Recurrent Neural Networks for Semantic Instance Segmentation
arXiv:1712.00617
Abstract
We present a recurrent model for semantic instance segmentation that sequentially generates binary masks and their associated class probabilities for every object in an image. Our proposed system is trainable end-to-end from an input image to a sequence of labeled masks and, compared to methods relying on object proposals, does not require post-processing steps on its output. We study the suitability of our recurrent model on three different instance segmentation benchmarks, namely Pascal VOC 2012, CVPPP Plant Leaf Segmentation and Cityscapes. Further, we analyze the object sorting patterns generated by our model and observe that it learns to follow a consistent pattern, which correlates with the activations learned in the encoder part of our network. Source code and models are available at https://imatge-upc.github.io/rsis/
References in corpus (8)
- Sequence to Sequence Learning with Neural Networks
- End to End Learning for Self-Driving Cars
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Matching Networks for One Shot Learning
- Semantic Instance Segmentation with a Discriminative Loss Function
- Simultaneous Detection and Segmentation
- Capacity and Trainability in Recurrent Neural Networks
- Instance-sensitive Fully Convolutional Networks
Cited by in corpus (12)
- Pix2seq: A Language Modeling Framework for Object Detection
- RVOS: End-to-End Recurrent Network for Video Object Segmentation
- Budget-aware Semi-Supervised Semantic and Instance Segmentation
- End-to-End Object Detection with Fully Convolutional Network
- Fast Convergence of DETR with Spatially Modulated Co-Attention
- Myocardial Segmentation of Cardiac MRI Sequences with Temporal Consistency for Coronary Artery Disease Diagnosis
- Recurrent U-net for automatic pelvic floor muscle segmentation on 3D ultrasound
- Recurrent Instance Segmentation using Sequences of Referring Expressions
- LeafMask: Towards Greater Accuracy on Leaf Segmentation
- Unifying Part Detection and Association for Recurrent Multi-Person Pose Estimation
- RethNet: Object-by-Object Learning for Detecting Facial Skin Problems
- Mask-guided sample selection for Semi-Supervised Instance Segmentation