Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs

Laude, Emanuel; Lange, Jan-Hendrik; Jonas, Schüpfer,; Domokos, Csaba; Leal-Taixé, Laura; Schmidt, Frank; Andres, Bjoern; Cremers, Daniel

doi:10.1109/cvpr.2018.00174

Cited by 10 publications

(6 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Discrete optimization is one of hottest topics in mathematics and is widely used to solve computer vision problems (Kim et al 2017;Laude et al 2018). In this paper, we propose a new discrete back propagation algorithm, where a projection function is exploited to binarize or quantize the input variables in a unified framework.…”

Section: Discrete Back Propagation Via Projectionmentioning

confidence: 99%

“…(1) The binarization of CNNs could be essentially solved based on the discrete optimization, but it has long been neglected in previous work. Discrete optimization methods can often provide strong guarantees about the quality of the solutions they find and lead to much better performance in practice (Felzenszwalb and Zabih 2007;Kim et al 2017;Laude et al 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The proteasome controls ESCRT-III–mediated cell division in an archaeon

Risa

Hurtig

Bray

et al. 2020

Science

View full text Add to dashboard Cite

Sulfolobus acidocaldarius is the closest experimentally tractable archaeal relative of eukaryotes and, despite lacking obvious cyclin-dependent kinase and cyclin homologs, has an ordered eukaryote-like cell cycle with distinct phases of DNA replication and division. Here, in exploring the mechanism of cell division in S. acidocaldarius, we identify a role for the archaeal proteasome in regulating the transition from the end of one cell cycle to the beginning of the next. Further, we identify the archaeal ESCRT-III homolog, CdvB, as a key target of the proteasome and show that its degradation triggers division by allowing constriction of the CdvB1:CdvB2 ESCRT-III division ring. These findings offer a minimal mechanism for ESCRT-III–mediated membrane remodeling and point to a conserved role for the proteasome in eukaryotic and archaeal cell cycle control.

show abstract

Section: Discrete Back Propagation Via Projectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The proteasome controls ESCRT-III–mediated cell division in an archaeon

Risa

Hurtig

Bray

et al. 2020

Science

View full text Add to dashboard Cite

show abstract

“…An optimization process using a PGM involves defining an energy function, which can embed contextual information about the data, i.e., relationships among data points at different resolutions, scales, or time steps (prior knowledge). PGMs can be optimized by targeting the maximization of the joint probability (or the minimization of the energy function) of the graph (Laude et al, 2018), which would result in specific river network predictions. Although classes of PGMs (e.g., Bayesian network models) have been used for water quality applications (Section 2), newer models that integrate PGM with DL such as DBN have been used for water quality predictions (Solanki et al, 2015; Yan et al, 2020).…”

Section: Opportunities For Advancement Of Water Quality MLmentioning

confidence: 99%

Can machine learning accelerate process understanding and decision‐relevant predictions of river water quality?

Varadharajan

Appling

Arora

et al. 2022

Hydrological Processes

View full text Add to dashboard Cite

The global decline of water quality in rivers and streams has resulted in a pressing need to design new watershed management strategies. Water quality can be affected by multiple stressors including population growth, land use change, global warming, and extreme events, with repercussions on human and ecosystem health. A scientific understanding of factors affecting riverine water quality and predictions at local to regional scales, and at sub‐daily to decadal timescales are needed for optimal management of watersheds and river basins. Here, we discuss how machine learning (ML) can enable development of more accurate, computationally tractable, and scalable models for analysis and predictions of river water quality. We review relevant state‐of‐the art applications of ML for water quality models and discuss opportunities to improve the use of ML with emerging computational and mathematical methods for model selection, hyperparameter optimization, incorporating process knowledge into ML models, improving explainablity, uncertainty quantification, and model‐data integration. We then present considerations for using ML to address water quality problems given their scale and complexity, available data and computational resources, and stakeholder needs. When combined with decades of process understanding, interdisciplinary advances in knowledge‐guided ML, information theory, data integration, and analytics can help address fundamental science questions and enable decision‐relevant predictions of riverine water quality.

show abstract

“…Size-constrained proposal e y < l a t e x i t s h a 1 _ b a s e 6 4 = " C P 7 J n V i B w g n m j Y I 5 t 4 ADMM for incorporating high-order segmentation priors on the target region's histogram of intensities [26] or compactness [17]. More recently, similar techniques have been proposed to include higher-order priors directly in the learning process [27,28]. To our knowledge, our work is the first employing a discretecontinuous framework for weakly-supervised segmentation.…”

Section: Crf-regularized Proposalmentioning

confidence: 99%

Discretely-constrained deep network for weakly supervised segmentation

Peng

Kervadec

Dolz³

et al. 2019

Preprint

View full text Add to dashboard Cite

An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions. Recent efforts have focused on incorporating such constraints in the training of convolutional neural networks (CNN), however this has so far been done within a continuous optimization framework. Yet, various segmentation constraints and regularization can be modeled and optimized more efficiently in a discrete formulation. This paper proposes a method, based on the alternating direction method of multipliers (ADMM) algorithm, to train a CNN with discrete constraints and regularization priors. This method is applied to the segmentation of medical images with weak annotations, where both size constraints and boundary length regularization are enforced. Experiments on two benchmark datasets for medical image segmentation show our method to provide significant improvements compared to existing approaches in terms of segmentation accuracy, constraint satisfaction and convergence speed.

show abstract

Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs

Cited by 10 publications

References 56 publications

The proteasome controls ESCRT-III–mediated cell division in an archaeon

The proteasome controls ESCRT-III–mediated cell division in an archaeon

Can machine learning accelerate process understanding and decision‐relevant predictions of river water quality?

Discretely-constrained deep network for weakly supervised segmentation

Contact Info

Product

Resources

About