Diverse M-Best Solutions in Markov Random Fields

By Dhruv Batra, Payman Yadollahpour, Abner Guzmán-Rivera, Gregory Shakhnarovich. 2012

199 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Probabilistic & Bayesian Methods, Signal Processing

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 Probabilistic & Bayesian Methods

In Signal Processing

Citations in the corpus

Self-Consistency Improves Chain of Thought Reasoning in Language Models (2022, background): “Other work has sought to explicitly promote diversity in the decoding process (Batra et al., 2012; Li et al., 2016; Vijayakumar et al., 2018).”
A Simple, Fast Diverse Decoding Algorithm for Neural Generation (2016, methodology): “The most relevant is work from Gimpel et al. (2013) and Batra et al. (2012) that produces diverse N-best lists by adding a dissimilarity function based on N-gram overlaps, distancing the current translation from already-generated ones by choosing translations that have high scores but are distinct…”
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models (2016, methodology): “Drawing from recent work in the probabilistic graphical models literature on Diverse M-Best (DivMBest) MAP inference (Batra et al., 2012; Prasad et al., 2014; Kirillov et al., 2015), we optimize an objective that consists of two terms – the sequence likelihood under the model and a dissimilarity ter”
Importance of Search and Evaluation Strategies in Neural Dialogue Modeling (2018, methodology): “C L ] 3 N ov 2 01 9 lier works by Batra et al. (2012).”
Don't just listen, use your imagination: Leveraging visual common sense for non-visual tasks (2015, background): “Instead of generating one image per text description, one could consider generating multiple diverse images to better capture the underlying distribution [3].”
Inferring the Why in Images (2014, methodology): “For both learning and evaluation, we require theK-best solutions, which can be done efficiently with approximate approaches such as K-best MAP estimation [3, 20] or sampling techniques [28, 25].”
MultiSeg: Semantically Meaningful, Scale-Diverse Segmentations From Minimal User Input (2019, methodology): “Diverse Predictions: While there is a large body of work on making diverse predictions [3, 9, 13, 19, 20], we briefly discuss works that produce a diverse set of solutions in interactive image segmentation.”
Creativity: Generating Diverse Questions Using Variational Autoencoders (2017, background): “However in [50] only a single question is generated per image, while the approach discussed in [63] generates diverse questions by sampling from a complicated energy landscape, which is intractable in general [23, 5].”
Resolving Language and Vision Ambiguities Together: Joint Segmentation & Prepositional Attachment Resolution in Captioned Scenes (2016, background): “This shows a need for diverse hypotheses and reasoning about visual features when picking a sentence parse. oracle denotes the best achievable performance using these 10 hypotheses.”
Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles (2016, methodology): “Oracle metrics allow the evaluation of multiple-prediction systems separately from downstream re-ranking or selection systems, and have been extensively used in previous work [3, 5, 8, 9, 15, 16, 23, 24].”
Confident Multiple Choice Learning (2017, methodology): “For example, (Park & Ramanan, 2011; Batra et al., 2012) proposed human-pose estimation methods which produce multiple predictions and then reﬁne them by employing a temporal model, and (Collins & Koo, 2005) proposed a sentence parsing method which re-ranks the output of an initial system which…”
Pose for Action - Action for Pose (2016, background): “Instead of complete articulated pose, [22] and [2] track individual body parts and regularize the trajectories of the body parts through the location of neighboring parts.”
Learning Everything about Anything: Webly-Supervised Visual Concept Learning (2014, background): “This formulation searches for a subset of ngrams that are visually manageable (have reliable ngram classifiers) and cover the space of variance within a concept (similar to [3, 22]).”
Predicting Motivations of Actions by Leveraging Text (2014, methodology): “We often require the n-best solutions, which can be done efficiently with approximate approaches such as n-best MAP estimation [4, 21] or sampling techniques [28, 25].”
Making 360° Video Watchable in 2D: Learning Videography for Click Free Viewing (2017, methodology): “Diverse solution search Generating a diverse set of candidate solutions has been widely discussed in different domains [6, 11, 25, 28, 41].”
Importance of a Search Strategy in Neural Dialogue Modelling (2018, methodology): “Search To address the locality issue in beam search, we propose an iterative beam search to radically increase the size of search space without introducing much computational overhead, inspired by earlier work on diverse beam search (Vijayakumar et al., 2018; Batra et al., 2012; Li et al., 2016).”
Multiple Choice Learning: Learning to Produce Multiple Structured Outputs (2012, methodology): “We compare our algorithm against three alternatives for producing multiple predictions: i) Single SSVM + M -Best MAP [29], ii) Single SSVM + Diverse M -Best MAP [3] and iii) Clustering + Multiple SSVMs.”