An Analysis of Scale Invariance in Object Detection - SNIP

22 Nov 2017  ·  Bharat Singh, Larry S. Davis ·

An analysis of different techniques for recognizing and detecting objects under extreme scale variation is presented. Scale specific and scale invariant design of detectors are compared by training them with different configurations of input data. By evaluating the performance of different network architectures for classifying small objects on ImageNet, we show that CNNs are not robust to changes in scale. Based on this analysis, we propose to train and test detectors on the same scales of an image-pyramid. Since small and large objects are difficult to recognize at smaller and larger scales respectively, we present a novel training scheme called Scale Normalization for Image Pyramids (SNIP) which selectively back-propagates the gradients of object instances of different sizes as a function of the image scale. On the COCO dataset, our single model performance is 45.7% and an ensemble of 3 networks obtains an mAP of 48.3%. We use off-the-shelf ImageNet-1000 pre-trained models and only train with bounding box supervision. Our submission won the Best Student Entry in the COCO 2017 challenge. Code will be made available at \url{http://bit.ly/2yXVg4c}.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Object Detection COCO test-dev D-RFCN + SNIP (DPN-98 with flip, multi-scale) box mAP 45.7 # 132
AP50 67.3 # 61
AP75 51.1 # 65
APS 29.3 # 56
APM 48.8 # 69
APL 57.1 # 79
Hardware Burden None # 1
Operations per network pass None # 1
Object Detection COCO test-dev D-RFCN + SNIP (ResNet-101, multi-scale) box mAP 43.4 # 155
AP50 65.5 # 73
AP75 48.4 # 89
APS 27.2 # 72
APM 46.5 # 94
APL 54.9 # 103
Hardware Burden None # 1
Operations per network pass None # 1

Methods