Recurrent Neural Networks for Semantic Instance Segmentation
By Amaia Salvador, Miriam Bellver, Manel Baradad, Ferran Marqués, Jordi Torres, Xavier Giró-i-Nieto. 2017
65 citations recorded by the source corpus.
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 this https URL
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Hongsheng Li
- Xiaogang Wang
- Ting-Li Chen
- Peng Gao
- David J. Fleet
- Jifeng Dai
- Geoffrey E. Hinton
- Quoc V. Le
In Computer Vision and Pattern Recognition
- Xiaogang Wang
- Luc Van Gool
- Hongsheng Li
- Dacheng Tao
- Ming-Hsuan Yang
- Trevor Darrell
- Jitendra Malik
- Yi Yang
In Model Architectures
- Xiaogang Wang
- Peng Gao
- Hongsheng Li
- David J. Fleet
- Jifeng Dai
- Ting-Li Chen
- Saurabh Saxena
- Yassine Ruichek
Citations in the corpus
- End-to-End Object Detection with Transformers (2020, neutral): “Closest to our approach are end-to-end set predictions for object detection [43] and instance segmentation [41,30,36,42].”
- Pix2seq: A Language Modeling Framework for Object Detection (2021, background): “Our work is also related to recurrent models in object detection (Stewart et al., 2016; Park & Berg, 2015; Romera-Paredes & Torr, 2016; Salvador et al., 2017; Ren & Zemel, 2017), in which the system learns to predict one object at a time.”
- Survey on semantic segmentation using deep learning techniques (2019, background): “Amaia et al. [75] present an encoder / decoder based recurrent neural network architecture for semantic instance segmentation.”
- Fast Convergence of DETR with Spatially Modulated Co-Attention (2021, background): “Recently, another branch of object detection methods [35, 34, 32, 4] beyond one-stage and two-stage ones has gained popularity.”