Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image

Abstract

Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder-decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available.

arXiv commentInternational Journal of Computer Vision, Springer Verlag, 2020, Special Issue on Deep Learning for Robotic Vision

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Multi-Scale Context Aggregation by Dilated Convolutions
• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
• Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
• Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removal
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
• An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
• Convolutional Oriented Boundaries
• Dual Graph Convolutional Network for Semantic Segmentation
• Symmetry Aware Evaluation of 3D Object Detection and Pose Estimation in Scenes of Many Parts in Bulk
• Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network

Cited by in corpus (1)

• FPCC: Fast Point Cloud Clustering based Instance Segmentation for Industrial Bin-picking