of state-of-the-art object detectors. On one hand, we have two-stage detectors, such as Faster R-CNN (Region-based Convolutional Neural Networks) or Mask R-CNN, that (i) use a Region Proposal Network to generate regions of interests in the first stage and (ii) send the region proposals down the pipeline for object classification and bounding-box regression. Such models reach the highest accuracy rates, but are typically slower. On the other hand, we have single-stage detectors, such as YOLO (You Only Look Once) and SSD (Singe Shot MultiBox Detector), that treat object detection as a simple regression problem which takes an input image and learns the class probabilities and bounding box coordinates. Such models reach lower accuracy rates, but are much faster than two-stage object detectors. In this paper, we propose to use an image difficulty predictor to achieve an optimal trade-off between accuracy and speed in object detection. The image difficulty predictor is applied on the test images to split them into easy versus hard images. Once separated, the easy images are sent to the faster single-stage detector, while the hard images are sent to the more accurate two-stage detector. Our experiments on PASCAL VOC 2007 show that using image difficulty compares favorably to a random split of the images. Our method is flexible, in that it allows to choose a desired threshold for splitting the images into easy versus hard.


Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection

Modern leading object detectors are either two-stage or one-stage networ...

Continuous Trade-off Optimization between Fast and Accurate Deep Face Detectors

Although deep neural networks offer better face detection results than s...

PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery

Non-maximum Suppression (NMS) is an essential postprocessing step in mod...

ALFA: Agglomerative Late Fusion Algorithm for Object Detection

We propose ALFA - a novel late fusion algorithm for object detection. AL...

Event Camera as Region Proposal Network

The human eye consists of two types of photoreceptors, rods and cones. R...

Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors

Object detection aims at high speed and accuracy simultaneously. However...

Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection

Complicated underwater environments bring new challenges to object detec...

Please sign up or login with your details

Forgot password? Click here to reset