Boundary-Aware Instance Segmentation

Hayder, Zeeshan; He, Xuming; Salzmann, Mathieu

doi:10.1109/cvpr.2017.70

Cited by 155 publications

(91 citation statements)

References 30 publications

(84 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [17] a simultaneous detection and segmentation algorithm is developed that classifies and refines CNN features obtained from regions under R-CNN [16] bounding box proposals. The work in [18] emphasizes on refining object boundaries for binary segmentation masks initially generated from bounding box proposals. In [12] a multi-task network cascade is introduced that, beyond sharing features from the encoder in all following tasks, subsequently adds blocks for i) bounding box generation, ii) instance mask generation and iii) mask categorization.…”

Section: Related Workmentioning

confidence: 99%

Seamless Scene Segmentation

Porzi¹,

Bulò²,

Colovic³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

234

203

View full text Add to dashboard Cite

In this work we introduce a novel, CNN-based architecture that can be trained end-to-end to deliver seamless scene segmentation results. Our goal is to predict consistent semantic segmentation and detection results by means of a panoptic output format, going beyond the simple combination of independently trained segmentation and detection models. The proposed architecture takes advantage of a novel segmentation head that seamlessly integrates multi-scale features generated by a Feature Pyramid Network with contextual information conveyed by a lightweight DeepLab-like module. As additional contribution we review the panoptic metric and propose an alternative that overcomes its limitations when evaluating non-instance categories. Our proposed network architecture yields state-ofthe-art results on three challenging street-level datasets, i.e. Cityscapes, Indian Driving Dataset and Mapillary Vistas.

show abstract

Section: Related Workmentioning

confidence: 99%

Seamless Scene Segmentation

Porzi¹,

Bulò²,

Colovic³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

234

203

View full text Add to dashboard Cite

show abstract

“…Lin et al [29] propose a multi-resolution approach for object detection which they call feature pyramid networks. In [16], the region proposals are refined with network that predicts the distance to the boundary which is then transformed into a binary object mask. Khoreva et al [20] jointly perform instance and semantic segmentation.…”

Section: Related Workmentioning

confidence: 99%

3D Instance Segmentation via Multi-Task Metric Learning

Lahoud

Ghanem

Oswald

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

174

117

View full text Add to dashboard Cite

We propose a novel method for instance label segmentation of dense 3D voxel grids. We target volumetric scene representations which have been acquired with depth sensors or multi-view stereo methods and which have been processed with semantic 3D reconstruction or scene completion methods. The main task is to learn shape information about individual object instances in order to accurately separate them, including connected and incompletely scanned objects. We solve the 3D instance-labeling problem with a multi-task learning strategy. The first goal is to learn an abstract feature embedding which groups voxels with the same instance label close to each other while separating clusters with different instance labels from each other. The second goal is to learn instance information by estimating directional information of the instances' centers of mass densely for each voxel. This is particularly useful to find instance boundaries in the clustering post-processing step, as well as for scoring the quality of segmentations for the first goal. Both synthetic and real-world experiments demonstrate the viability of our approach. Our method achieves state-ofthe-art performance on the ScanNet 3D instance segmentation benchmark [4].

show abstract

“…The MNC approach [10], based on Faster-RCNN [47], repeats this process twice [10] while [33] does it multiple times. [22] extends [10] to model the shape of objects. The fully convolutional instance segmentation method of [32] also combines segmentation proposal and object detection using a position sensitive score map.…”

Section: Related Workmentioning

confidence: 99%

Semi-convolutional Operators for Instance Segmentation

Novotný

Albanie

Larlus

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Object detection and instance segmentation are dominated by region-based methods such as Mask RCNN. However, there is a growing interest in reducing these problems to pixel labeling tasks, as the latter could be more efficient, could be integrated seamlessly in imageto-image network architectures as used in many other tasks, and could be more accurate for objects that are not well approximated by bounding boxes. In this paper we show theoretically and empirically that constructing dense pixel embeddings that can separate object instances cannot be easily achieved using convolutional operators. At the same time, we show that simple modifications, which we call semi-convolutional, have a much better chance of succeeding at this task. We use the latter to show a connection to Hough voting as well as to a variant of the bilateral kernel that is spatially steered by a convolutional network. We demonstrate that these operators can also be used to improve approaches such as Mask RCNN, demonstrating better segmentation of complex biological shapes and PASCAL VOC categories than achievable by Mask RCNN alone.

show abstract

Boundary-Aware Instance Segmentation

Cited by 155 publications

References 30 publications

Seamless Scene Segmentation

Seamless Scene Segmentation

3D Instance Segmentation via Multi-Task Metric Learning

Semi-convolutional Operators for Instance Segmentation

Contact Info

Product

Resources

About