Corpus ID: 13586383

Mix-and-Match Tuning for Self-Supervised Semantic Segmentation

@article{Zhan2018MixandMatchTF,
  title={Mix-and-Match Tuning for Self-Supervised Semantic Segmentation},
  author={Xiaohang Zhan and Z. Liu and Ping Luo and X. Tang and Chen Change Loy},
  journal={ArXiv},
  year={2018},
  volume={abs/1712.00661}
}
  • Xiaohang Zhan, Z. Liu, +2 authors Chen Change Loy
  • Published 2018
  • Computer Science
  • ArXiv
  • Deep convolutional networks for semantic image segmentation typically require large-scale labeled data, e.g. ImageNet and MS COCO, for network pre-training. To reduce annotation efforts, self-supervised semantic segmentation is recently proposed to pre-train a network without any human-provided labels. The key of this new form of learning is to design a proxy task (e.g. image colorization), from which a discriminative loss can be formulated on unlabeled data. Many proxy tasks, however, lack the… CONTINUE READING
    14 Citations
    Cross Pixel Optical Flow Similarity for Self-Supervised Learning
    • 22
    • PDF
    Human-in-the-loop image segmentation and annotation
    • 2
    • PDF
    A survey of semi- and weakly supervised semantic segmentation of images
    • 2
    Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations
    • 10
    • PDF
    MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network
    • 1
    • PDF
    Bridge Segmentation Performance Gap Via Evolving Shape Prior
    Self-Supervised Drivable Area and Road Anomaly Segmentation Using RGB-D Data For Robotic Wheelchairs
    • 13
    • PDF
    Auto-Annotation Quality Prediction for Semi-Supervised Learning with Ensembles
    • 1
    • PDF
    Are We Hungry for 3D LiDAR Data for Semantic Segmentation?
    • 1
    • PDF

    References

    SHOWING 1-10 OF 41 REFERENCES
    Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
    • 445
    • PDF
    Colorization as a Proxy Task for Visual Understanding
    • 183
    • Highly Influential
    • PDF
    BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
    • Jifeng Dai, Kaiming He, Jian Sun
    • Computer Science
    • 2015 IEEE International Conference on Computer Vision (ICCV)
    • 2015
    • 519
    • PDF
    Fully Convolutional Networks for Semantic Segmentation
    • 7,744
    • PDF
    What's the Point: Semantic Segmentation with Point Supervision
    • 355
    • PDF
    Weakly Supervised Semantic Segmentation Using Web-Crawled Videos
    • 81
    • PDF
    Deep Learning Markov Random Field for Semantic Segmentation
    • 68
    • PDF
    Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade
    • 131
    • PDF
    Semantic Image Segmentation via Deep Parsing Network
    • 472
    • PDF
    ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
    • 334
    • PDF