Filters








54,378 Hits in 6.3 sec

House-GAN++: Generative Adversarial Layout Refinement Networks [article]

Nelson Nauata, Sepidehsadat Hosseini, Kai-Hung Chang, Hang Chu, Chin-Yi Cheng, Yasutaka Furukawa
2021 arXiv   pre-print
The iterative generator also creates a new opportunity in further improving a metric of choice via meta-optimization techniques by controlling when to pass which input constraints during iterative layout  ...  Our qualitative and quantitative evaluation based on the three standard metrics demonstrate that the proposed system makes significant improvements over the current state-of-the-art, even competitive against  ...  The iterative generator also creates a new opportunity in further improving a metric of choice via meta-optimization techniques by controlling when to pass which input constraints during iterative layout  ... 
arXiv:2103.02574v1 fatcat:kqeskhqec5dulesb23mkl6gkme

Efficient Hybrid Multiobjective Optimization of Pressure Swing Adsorption

Zhimian Hao, Adrian Caspari, Artur M. Schweidtmann, Yannic Vaupel, Alexei A. Lapkin, Adel Mhamdi
2021 Chemical Engineering Journal  
., TSEMO) searches the entire decision space and identifies an approximated Pareto front within a small number of simulations.  ...  In the second step, a gradient-based deterministic algorithm (i.e., DyOS) is initialized at the approximated Pareto front to further refine the solutions until local optimality.  ...  Acknowledgments Authors declare no competing financial interest. ZH acknowledges the financial support from Cambridge Trust and Chinese Scholarship Council.  ... 
doi:10.1016/j.cej.2021.130248 fatcat:vt5shizmaneklgerpzvmd374lu

Experimental accuracy in protein structure refinement via molecular dynamics simulations

Lim Heo, Michael Feig
2018 Proceedings of the National Academy of Sciences of the United States of America  
A significant energetic driving force toward the native state was lacking until its immediate vicinity, and there was significant sampling of off-pathway states competing for productive refinement.  ...  The role of recent force field improvements is discussed and transition paths are analyzed in detail to inform which key transitions have to be overcome to achieve successful refinement.  ...  A significant energetic driving force toward the native state was lacking until its immediate vicinity, and there was significant sampling of off-pathway states competing for productive refinement.  ... 
doi:10.1073/pnas.1811364115 fatcat:uxa7gxqwfzakxoimaswg3mwpki

AutoPhaseNN: Unsupervised Physics-aware Deep Learning of 3D Nanoscale Bragg Coherent Diffraction Imaging [article]

Yudong Yao, Henry Chan, Subramanian Sankaranarayanan, Prasanna Balaprakash, Ross J. Harder, Mathew J. Cherukara
2022 arXiv   pre-print
shown real space images.  ...  By incorporating the physics of the imaging technique into the DL model during training, AutoPhaseNN learns to invert 3D BCDI data from reciprocal space to real space in a single shot without ever being  ...  A refinement procedure was conducted on the real space images predicted by AutoPhaseNN.  ... 
arXiv:2109.14053v2 fatcat:y6hntugnbbgb3kyxl3fhpdkzci

Iterative Entity Alignment with Improved Neural Attribute Embedding

Ning Pang, Weixin Zeng, Jiuyang Tang, Zhen Tan, Xiang Zhao
2019 Extended Semantic Web Conference  
Besides, entity representations are refined via an iterative training process on the neural network.  ...  We evaluate our proposal on real-life datasets against state-of-the-art methods, and the results demonstrate the effectiveness of our solution.  ...  Furthermore, we devise an iterative training strategy to enlarge training set and generate better entity embeddings via neural network.  ... 
dblp:conf/esws/PangZTT019 fatcat:hshscymdnncffmim2bgi4rqtn4

Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints [article]

Yan Xu, Xinge Zhu, Jianping Shi, Guofeng Zhang, Hujun Bao, Hongsheng Li
2019 arXiv   pre-print
Extensive experiments on KITTI depth completion dataset and NYU-Depth-V2 dataset demonstrate that our method achieves state-of-the-art performance.  ...  In this paper, to regularize the depth completion and improve the robustness against noise, we propose a unified CNN framework that 1) models the geometric constraints between depth and surface normal  ...  Then, we transform the predicted depth and normal to the planeorigin distance space, and conduct a refinement process in this space via a diffusion model to enforce the geometric constraints.  ... 
arXiv:1910.06727v1 fatcat:3aloiqs3trf7xkgccbigqzxxsy

ZoomOut: Spectral Upsampling for Efficient Shape Correspondence [article]

Simone Melzi, Jing Ren, Emanuele Rodolà, Abhishek Sharma, Peter Wonka, Maks Ovsjanikov
2019 arXiv   pre-print
We present a simple and efficient method for refining maps or correspondences by iterative upsampling in the spectral domain that can be implemented in a few lines of code.  ...  In each application we demonstrate an improvement with respect to both the quality of the results and the computational speed compared to the best competing methods, with up to two orders of magnitude  ...  These approaches have the space of functions that can be transferred [Nogneng et al. 2018]. been recently generalized by spectral generalized multidimensional Iterative Map Refinement  ... 
arXiv:1904.07865v4 fatcat:qbbqlz7ejrf3hli62ggfea3foy

A learning heuristic for space mapping and searching self-organizing systems using adaptive mesh refinement

