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
Posted ContentDOI
Transfer learning framework for cell segmentation with incorporation of geometric features
Jin Y,Toberoff A,Elham Azizi +2 more
TL;DR: Wang et al. as discussed by the authors proposed a novel transfer learning, cell segmentation framework incorporating shape-aware features in a deep learning model, with multi-level watershed and morphological post-processing steps.
Posted Content
BshapeNet: Object Detection and Instance Segmentation with Bounding Shape Masks
Ba Rom Kang,Hayoung Kim +1 more
TL;DR: This work proposes BshapeNet+, a network that combines a bshape mask branch with a Mask R-CNN to improve instance segmentation as well as detection, and demonstrates the best performance in both tasks and achieves highly competitive results with state of the art (SOTA) models.
Proceedings ArticleDOI
Object Classification Using Spectral Images and Deep Learning
TL;DR: This paper proposes a procedure to classify spectral images with a Convolutional Neural Network approach which consists in the experimental acquisition of two datasets, medicines and honey, the pre-processing of the raw data, the design of the (CNN) and finally the classification results performed by the designed CNN.
Journal ArticleDOI
SDTP: Semantic-Aware Decoupled Transformer Pyramid for Dense Image Prediction
TL;DR: Wang et al. as mentioned in this paper proposed a Semantic-aware Decoupled Transformer Pyramid (SDTP) for dense image prediction, consisting of Intra-level Semantic Promotion (ISP), Cross-level DecOUpled Interaction (CDI), and Attention Refinement Function (ARF).
Journal ArticleDOI
Realtime single-stage instance segmentation network based on anchors
Jintong Cai,Yujie Li +1 more
TL;DR: In this article, a single-stage detector is proposed for instance segmentation, which uses anchors of different sizes on multi-scale feature maps and adds a new branch to the prediction head to generate prototype masks and mask coefficients.
References
More filters
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Proceedings ArticleDOI
Pyramid Scene Parsing Network
TL;DR: This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task.
Proceedings Article
Understanding the difficulty of training deep feedforward neural networks
Xavier Glorot,Yoshua Bengio +1 more
TL;DR: The objective here is to understand better why standard gradient descent from random initialization is doing so poorly with deep neural networks, to better understand these recent relative successes and help design better algorithms in the future.
Proceedings ArticleDOI
The Cityscapes Dataset for Semantic Urban Scene Understanding
Marius Cordts,Mohamed Omran,Sebastian Ramos,Timo Rehfeld,Markus Enzweiler,Rodrigo Benenson,Uwe Franke,Stefan Roth,Bernt Schiele +8 more
TL;DR: This work introduces Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling, and exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity.