Counting Everyday Objects in Everyday Scenes

We are interested in counting the number of instances of object classes in natural, everyday images. Previous counting approaches tackle the problem in restricted domains such as counting pedestrians in surveillance videos... Counts can also be estimated from outputs of other vision tasks like object detection. In this work, we build dedicated models for counting designed to tackle the large variance in counts, appearances, and scales of objects found in natural scenes. Our approach is inspired by the phenomenon of subitizing - the ability of humans to make quick assessments of counts given a perceptual signal, for small count values. Given a natural scene, we employ a divide and conquer strategy while incorporating context across the scene to adapt the subitizing idea to counting. Our approach offers consistent improvements over numerous baseline approaches for counting on the PASCAL VOC 2007 and COCO datasets. Subsequently, we study how counting can be used to improve object detection. We then show a proof of concept application of our counting methods to the task of Visual Question Answering, by studying the `how many?' questions in the VQA and COCO-QA datasets. read more

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Counting COCO count-test ens m-reIRMSE 0.18 # 1
m-reIRMSE-nz 0.81 # 1
mRMSE 0.36 # 3
mRMSE-nz 1.98 # 3
Object Counting COCO count-test Aso-sub-ft-3x3 m-reIRMSE 0.24 # 7
m-reIRMSE-nz 0.87 # 4
mRMSE 0.38 # 4
mRMSE-nz 2.08 # 4
Object Counting COCO count-test glance-ft-2L m-reIRMSE 0.23 # 6
m-reIRMSE-nz 0.91 # 5
mRMSE 0.42 # 6
mRMSE-nz 2.25 # 6
Object Counting COCO count-test Fast-RCNN m-reIRMSE 0.20 # 5
m-reIRMSE-nz 1.13 # 7
mRMSE 0.49 # 7
mRMSE-nz 2.78 # 7
Object Counting COCO count-test Seq-sub-ft-3x3 m-reIRMSE 0.18 # 1
m-reIRMSE-nz 0.82 # 2
mRMSE 0.35 # 2
mRMSE-nz 1.96 # 2
Object Counting Pascal VOC 2007 count-test glance-noft-2L m-reIRMSE-nz 0.73 # 2
m-relRMSE 0.27 # 1
mRMSE 0.50 # 1
mRMSE-nz 1.83 # 2
Object Counting Pascal VOC 2007 count-test Seq-sub-ft-3x3 m-reIRMSE-nz 0.68 # 4
m-relRMSE 0.22 # 3
mRMSE 0.43 # 3
mRMSE-nz 1.65 # 4
Object Counting Pascal VOC 2007 count-test ens m-reIRMSE-nz 0.65 # 5
m-relRMSE 0.20 # 4
mRMSE 0.42 # 4
mRMSE-nz 1.68 # 3
Object Counting Pascal VOC 2007 count-test Fast-RCNN m-reIRMSE-nz 0.85 # 1
m-relRMSE 0.26 # 2
mRMSE 0.50 # 1
mRMSE-nz 1.92 # 1

Methods


No methods listed for this paper. Add relevant methods here