Carolyn L. Phillips
2014 Journal of Computational Physics  
Using a method inspired by the adaptive mesh refinement method, the heuristic iteratively issues batches of queries to be executed in parallel, based on what has been learned from previous iterations.  ...  Since these ordered states are emergent, often experiment, not analysis, is necessary to create a diagram of ordered states over the parameter space.  ...  Thus we are measuring whether the additional terms improve the search relative to an iterated uniform search.  ... 
doi:10.1016/j.jcp.2014.05.001 fatcat:humtzk5vsbdmtfzpiqlazn6riu

Adaptive Imitation Scheme for Memetic Algorithms [chapter]

Ehsan Shahamatnia, Ramin Ayanzadeh, Rita A. Ribeiro, Saeid Setayeshi
2011 IFIP Advances in Information and Communication Technology  
These algorithms are similar in nature to genetic algorithms as they follow evolutionary strategies, but they also incorporate a refinement phase during which they learn about the problem and search space  ...  In the first iterations population should be as diverse as possible to cover all searching space, but achieving final iterations diversity of solutions decreases.  ...  Each person during his life span benefits from the interactions with the environment as means to improve his competency in the society, but the scale to which he is influenced from the environment usually  ... 
doi:10.1007/978-3-642-19170-1_12 fatcat:yxt5pyb5ljcvdmvxzxzvze6gfi

End-to-end Graph-constrained Vectorized Floorplan Generation with Panoptic Refinement [article]

Jiachen Liu, Yuan Xue, Jose Duarte, Krishnendra Shekhawat, Zihan Zhou, Xiaolei Huang
2022 arXiv   pre-print
We have conducted extensive experiments on a real-world floorplan dataset, and the results show that our method achieves state-of-the-art performance under different settings and evaluation metrics.  ...  To generate high fidelity vectorized floorplans, we propose a novel two-stage framework, including a draft stage and a multi-round refining stage.  ...  We appreciate the help from professors and graduate students from College of Arts and Architecture at Penn State with the user study.  ... 
arXiv:2207.13268v1 fatcat:tmk6p55mt5amplfa72zrpccxhi

A complete data processing workflow for CryoET and subtomogram averaging [article]

Muyuan Chen, James M. Bell, Xiaodong Shi, Stella Y. Sun, Zhao Wang, Steven J. Ludtke
2019 arXiv   pre-print
This workflow greatly reduces human effort and increases throughput, and is capable of determining protein structures at state-of-the-art resolutions for both purified macromolecules and cells.  ...  We refine even/odd particle sets independently in the subtilt refinement.  ...  Next, 4 rounds of subtomogram refinement and 3 rounds of subtilt refinement were performed to arrive at the final map, which was sharpened using a 1-D structure factor  ... 
arXiv:1902.03978v1 fatcat:gcoh6hwq7nca5exzo5w62w62ra

Partial Predicate Abstraction and Counter-Example Guided Refinement [article]

Tuba Yavuz
2017 arXiv   pre-print
for model checking infinite-state systems.  ...  The proposed approach incrementally considers growing sets of predicates for abstraction refinement.  ...  Although CEGAAR could not compete with POLY, this is expected as the verification stage is performed from scratch after every refinement.  ... 
arXiv:1712.01734v1 fatcat:cknqqeht2vcyjo4o7upb363xgm

Cascaded Scene Flow Prediction using Semantic Segmentation [article]

Zhile Ren, Deqing Sun, Jan Kautz, Erik B. Sudderth
2017 arXiv   pre-print
Our cascaded classification framework accurately models 3D scenes by iteratively refining semantic segmentation masks, stereo correspondences, 3D rigid motion estimates, and optical flow fields.  ...  We evaluate our method on the challenging KITTI autonomous driving benchmark, and show that accounting for the motion of segmented vehicles leads to state-of-the-art performance.  ...  This cascaded framework enables efficient, adaptive discretization of a large state space for flow and disparity, and is a principled way of optimizing a limited number of inference iterations [12] .  ... 
arXiv:1707.08313v2 fatcat:qzr2hogpdvhpzmhfrhwkqong6u

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild [article]

Alexander Grabner, Yaming Wang, Peizhao Zhang, Peihong Guo, Tong Xiao, Peter Vajda, Peter M. Roth, Vincent Lepetit
2020 arXiv   pre-print
We evaluate our approach on the challenging Pix3D dataset and achieve up to 55% relative improvement compared to state-of-the-art refinement methods in multiple metrics.  ...  for 3D pose refinement.  ...  Our refinement outperforms the baseline as well as competing refinement methods across all metrics.  ... 
arXiv:2007.08939v1 fatcat:43bixtu4ujfcnhiimepl4ra7oe

High-Accuracy Protein Structures By Combining Machine-Learning With Physics-Based Refinement [article]

Lim Heo, Michael Feig
2019 bioRxiv   pre-print
Here we show that combining machine-learning based models from AlphaFold with state-of-the-art physics-based refinement via molecular dynamics simulations further improves predictions to outperform any  ...  Protein structure prediction has long been available as an alternative to experimental structure determination, especially via homology modeling based on templates from related sequences.  ...  MD refinement further improved AlphaFold predictions.  ... 
doi:10.1101/731521 fatcat:y6k7qlgaivd73hpimxue24vpyi
« Previous Showing results 1 — 15 out of 54,378 results