Dissimilarity Coefficient based Weakly Supervised Object Detection

CVPR 2019  ·  Aditya Arun, C. V. Jawahar, M. Pawan Kumar ·

We consider the problem of weakly supervised object detection, where the training samples are annotated using only image-level labels that indicate the presence or absence of an object category. In order to model the uncertainty in the location of the objects, we employ a dissimilarity coefficient based probabilistic learning objective. The learning objective minimizes the difference between an annotation agnostic prediction distribution and an annotation aware conditional distribution. The main computational challenge is the complex nature of the conditional distribution, which consists of terms over hundreds or thousands of variables. The complexity of the conditional distribution rules out the possibility of explicitly modeling it. Instead, we exploit the fact that deep learning frameworks rely on stochastic optimization. This allows us to use a state of the art discrete generative model that can provide annotation consistent samples from the conditional distribution. Extensive experiments on PASCAL VOC 2007 and 2012 data sets demonstrate the efficacy of our proposed approach.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Weakly Supervised Object Detection PASCAL VOC 2007 Pred Net (Ens) MAP 53.6 # 6
Weakly Supervised Object Detection PASCAL VOC 2012 test Pred Net (Ens) MAP 49.5 # 5


No methods listed for this paper. Add relevant methods here