Dissimilarity Coefficient based Weakly Supervised Object Detection

11/25/2018
by   Aditya Arun, et al.
0

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.

READ FULL TEXT

page 4

page 6

page 14

research
07/18/2020

Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances

Recent approaches for weakly supervised instance segmentations depend on...
research
06/18/2012

Modeling Latent Variable Uncertainty for Loss-based Learning

We consider the problem of parameter estimation using weakly supervised ...
research
05/02/2017

Transfer Learning by Ranking for Weakly Supervised Object Annotation

Most existing approaches to training object detectors rely on fully supe...
research
06/26/2017

Few-shot Object Detection

In this paper, we study object detection using a large pool of unlabeled...
research
07/05/2022

ORF-Net: Deep Omni-supervised Rib Fracture Detection from Chest CT Scans

Most of the existing object detection works are based on the bounding bo...
research
04/10/2019

BAOD: Budget-Aware Object Detection

We study the problem of object detection from a novel perspective in whi...
research
03/04/2020

Annotation-free Learning of Deep Representations for Word Spotting using Synthetic Data and Self Labeling

Word spotting is a popular tool for supporting the first exploration of ...

Please sign up or login with your details

Forgot password? Click here to reset