Weakly Supervised Object Boundaries

By Anna Khoreva, Rodrigo Benenson, Mohamed Omran, Matthias Hein, Bernt Schiele. 2015

46 citations recorded by the source corpus.

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 boundaries without using any object-specific boundary annotations. With the proposed weak supervision techniques we achieve the top performance on the object boundary detection task, outperforming by a large margin the current fully supervised state-of-theart methods.

Subfields: Civil and Structural Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Civil and Structural Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Holistically-Nested Edge Detection (2015, background): “After decades of research, there have emerged a number of properties that a researcher in the ﬁeld might generally agree are key and that are likely to play a role in a successful system: (1) carefully designed and/or learned features [26, 5], (2) multi-scale response fusion [38, 30, 28], (3)…”
Learning Random-Walk Label Propagation for Weakly-Supervised Semantic Segmentation (2017, methodology): “Learning edges with a weaker form of edge supervision is proposed in [10]; however, this method relies on a combination of heuristic boundary detectors and bounding boxes for supervision.”
Semantic Edge Detection with Diverse Deep Supervision (2018, methodology): “ith several stateof-the-art methods. 5.2 Evaluation on SBD We compare DDS-R/DDS-U on the SBD dataset with several state-of-the-art methods including InvDet [1], HFL-FC8 [4], HFL-CRF [4], BNF [54], WS [47], DilConv [46], DSN [2], COB [3], CASENet [2] and SEAL [23]. Results are summarized in Table2. I”
Simple Does It: Weakly Supervised Instance and Semantic Segmentation (2016, methodology): “We use the weakly supervised boundary detection technique from [17] to learn boundaries directly from the Pascal VOC12 box annotations.”
Attention-Based Dropout Layer for Weakly Supervised Object Localization (2019, background): “Existing approaches mine and track discriminative features of each class for object detection [45, 36, 37, 9, 45, 25, 21, 41, 19, 2, 39, 15, 63, 7, 5, 4, 48, 14, 65, 32, 31, 58, 62, 8, 6] and segmentation [33, 29, 18, 16, 24, 52, 50].”
Object Contour and Edge Detection with RefineContourNet (2019, methodology): “ted Edge Detection (HED) [32] has shown that it is benecial to use features of a pre-trained classication network to capture desired image boundaries and suppressing undesired edges. Khoreva et al. [13] have specically trained the HED on object contour detection and proven the potential of HED for t”
W-TALC: Weakly-supervised Temporal Activity Localization and Classification (2018, background): “In computer vision, researchers have utilized weak labels to learn models for several tasks including semantic segmentation [18,28,63], visual tracking [69], reconstruction [52,25], video summarization [37], learning robotic manipulations [46], video captioning [41], object boundaries [29], place re”
Learning to Detect Salient Objects with Image-Level Supervision (2017, methodology): “Weakly supervised learning has been attracting increasingly more attention from areas like object detection [44], semantic segmentation [37], and boundary detection [18].”
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-Supervised Object and Action Localization (2017, background): “Weakly-supervised approaches have been proposed for various visual classification and localization tasks including object detection [55, 13, 9, 41, 3, 50, 43, 8, 32, 61, 40], semantic segmentation [33, 26] and visual attribute localization [2, 53, 57, 52, 39].”
DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection (2019, methodology): “For line detection, DCNN-based methods have also been proposed for tasks such as edge detection [12], [13], contour detection [14], [15], boundary segmentation [16], [17] and so on.”
Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks (2016, methodology): “Speciﬁcally, Khoreva et al. [19] retrained HED [2] on object contours, and Yang et al. [21] proposed a novel encoder-decoder architecture to tackle the same task.”