Deep Watershed Transform for Instance Segmentation
Min Bai,Raquel Urtasun +1 more
- pp 2858-2866
TLDR
This paper presents a simple yet powerful end-to-end convolutional neural network that achieves more than double the performance over the state-of-the-art on the challenging Cityscapes Instance Level Segmentation task.Abstract:
Most contemporary approaches to instance segmentation use complex pipelines involving conditional random fields, recurrent neural networks, object proposals, or template matching schemes. In this paper, we present a simple yet powerful end-to-end convolutional neural network to tackle this task. Our approach combines intuitions from the classical watershed transform and modern deep learning to produce an energy map of the image where object instances are unambiguously represented as energy basins. We then perform a cut at a single energy level to directly yield connected components corresponding to object instances. Our model achieves more than double the performance over the state-of-the-art on the challenging Cityscapes Instance Level Segmentation task.read more
Citations
More filters
Proceedings ArticleDOI
Path Aggregation Network for Instance Segmentation
TL;DR: PANet as mentioned in this paper enhances the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation, which shortens the information path between lower layers and topmost feature.
Proceedings ArticleDOI
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
TL;DR: In this article, the authors make the observation that the performance of multi-task learning is strongly dependent on the relative weighting between each task's loss, and propose a principled approach to weight multiple loss functions by considering the homoscedastic uncertainty of each task.
Journal ArticleDOI
Mask R-CNN
TL;DR: Mask R-CNN as discussed by the authors extends Faster-RCNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition, which achieves state-of-the-art performance in instance segmentation.
Proceedings ArticleDOI
Panoptic Segmentation
TL;DR: A novel panoptic quality (PQ) metric is proposed that captures performance for all classes (stuff and things) in an interpretable and unified manner and is performed a rigorous study of both human and machine performance for PS on three existing datasets, revealing interesting insights about the task.
References
More filters
Proceedings Article
Learning to segment object candidates
TL;DR: A new way to generate object proposals is proposed, introducing an approach based on a discriminative convolutional network that obtains substantially higher object recall using fewer proposals and is able to generalize to unseen categories it has not seen during training.
Book ChapterDOI
Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
TL;DR: A multi-resolution reconstruction architecture based on a Laplacian pyramid that uses skip connections from higher resolution feature maps and multiplicative gating to successively refine segment boundaries reconstructed from lower-resolution maps is described.
Book ChapterDOI
Recurrent Instance Segmentation
TL;DR: In this paper, an end-to-end recurrent neural network (RNN) is proposed for instance segmentation, which is based on a spatial memory that keeps track of what pixels have been explained and allows occlusion handling.
Proceedings ArticleDOI
A MultiPath Network for Object Detection
Sergey Zagoruyko,Adam Lerer,Tsung-Yi Lin,Pedro O. Pinheiro,Sam Gross,Soumith Chintala,Piotr Dollár +6 more
TL;DR: Three modifications to the standard Fast R-CNN object detector are tested, including a skip connections that give the detector access to features at multiple network layers, a foveal structure to exploit object context at multiple object resolutions, and an integral loss function and corresponding network adjustment that improve localization.
Journal ArticleDOI
Finely-grained annotated datasets for image-based plant phenotyping
TL;DR: A collection of benchmark datasets of raw and annotated top-view color images of rosette plants to invigorate the development of algorithms in the context of plant phenotyping and provide new interesting datasets for the general computer vision community to experiment on.