Weakly Supervised Object Boundaries

@article{Khoreva2016WeaklySO,
  title={Weakly Supervised Object Boundaries},
  author={Anna Khoreva and Rodrigo Benenson and Mohamed Omran and Matthias Hein and Bernt Schiele},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={183-192}
}
State-of-the-art learning based boundary detection methods require extensive training data. Since labelling object boundaries is one of the most expensive types of annotations, there is a need to relax the requirement to carefully annotate images to make both the training more affordable and to extend the amount of training data. In this paper we propose a technique to generate weakly supervised annotations and show that bounding box annotations alone suffice to reach high-quality object… 
Simple Does It: Weakly Supervised Instance and Semantic Segmentation
TLDR
This work proposes a new approach that does not require modification of the segmentation training procedure and shows that when carefully designing the input labels from given bounding boxes, even a single round of training is enough to improve over previously reported weakly supervised results.
Weakly Supervised Semantic Labelling and Instance Segmentation
TLDR
This work proposes to recursively train a convnet such that outputs are improved after each iteration, and explores which aspects affect the recursive training, and which is the most suitable box-guided segmentation to use as initialisation.
Object Boundary Detection and Classification with Image-Level Labels
TLDR
It is shown that high pixel-wise scores are indicative for the location of semantic boundaries, which suggests that the semantic boundary problem can be approached without using edge labels during the training phase.
Attention-Based Dropout Layer for Weakly Supervised Object Localization
  • Junsuk Choe, Hyunjung Shim
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
TLDR
An Attention-based Dropout Layer (ADL), which utilizes the self-attention mechanism to process the feature maps of the model to improve the accuracy of WSOL, achieving a new state-of-the-art localization accuracy in CUB-200-2011 dataset.
Learning to Detect Salient Objects with Image-Level Supervision
TLDR
This paper develops a weakly supervised learning method for saliency detection using image-level tags only, which outperforms unsupervised ones with a large margin, and achieves comparable or even superior performance than fully supervised counterparts.
Learning Random-Walk Label Propagation for Weakly-Supervised Semantic Segmentation
TLDR
It is shown that by learning the label-propagator jointly with the segmentation predictor, the network is able to effectively learn semantic edges given no direct edge supervision, and that training a segmentation network in this way outperforms the naive approach.
Semantic Edge Detection with Diverse Deep Supervision
TLDR
A novel fully convolutional neural network is proposed using diverse deep supervision within a multi-task framework where bottom layers aim at generating category-agnostic edges, while top layers are responsible for the detection of category-aware semantic edges.
Deep Crisp Boundaries: From Boundaries to Higher-Level Tasks
TLDR
This work proposes a novel refinement architecture to address the challenging problem of learning a crisp edge detector using ConvNet, and achieves superior performance, surpassing human accuracy when using standard criteria on BSDS500, and largely outperforming the state-of-the-art methods when using more strict criteria.
Multi-scale Discriminative Location-Aware Network for Few-Shot Semantic Segmentation
TLDR
A Multi-scale Discriminative Location-aware (MDL) network to tackle the few-shot semantic segmentation problem is proposed, and the global average pooling layer is added to produce location feature information.
...
...

References

SHOWING 1-10 OF 48 REFERENCES
Learning to segment under various forms of weak supervision
TLDR
This work proposes a unified approach that incorporates various forms of weak supervision - image level tags, bounding boxes, and partial labels - to produce a pixel-wise labeling on the challenging Siftflow dataset.
Is object localization for free? - Weakly-supervised learning with convolutional neural networks
TLDR
A weakly supervised convolutional neural network is described for object classification that relies only on image-level labels, yet can learn from cluttered scenes containing multiple objects.
Unsupervised Learning of Edges
TLDR
This work presents a simple yet effective approach for training edge detectors without human supervision, and shows that when using a deep network for the edge detector, this approach provides a novel pre-training scheme for object detection.
From image-level to pixel-level labeling with Convolutional Networks
TLDR
A Convolutional Neural Network-based model is proposed, which is constrained during training to put more weight on pixels which are important for classifying the image, and which beats the state of the art results in weakly supervised object segmentation task by a large margin.
segDeepM: Exploiting segmentation and context in deep neural networks for object detection
TLDR
This paper frames the problem as inference in a Markov Random Field, in which each detection hypothesis scores object appearance as well as contextual information using Convolutional Neural Networks, and allows the hypothesis to choose and score a segment out of a large pool of accurate object segmentation proposals.
Semantic Segmentation with Boundary Neural Fields
TLDR
A Boundary Neural Field (BNF) is introduced, which is a global energy model integrating FCN predictions with boundary cues that is used to enhance semantic segment coherence and to improve object localization.
Weakly supervised semantic segmentation with a multi-image model
TLDR
A novel method for weakly supervised semantic segmentation using a multi-image model (MIM) - a graphical model for recovering the pixel labels of the training images and introducing an “objectness” potential, that helps separating objects from background classes.
Learning object class detectors from weakly annotated video
TLDR
It is shown that training from a combination of weakly annotated videos and fully annotated still images using domain adaptation improves the performance of a detector trained from still images alone.
Situational object boundary detection
  • J. Uijlings, V. Ferrari
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
TLDR
S situational object boundary detection is proposed: first define a variety of situations and train a specialized object boundary detector for each of them using [10], then given a test image, it is classified into these situations using its context, which is model by global image appearance.
High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and Its Applications to High-Level Vision
TLDR
This work shows how to predict boundaries by exploiting object-level features from a pretrained object-classification network, and demonstrates that using their boundaries the authors improve the performance of state-of-the-art methods on the problems of semantic boundary labeling, semantic segmentation and object proposal generation.
...
...