1 code implementation • 16 Feb 2024 • Divin Yan, Lu Qi, Vincent Tao Hu, Ming-Hsuan Yang, Meng Tang
To address the observed appearance overlap between synthesized images of rare classes and tail classes, we propose a method based on contrastive learning to minimize the overlap between distributions of synthetic images for different classes.
no code implementations • 17 Dec 2023 • Vincent Tao Hu, David W Zhang, Pascal Mettes, Meng Tang, Deli Zhao, Cees G. M. Snoek
Flow Matching is an emerging generative modeling technique that offers the advantage of simple and efficient training.
no code implementations • 28 Nov 2023 • Jacob Schnell, Jieke Wang, Lu Qi, Vincent Tao Hu, Meng Tang
We propose ScribbleGen, a generative data augmentation method that leverages a ControlNet diffusion model conditioned on semantic scribbles to produce high-quality training data.
1 code implementation • Findings (ACL) 2022 • Yicheng Zou, Hongwei Liu, Tao Gui, Junzhe Wang, Qi Zhang, Meng Tang, Haixiang Li, Daniel Wang
Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation.
no code implementations • 4 May 2021 • Meng Tang, Xin Ju, Louis J. Durlofsky
The surrogate model is trained to predict the 3D CO2 saturation and pressure fields in the storage aquifer, and 2D displacement maps at the Earth's surface.
no code implementations • 11 May 2020 • Kejie Li, Martin Rünz, Meng Tang, Lingni Ma, Chen Kong, Tanner Schmidt, Ian Reid, Lourdes Agapito, Julian Straub, Steven Lovegrove, Richard Newcombe
We introduce FroDO, a method for accurate 3D reconstruction of object instances from RGB video that infers object location, pose and shape in a coarse-to-fine manner.
no code implementations • 21 Oct 2019 • Gege Wen, Meng Tang, Sally M. Benson
This paper proposes a deep neural network approach for predicting multiphase flow in heterogeneous domains with high computational efficiency.
no code implementations • 16 Aug 2019 • Meng Tang, Yimin Liu, Louis J. Durlofsky
High-fidelity numerical simulation results for the posterior geomodels (generated by the surrogate-based data assimilation procedure) are shown to be in essential agreement with the recurrent R-U-Net predictions.
1 code implementation • ACL 2019 • Dinghan Shen, Pengyu Cheng, Dhanasekar Sundararaman, Xinyuan Zhang, Qian Yang, Meng Tang, Asli Celikyilmaz, Lawrence Carin
Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems.
1 code implementation • CVPR 2019 • Dmitrii Marin, Meng Tang, Ismail Ben Ayed, Yuri Boykov
Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization.
4 code implementations • 12 May 2018 • Hoel Kervadec, Jose Dolz, Meng Tang, Eric Granger, Yuri Boykov, Ismail Ben Ayed
To the best of our knowledge, the method of [Pathak et al., 2015] is the only prior work that addresses deep CNNs with linear constraints in weakly supervised segmentation.
no code implementations • CVPR 2018 • Meng Tang, Abdelaziz Djelouah, Federico Perazzi, Yuri Boykov, Christopher Schroers
Our normalized cut loss approach to segmentation brings the quality of weakly-supervised training significantly closer to fully supervised methods.
no code implementations • ECCV 2018 • Meng Tang, Federico Perazzi, Abdelaziz Djelouah, Ismail Ben Ayed, Christopher Schroers, Yuri Boykov
This approach simplifies weakly-supervised training by avoiding extra MRF/CRF inference steps or layers explicitly generating full masks, while improving both the quality and efficiency of training.
no code implementations • 16 May 2017 • Dmitrii Marin, Meng Tang, Ismail Ben Ayed, Yuri Boykov
We call it Breiman's bias due to its similarity to the histogram mode isolation previously discovered by Breiman in decision tree learning with Gini impurity.
no code implementations • ICCV 2015 • Meng Tang, Ismail Ben Ayed, Dmitrii Marin, Yuri Boykov
Our bound formulation for kernel K-means allows to combine general pair-wise feature clustering methods with image grid regularization using graph cuts, similarly to standard color model fitting techniques for segmentation.
no code implementations • 24 Jun 2015 • Meng Tang, Dmitrii Marin, Ismail Ben Ayed, Yuri Boykov
We propose a new segmentation model combining common regularization energies, e. g. Markov Random Field (MRF) potentials, and standard pairwise clustering criteria like Normalized Cut (NC), average association (AA), etc.