Enming Luo

Enming Luo

Auto-generated profile, based on publicly available information

Enming Luo

Google Research, Mountain View, CA, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 March 2015 in IEEE Transactions on Image Processing
Verified
Journal Article
Open access
ELEnming Luo
Enming Luo
SCStanley H. Chan
Stanley H. Chan
TNTruong Q. Nguyen
Truong Q. Nguyen
We propose a data-dependent denoising procedure to restore noisy images. Different from existing denoising algorithms which search for patches from either the noisy image or a generic database, the new algorithm finds patches from a database that contains relevant patches. We formulate the denoising problem as an optimal filter design problem and make two contributions. First, we determine the basis function of the denoising filter by solving a group sparsity minimization problem. The optimization formulation generalizes existing denoising algorithms and offers systematic analysis of the performance. Improvement methods are proposed to enhance the patch search process. Second, we determine the spectral coefficients of the denoising filter by considering a localized Bayesian prior. The localized prior leverages the similarity of the targeted database, alleviates the intensive Bayesian computation, and links the new method to the classical linear minimum mean squared error estimation. We demonstrate applications of the proposed method in a variety of scenarios, including text images, multiview images, and face images. Experimental results show the superiority of the new algorithm over existing methods.

11 July 2016 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ELEnming Luo
Enming Luo
SCStanley Chan
Stanley Chan
TNTruong Q. Nguyen
Truong Q. Nguyen
We propose an adaptive learning procedure to learn patch-based image priors for image denoising. The new algorithm, called the expectation-maximization (EM) adaptation, takes a generic prior learned from a generic external database and adapts it to the noisy image to generate a specific prior. Different from existing methods that combine internal and external statistics in ad hoc ways, the proposed algorithm is rigorously derived from a Bayesian hyper-prior perspective. There are two contributions of this paper. First, we provide full derivation of the EM adaptation algorithm and demonstrate methods to improve the computational complexity. Second, in the absence of the latent clean image, we show how EM adaptation can be modified based on pre-filtering. The experimental results show that the proposed adaptation algorithm yields consistently better denoising results than the one without adaptation and is superior to several state-of-the-art algorithms.

19 November 2020
Verified
Book Chapter
Closed access
PDF file
KSKarishma Sharma
Karishma Sharma
PDPinar Donmez
Pinar Donmez
ELEnming Luo
Enming Luo
YLYan Liu
Yan Liu
IYI. Zeki Yalniz
I. Zeki Yalniz

4 March 2024
Verified
Conference Paper
Open access
WQWei Qiao
Wei Qiao
TDTushar Dogra
Tushar Dogra
OSOtilia Stretcu
Otilia Stretcu
YLYu-Han Lyu
Yu-Han Lyu
TFTiantian Fang
Tiantian Fang
MTMehmet Tek
Mehmet Tek

10 March 2025
Verified
Conference Paper
Open access
ELEnming Luo
Enming Luo
WQWei Qiao
Wei Qiao
KWKatie Warren
Katie Warren
JLJingxiang Li
Jingxiang Li
EXEric Xiao
Eric Xiao
AFAriel Fuxman
Ariel Fuxman
We present a scalable and agile approach for ads image content moderation at Google, addressing the challenges of moderating massive volumes of ads with diverse content and evolving policies. The proposed method utilizes human-curated textual descriptions and cross-modal text-image co-embeddings to enable zero-shot classification of policy violating ads images, bypassing the need for extensive supervised training data and human labeling. By leveraging large language models (LLMs) and user expertise, the system generates and refines a comprehensive set of textual descriptions representing policy guidelines. During inference, co-embedding similarity between incoming images and the textual descriptions serves as a reliable signal for policy violation detection, enabling efficient and adaptable ads content moderation. Evaluation results demonstrate the efficacy of this framework in significantly boosting the detection of policy violating content.

5 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
GHGuan Zhe Hong
Guan Zhe Hong
YCYin Cui
Yin Cui
AFAriel Fuxman
Ariel Fuxman
SCStanley Chan
Stanley Chan
ELEnming Luo
Enming Luo
In this paper, we study how the granularity of pretraining labels affects the generalization of deep neural networks in image classification tasks. We focus on the "fine-to-coarse" transfer learning setting, where the pretraining label space is more fine-grained than that of the target problem. Empirically, we show that pretraining on the leaf labels of ImageNet21k produces better transfer results on ImageNet1k than pretraining on other coarser granularity levels, which supports the common practice used in the community. Theoretically, we explain the benefit of fine-grained pretraining by proving that, for a data distribution satisfying certain hierarchy conditions, 1) coarse-grained pretraining only allows a neural network to learn the "common" or "easy-to-learn" features well, while 2) fine-grained pretraining helps the network learn the "rarer" or "fine-grained" features in addition to the common ones, thus improving its accuracy on hard downstream test samples in which common features are missing or weak in strength. Furthermore, we perform comprehensive experiments using the label hierarchies of iNaturalist 2021 and observe that the following conditions, in addition to proper choice of label granularity, enable the transfer to work well in practice: 1) the pretraining dataset needs to have a meaningful label hierarchy, and 2) the pretraining and target label functions need to align well.