Backtracking spatial pyramid pooling-based image classifier for weakly supervised top–down salient object detection
Top-down (TD) saliency models produce a probability map that peaks at target locations specified by a task or goal such as object detection. They are usually trained in a fully supervised (FS) setting involving pixel-level annotations of objects. We propose a weakly supervised TD saliency framework...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/142295 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-142295 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1422952020-06-18T07:44:38Z Backtracking spatial pyramid pooling-based image classifier for weakly supervised top–down salient object detection Cholakkal, Hisham Johnson, Jubin Rajan, Deepu School of Computer Science and Engineering Engineering::Computer science and engineering Top-down Saliency Salient Object Detection Top-down (TD) saliency models produce a probability map that peaks at target locations specified by a task or goal such as object detection. They are usually trained in a fully supervised (FS) setting involving pixel-level annotations of objects. We propose a weakly supervised TD saliency framework using only binary labels that indicate the presence or absence of an object in an image. First, the probabilistic contribution of each image region to the confidence of a convolutional neural network-based image classifier is computed through a backtracking strategy to produce TD saliency. From a set of saliency maps of an image produced by fast bottom-up (BU) saliency approaches, we select the best saliency map suitable for the TD task. The selected BU saliency map is combined with the TD saliency map. Features having high combined saliency are used to train a linear SVM classifier to estimate feature saliency. This is integrated with combined saliency and further refined through a multi-scale superpixel averaging of saliency map. We evaluate the performance of the proposed weakly supervised TD saliency and achieve comparable performance with FS approaches. Experiments are carried out on seven challenging datasets, and quantitative results are compared with 40 closely related approaches across four different applications. 2020-06-18T07:44:38Z 2020-06-18T07:44:38Z 2018 Journal Article Cholakkal, H., Johnson, J., & Rajan, D. (2018). Backtracking spatial pyramid pooling-based image classifier for weakly supervised top–down salient object detection. IEEE Transactions on Image Processing, 27(12), 6064-6078. doi:10.1109/TIP.2018.2864891 1057-7149 https://hdl.handle.net/10356/142295 10.1109/TIP.2018.2864891 30106724 2-s2.0-85051802283 12 27 6064 6078 en IEEE Transactions on Image Processing © 2018 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Top-down Saliency Salient Object Detection |
spellingShingle |
Engineering::Computer science and engineering Top-down Saliency Salient Object Detection Cholakkal, Hisham Johnson, Jubin Rajan, Deepu Backtracking spatial pyramid pooling-based image classifier for weakly supervised top–down salient object detection |
description |
Top-down (TD) saliency models produce a probability map that peaks at target locations specified by a task or goal such as object detection. They are usually trained in a fully supervised (FS) setting involving pixel-level annotations of objects. We propose a weakly supervised TD saliency framework using only binary labels that indicate the presence or absence of an object in an image. First, the probabilistic contribution of each image region to the confidence of a convolutional neural network-based image classifier is computed through a backtracking strategy to produce TD saliency. From a set of saliency maps of an image produced by fast bottom-up (BU) saliency approaches, we select the best saliency map suitable for the TD task. The selected BU saliency map is combined with the TD saliency map. Features having high combined saliency are used to train a linear SVM classifier to estimate feature saliency. This is integrated with combined saliency and further refined through a multi-scale superpixel averaging of saliency map. We evaluate the performance of the proposed weakly supervised TD saliency and achieve comparable performance with FS approaches. Experiments are carried out on seven challenging datasets, and quantitative results are compared with 40 closely related approaches across four different applications. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Cholakkal, Hisham Johnson, Jubin Rajan, Deepu |
format |
Article |
author |
Cholakkal, Hisham Johnson, Jubin Rajan, Deepu |
author_sort |
Cholakkal, Hisham |
title |
Backtracking spatial pyramid pooling-based image classifier for weakly supervised top–down salient object detection |
title_short |
Backtracking spatial pyramid pooling-based image classifier for weakly supervised top–down salient object detection |
title_full |
Backtracking spatial pyramid pooling-based image classifier for weakly supervised top–down salient object detection |
title_fullStr |
Backtracking spatial pyramid pooling-based image classifier for weakly supervised top–down salient object detection |
title_full_unstemmed |
Backtracking spatial pyramid pooling-based image classifier for weakly supervised top–down salient object detection |
title_sort |
backtracking spatial pyramid pooling-based image classifier for weakly supervised top–down salient object detection |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/142295 |
_version_ |
1681058368703168512 |