Weakly Supervised One Shot Segmentation

One-shot learning is a challenging discipline of machine learning since it gnaws at the concept of learning from large amounts of data. This is akin to making machine learning algorithms generalize from a few examples, much like how humans learn. We explore another novel dimension to this problem, of using weak supervision (labels only) in the one-shot domain, and specifically analyse it in the context of semantic segmentation. This is a challenging problem since we operate in the scarcity of data and supervision. We present a simple yet effective approach, whereby exploiting information from the base training classes in the current one-shot segmentation set-up allows for weak supervision to be easily used. We show that this strategy can be leveraged to achieve nearly the same results as full supervision, but with no pixel annotations, allowing fully automated segmentation. Comparisons to several fully supervised methods show convincing results. As well as better results than a weakly supervised baseline. Also presented is a baseline for generalized segmentation under one-shot and weak supervision assumptions.

[1]  Wei Shen,et al.  Few-Shot Image Recognition by Predicting Parameters from Activations , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Huimin Ma,et al.  Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  King-Sun Fu,et al.  A survey on image segmentation , 1981, Pattern Recognit..

[4]  Mohammad Rastegari,et al.  CNN-aware binary MAP for general semantic segmentation , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[5]  Joshua B. Tenenbaum,et al.  Meta-Learning for Semi-Supervised Few-Shot Classification , 2018, ICLR.

[6]  Luc Van Gool,et al.  One-Shot Video Object Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Trevor Darrell,et al.  Learning to Segment Every Thing , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[9]  Yi Yang,et al.  SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation , 2018, IEEE Transactions on Cybernetics.

[10]  Bharath Hariharan,et al.  Low-Shot Visual Recognition by Shrinking and Hallucinating Features , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[11]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

[12]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[13]  Jitendra Malik,et al.  Simultaneous Detection and Segmentation , 2014, ECCV.

[14]  Gustavo Carneiro,et al.  Bayesian Semantic Instance Segmentation in Open Set World , 2018, ECCV.

[15]  Alexei A. Efros,et al.  Conditional Networks for Few-Shot Semantic Segmentation , 2018, ICLR.

[16]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[17]  Alexander S. Ecker,et al.  One-Shot Instance Segmentation , 2018, ArXiv.

[18]  Alexander S. Ecker,et al.  One-Shot Segmentation in Clutter , 2018, ICML.

[19]  George Papandreou,et al.  Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation , 2015, ArXiv.

[20]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[21]  한보형.  Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network , 2016 .

[22]  Byron Boots,et al.  One-Shot Learning for Semantic Segmentation , 2017, BMVC.

[23]  Eric P. Xing,et al.  Few-Shot Semantic Segmentation with Prototype Learning , 2018, BMVC.

[24]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.