Deep Learning for Semantic Part Segmentation with High-Level Guidance

By Stavros Tsogkas, Iasonas Kokkinos, George Papandreou, Andrea Vedaldi. 2015

43 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning (2016, background): “…order to explore the hidden semantics in the CNN, many studies have focused on the visualization of CNN units (Zeiler and Fergus 2014; Mahendran and Vedaldi 2015; Simonyan, Vedaldi, and Zisserman 2013; Dosovitskiy and Brox 2015; Aubry and Russell 2015) and analyzed their statistical features…”
Convolutional Neural Fabrics (2016, background): “Our results are slightly worse than [31, 33], but the latter are based on the VGG-16 network.”
Repurposing GANs for One-Shot Semantic Part Segmentation (2021, methodology): “TABLE 4 IOU Scores on PASCAL-Parts Car Segmentation Model BodyPlateLightWheelWindow BGAverage CNN [43] 73.4 41.7 42.2 66.3 61 67.4 58.7 CNN+CRF [43] 75.4 35.8 36.1 64.3 61.8 68.7 57 Ours (Auto-shot) 75.5 17.8 29.3 57.2 62.4 70.7 52.2 OMPS [64] 86.3 50.5 55.1 75.5 65.2 - 66.5 Ours (Auto-shot) w/o bg ”
SEMANTIC SEGMENTATION OF AERIAL IMAGES WITH AN ENSEMBLE OF CNNS (2016, unknown): “Similarly, [Tsogkas et al., 2015] combine a CNN with a fully connected CRF, but add a Restricted Boltzmann Machine to learn high-level prior information about objects, which was previously lacking.”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, background): “…[14, 27,67], region proposal generation [30,82,85], instance segmentation [21, 37, 82], pose estimation, part segmentation, and landmark localization [3,15,42,75,81,96,98,104,111], as well as the large body of works around object detection and image classiﬁcation e.g. [22,31,32,40,52,85,89,93,94].”
Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs (2017, methodology): “…predicts labels for pixels, we follow (Tsogkas et al., 2015) and map pixel CRF (as in Kae et al. (2013)) 93.23 GLOC (Kae et al., 2013) 94.95 DNN (Tsogkas et al., 2015) 96.54 DNN+CRF+SBM (Tsogkas et al., 2015) 96.97 labels to superpixels by using the most frequent label in a superpixel as the class.”