Weakly supervised multi-scale recurrent convolutional neural network for co-saliency detection and co-segmentation
- PDF / 3,790,332 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 8 Downloads / 182 Views
(0123456789().,-volV) (0123456789().,-volV)
IAPR-MEDPRAI
Weakly supervised multi-scale recurrent convolutional neural network for co-saliency detection and co-segmentation Aditya Kompella1
•
Raghavendra V. Kulkarni2
Received: 23 October 2018 / Accepted: 14 May 2019 Ó Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract A new approach involving multi-scale recurrent convolutional neural network (RCNN) has been proposed for co-saliency object detection. The proposed approach involves careful separation of foreground and background superpixel regions from a single image taken from a related group of images in order to train an RCNN to extract the common salient object regions. The one-dimensional convolutional neural network (CNN) is trained using superpixels extracted from several multi-scaled images derived from a single image in every group. The output of the CNN is fed into the recurrent neural network to classify the common object superpixel properties from the remaining images. The superpixel feature trainingbased RCNN approach addresses two challenges: It requires a small training dataset of about 38 representative images. Further, the use of 1-dimensional superpixel features to train the RCNN results in faster training. The proposed approach delivers accurate identification and segmentation of the common salient object from an image group even under extreme background conditions and object pose variations. The approach has been extensively evaluated using public domain datasets, such as imagepair, iCoseg-sub and iCoseg. The proposed approach delivers higher accuracy, F-measure and lower mean absolute error compared to several state-of-the-art approaches. Keywords Co-salient object detection Image co-segmentation Recurrent convolutional neural network Visual attention Weakly supervised training
1 Introduction Recent deep learning-based computer vision applications can handle the explosive growth of visual information in the form of images. Computer vision applications modeled upon human visual perception have gained popularity. Human visual perception can identify and locate the objects in images easily even if the object exhibits extreme deformities or is located in complex backgrounds. Several
& Aditya Kompella [email protected]; [email protected] Raghavendra V. Kulkarni [email protected] 1
Center for Machine Learning and Computational Intelligence, M S Ramaiah University of Applied Sciences, Bangalore, Karnataka State, India
2
Department of Electronics and Communication Engineering, M S Ramaiah University of Applied Sciences, Bangalore, Karnataka State, India
research areas, such as saliency-based models and eye fixation models have been inspired from human visual perception. Saliency-based object detection aims to extract from a single image the visually salient object that attracts the visual perception. The output of salient object detection generates a saliency map (SM ) where the probability of the each pixel represents whether the pixel belongs to salient
Data Loading...
