Structured Learning and Prediction in Computer Vision

By Sebastian Nowozin, Christoph H. Lampert. 2011

391 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Model Architectures

Citations in the corpus

EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning (2019, background): “es “Image-to-Edges” problems [5,10,26, 29]. Canny edge detector, an early scheme for constructing edge maps, for example, is roughly 30 years old [6]. Dollar´ and Zitnikc [11] use structured learning [35] on random decision forests to predict local edge masks. Holisticallynested Edge Detection (HED)”
On Structured Prediction Theory with Calibrated Convex Surrogate Losses (2017, background): “Tasks of this type appear in many practical domains such as computer vision [34], natural language processing [42] and bioinformatics [19].”
Fast Edge Detection Using Structured Forests (2014, methodology): “We demonstrate the potential of our approach as a general purpose edge detector by showing the strong cross dataset generalization of our learned edge models. ar X iv :1 40 6.”
Value Iteration Networks (2016, methodology): “…most recent deep RL works [19, 16, 10] employed NN architectures that are very similar to the standard networks used in supervised learning tasks, which typically consist of CNNs for feature extraction, and fully connected layers that map the features to a probability distribution over actions.”
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation (2015, methodology): “To address this we apply an efficient message passing algorithm which is based on the mean field approximation [36].”
Human Pose Estimation with Iterative Error Feedback (2015, background): “see references in [26]) but it is a relatively modern topic in conjunction with feature learning, for computer vision [4, 18, 37, 23].”
Evaluation of output embeddings for fine-grained image classification (2014, methodology): “Inspired by previous work on label embedding [56] [3] [1] and structured SVMs [52] [38], we propose to use a Structured Joint Embedding (SJE) framework (Fig.”
Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields (2015, background): “, 2003], semantic role labeling [Cohn and Blunsom, 2005], topic modeling [Zhu and Xing, 2010], information extraction [Peng and McCallum, 2006], shallow parsing [Sha and Pereira, 2003], named-entity recognition [Settles, 2004], as well as a host of other applications in natural language processing a”
Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing (2018, background): “These assumptions characterize the problem of program synthesis well, but also apply to many structured prediction problems [47, 37] and combinatorial optimization domains ( e.g. , [7]).”
Smart "Predict, then Optimize" (2017, background): “(2005), Nowozin et al. (2011)) in structured support vector machines (SSVMs).”
Structured Attentions for Visual Question Answering (2017, methodology): “We adopt the most straightforward graph structure to model image region arrangements - a grid-structured Conditional Random Field (CRF) [29].”
Deeply Learning the Messages in Message Passing Inference (2015, background): “Usually it is necessary to perform approximate marginal inference to calculate the gradients at each SGD iteration [13].”
Advanced Structured Prediction (2014, methodology): “This NP-hard combinatorial optimization problem frequently arises in machine learning and computer vision, in tasks like MAP inference in graphical models (Lauritzen, 1996; Koller and Friedman, 2009; Wainwright and Jordan, 2008) and structured prediction (Nowozin and Lampert, 2011).”
Deep Learning and Structured Prediction for the Segmentation of Mass in Mammograms (2015, methodology): “The learning process is based on the minimization of the empirical loss [11]:”
Learning Graphical Model Parameters with Approximate Marginal Inference (2013, neutral): “A recent review [10] is more thorough.”
Structured class-labels in random forests for semantic image labelling (2011, background): “Finally, we refer to [23], which gives a comprehensive tutorial on structured learning and prediction in computer vision.”
Closed-Form Approximate CRF Training for Scalable Image Segmentation (2014, background): “, the tutorial [24] for an introduction in the context of computer vision.”
PyStruct: learning structured prediction in python (2014, background): “Structured Prediction and Casting it into Software Structured prediction can be defined as making a prediction f(x) by maximizing a compatibility function between an input x and the possible labels y (Nowozin and Lampert, 2011).”