Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image - Archive ouverte HAL
Journal Articles International Journal of Computer Vision Year : 2020

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.
Fichier principal
Vignette du fichier
main.pdf (9.29 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02151828 , version 1 (13-06-2019)
hal-02151828 , version 2 (21-02-2020)
hal-02151828 , version 3 (11-04-2020)

Identifiers

Cite

Matthieu Grard, Emmanuel Dellandréa, Liming Chen. Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image. International Journal of Computer Vision, 2020, Special Issue on Deep Learning for Robotic Vision, ⟨10.1007/s11263-020-01323-0⟩. ⟨hal-02151828v3⟩
238 View
145 Download

Altmetric

Share

More