Search Results for author: Zhilu Zhang

Found 13 papers, 6 papers with code

Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations

no code implementations2 Mar 2022 Zhilu Zhang, Ruohao Wang, Hongzhi Zhang, Yunjin Chen, WangMeng Zuo

For the first issue, the more zoomed (telephoto) image can be naturally leveraged as the reference to guide the SR of the lesser zoomed (short-focus) image.

Reference-based Super-Resolution Self-Supervised Learning

Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision

1 code implementation ICCV 2021 Zhilu Zhang, Haolin Wang, Ming Liu, Ruohao Wang, Jiawei Zhang, WangMeng Zuo

To diminish the effect of color inconsistency in image alignment, we introduce to use a global color mapping (GCM) module to generate an initial sRGB image given the input raw image, which can keep the spatial location of the pixels unchanged, and the target sRGB image is utilized to guide GCM for converting the color towards it.

Optical Flow Estimation

Ex uno plures: Splitting One Model into an Ensemble of Subnetworks

no code implementations9 Jun 2021 Zhilu Zhang, Vianne R. Gao, Mert R. Sabuncu

We show that the proposed subnetwork ensembling method can perform as well as standard deep ensembles in both accuracy and uncertainty estimates, yet with a computational efficiency similar to MC dropout.

Computer Vision

Real-Time Uncertainty Estimation in Computer Vision via Uncertainty-Aware Distribution Distillation

no code implementations31 Jul 2020 Yichen Shen, Zhilu Zhang, Mert R. Sabuncu, Lin Sun

We propose a simple, easy-to-optimize distillation method for learning the conditional predictive distribution of a pre-trained dropout model for fast, sample-free uncertainty estimation in computer vision tasks.

Computer Vision Depth Estimation +1

Self-Distillation as Instance-Specific Label Smoothing

1 code implementation NeurIPS 2020 Zhilu Zhang, Mert R. Sabuncu

It has been recently demonstrated that multi-generational self-distillation can improve generalization.

Two-Dimensional Semi-Nonnegative Matrix Factorization for Clustering

no code implementations19 May 2020 Chong Peng, Zhilu Zhang, Zhao Kang, Chenglizhao Chen, Qiang Cheng

In particular, projection matrices are sought under the guidance of building new data representations, such that the spatial information is retained and projections are enhanced by the goal of clustering, which helps construct optimal projection directions.

Deep Adaptive Inference Networks for Single Image Super-Resolution

1 code implementation8 Apr 2020 Ming Liu, Zhilu Zhang, Liya Hou, WangMeng Zuo, Lei Zhang

Nonetheless, content and resource adaptive model is more preferred, and it is encouraging to apply simpler and efficient networks to the easier regions with less details and the scenarios with restricted efficiency constraints.

Image Super-Resolution Single Image Super Resolution

Omnibus Dropout for Improving The Probabilistic Classification Outputs of ConvNets

no code implementations25 Sep 2019 Zhilu Zhang, Adrian V. Dalca, Mert R. Sabuncu

Motivated by this, we explore the use of various structured dropout techniques to promote model diversity and improve the quality of probabilistic predictions.

Active Learning Ensemble Learning

Confidence Calibration for Convolutional Neural Networks Using Structured Dropout

no code implementations23 Jun 2019 Zhilu Zhang, Adrian V. Dalca, Mert R. Sabuncu

Motivated by this, we explore the use of structured dropout to promote model diversity and improve confidence calibration.

Active Learning Bayesian Inference +1

Cannot find the paper you are looking for? You can Submit a new open access paper.