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 Content
Deep Affinity Net: Instance Segmentation via Affinity
TL;DR: Deep Affinity Net is proposed, an effective affinity-based approach accompanied with a new graph partitioning algorithm Cascade-GAEC that achieves the best single-shot result as well as the fastest running time among all affinity- based models.
Journal ArticleDOI
Concealed object segmentation in terahertz imaging via adversarial learning
TL;DR: A novel Conditional Generative Adversarial Nets, named as Mask-CGANs to segment weapons in Terahertz imaging, which outperforms CGANs, and is fast enough to be implemented in a real-time security check system, which is 44 times faster than Mask-RCNN.
Posted Content
Mask Encoding for Single Shot Instance Segmentation
TL;DR: MeInst as mentioned in this paper distills the two-dimensional mask into a compact and fixed-dimensional representation vector, which allows the instance segmentation task to be incorporated into one-stage bounding-box detectors and results in a simple yet efficient instance-segmentation framework.
Proceedings ArticleDOI
Pointly-Supervised Instance Segmentation
TL;DR: In this paper , the authors propose an embarrassingly simple point annotation scheme to collect weak supervision for instance segmentation, which can be trained with point-based supervision collected via their scheme.
Journal ArticleDOI
Fuzzy image clustering incorporating local and region-level information with median memberships
TL;DR: Experiments show that the proposed method FALRCM (Fuzzy Adaptive Local and Region-level information C-Means) achieves better performance in terms of fuzzy partition coefficient, fuzzy partition entropy, Segmentation Accuracy (SA), mean Intersection-over-Union (mIoU), Peak Signal-to-Noise Ratio (PSNR) and visual effects compared with several state-of-the-art FCM variants.
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.