Deep attention-based classification network for robust depth prediction

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). 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 soft-weighted 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.

References in corpus (8)

• ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
• Residual Attention Network for Image Classification
• Deep Ordinal Regression Network for Monocular Depth Estimation
• Single-Image Depth Perception in the Wild
• Learning a Discriminative Feature Network for Semantic Segmentation
• RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
• Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
• Pixel-wise Attentional Gating for Parsimonious Pixel Labeling

Cited by in corpus (5)

• Deep Robust Single Image Depth Estimation Neural Network Using Scene Understanding
• Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation
• CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
• Auxiliary Learning for Deep Multi-task Learning
• LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery