Shape-aware Instance Segmentation

By Zeeshan Hayder, Xuming He, Mathieu Salzmann. 2016

31 citations recorded by the source corpus.

We address the problem of instance-level semantic segmentation, which aims at jointly detecting, segmenting and classifying every individual object in an image. In this context, existing methods typically propose candidate objects, usually as bounding boxes, and directly predict a binary mask within each such proposal. As a consequence, they cannot recover from errors in the object candidate generation process, such as too small or shifted boxes. In this paper, we introduce a novel object segment representation based on the distance transform of the object masks. We then design an object mask network (OMN) with a new residual-deconvolution architecture that infers such a representation and decodes it into the final binary object mask. This allows us to predict masks that go beyond the scope of the bounding boxes and are thus robust to inaccurate object candidates. We integrate our OMN into a Multitask Network Cascade framework, and learn the resulting shape-aware instance segmentation (SAIS) network in an end-to-end manner. Our experiments on the PASCAL VOC 2012 and the CityScapes datasets demonstrate the benefits of our approach, which outperforms the state-of-the-art in both object proposal generation and instance segmentation.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Pixelwise Instance Segmentation with a Dynamically Instantiated Network (2017, methodology): “5, our method sets a new state-of-theart on Cityscapes, surpassing concurrent work [20] and the best previous published work [42] by significant margins.”
Semantic Instance Segmentation with a Discriminative Loss Function (2017, methodology): “Methods that rely on bounding boxes in their pipeline [17, 28, 29, 12, 13, 42, 4, 26, 30, 22, 5, 18] all suffer from this issue.”
End-to-End Instance Segmentation with Recurrent Attention (2016, background): “Concurrent work [2, 19, 21] also explores a similar idea of using FCNs to output instance-sensitive embeddings.”
SGN: Sequential Grouping Networks for Instance Segmentation (2017, methodology): “Most of the instance segmentation approaches employ a two-step process by treating the problem as a foregroundbackground pixel labeling task within the object detection boxes [15, 16, 1, 29, 30].”
A survey of loss functions for semantic segmentation (2020, background): “Shape-aware loss [14] as the name suggests takes shape into account.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “6 Shape-Aware Instance Segmentation – Hayder et al. (2016) 17.4 36.7 29.3 34 DWT – Bai & Urtasun (2016) 15.”