Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Deep attention-based classification network for robust depth prediction|
|Citation:||Proceedings of the 14th Asian Conference on Computer Vision (ACCV 2018), as published in Lecture Notes in Computer Science, 2019 / vol.11364, pp.663-678|
|Publisher Place:||Cham, Switzerland|
|Series/Report no.:||Lecture Notes in Computer Science; 11364|
|Conference Name:||14th Asian Conference on Computer Vision (ACCV) (02 Dec 2018 - 06 Dec 2018 : Perth, Western Australia)|
|Ruibo Li, Ke Xian, Chunhua Shen, Zhiguo Cao, B, Hao Lu, and Lingxiao Hang|
|Abstract:||In this paper, we present our deep attention-based classification (DABC) network for robust single image depth prediction, in the context of the Robust Vision Challenge 2018 (ROB 2018) (http:// www.robustvision.net/index.php). Unlike conventional depth prediction, our goal is to design a model that can perform well in both indoor and outdoor scenes with a single parameter set. However, robust depth prediction suffers from two challenging problems: (a) How to extract more discriminative features for different scenes (compared to a single scene)? (b) How to handle the large differences of depth ranges between indoor and outdoor datasets? To address these two problems, we first formulate depth prediction as a multi-class classification task and apply a softmax classifier to classify the depth label of each pixel. We then introduce a global pooling layer and a channel-wise attention mechanism to adaptively select the discriminative channels of features and to update the original features by assigning important channels with higher weights. Further, to reduce the influence of quantization errors, we employ a softweighted sum inference strategy for the final prediction. Experimental results on both indoor and outdoor datasets demonstrate the effectiveness of our method. It is worth mentioning that we won the 2-nd place in single image depth prediction entry of ROB 2018, in conjunction with IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018.|
|Keywords:||Robust depth prediction; Attention; Classification network|
|Rights:||© Springer Nature Switzerland AG 2019|
|Appears in Collections:||Computer Science publications|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.