Search Results for author: Yi Sun

Found 37 papers, 11 papers with code

Spelling Correction using Phonetics in E-commerce Search

no code implementations ECNLP (ACL) 2022 Fan Yang, Alireza Bagheri Garakani, Yifei Teng, Yan Gao, Jia Liu, Jingyuan Deng, Yi Sun

In E-commerce search, spelling correction plays an important role to find desired products for customers in processing user-typed search queries.

Spelling Correction

Improving Relevance Quality in Product Search using High-Precision Query-Product Semantic Similarity

no code implementations ECNLP (ACL) 2022 Alireza Bagheri Garakani, Fan Yang, Wen-Yu Hua, Yetian Chen, Michinari Momma, Jingyuan Deng, Yan Gao, Yi Sun

Ensuring relevance quality in product search is a critical task as it impacts the customer’s ability to find intended products in the short-term as well as the general perception and trust of the e-commerce system in the long term.

Re-Ranking Semantic Similarity +1

A microstructure estimation Transformer inspired by sparse representation for diffusion MRI

no code implementations13 May 2022 Tianshu Zheng, Cong Sun, Weihao Zheng, Wen Shi, Haotian Li, Yi Sun, Yi Zhang, Guangbin Wang, Chuyang Ye, Dan Wu

Thus, the METSC is composed with three stages, an embedding stage, a sparse representation stage, and a mapping stage.

Using Natural Sentences for Understanding Biases in Language Models

1 code implementation12 May 2022 Sarah Alnegheimish, Alicia Guo, Yi Sun

Evaluation of biases in language models is often limited to synthetically generated datasets.

CMA-CLIP: Cross-Modality Attention CLIP for Image-Text Classification

no code implementations7 Dec 2021 Huidong Liu, Shaoyuan Xu, Jinmiao Fu, Yang Liu, Ning Xie, Chien-Chih Wang, Bryan Wang, Yi Sun

In this paper, we propose the Cross-Modality Attention Contrastive Language-Image Pre-training (CMA-CLIP), a new framework which unifies two types of cross-modality attentions, sequence-wise attention and modality-wise attention, to effectively fuse information from image and text pairs.

Text Classification

MESSFN : a Multi-level and Enhanced Spectral-Spatial Fusion Network for Pan-sharpening

no code implementations21 Sep 2021 Yuan Yuan, Yi Sun, Yuanlin Zhang

A novel Spectral-Spatial (SS) stream is established to hierarchically derive and fuse the multi-level prior spectral and spatial expertise from the MS stream and the PAN stream.

NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction

1 code implementation8 Sep 2021 Yi Sun, Yu Zheng, Chao Hao, Hangping Qiu

Using prompts to utilize language models to perform various downstream tasks, also known as prompt-based learning or prompt-learning, has lately gained significant success in comparison to the pre-train and fine-tune paradigm.

Entity Linking Language Modelling +1

Proof: Accelerating Approximate Aggregation Queries with Expensive Predicates

no code implementations27 Jul 2021 Daniel Kang, John Guibas, Peter Bailis, Tatsunori Hashimoto, Yi Sun, Matei Zaharia

Given a dataset $\mathcal{D}$, we are interested in computing the mean of a subset of $\mathcal{D}$ which matches a predicate.

ICINet: ICI-Aware Neural Network Based Channel Estimation for Rapidly Time-Varying OFDM Systems

no code implementations18 Jun 2021 Yi Sun, Hong Shen, Zhenguo Du, Lan Peng, Chunming Zhao

A novel intercarrier interference (ICI)-aware orthogonal frequency division multiplexing (OFDM) channel estimation network ICINet is presented for rapidly time-varying channels.

Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation

no code implementations25 Mar 2021 Yi Sun, Abel Valente, Sijia Liu, Dakuo Wang

Prior works on formalizing explanations of a graph neural network (GNN) focus on a single use case - to preserve the prediction results through identifying important edges and nodes.

Image Classification

Toward Human-Like Grasp: Dexterous Grasping via Semantic Representation of Object-Hand

no code implementations ICCV 2021 Tianqiang Zhu, Rina Wu, Xiangbo Lin, Yi Sun

We first build a dataset by accurately segmenting the functional areas of the object and annotating semantic touch code for each functional area to guide the dexterous hand to complete the functional grasp and post-grasp manipulation.

Self-Supervised Transfer Learning for Hand Mesh Recovery From Binocular Images

no code implementations ICCV 2021 Zheng Chen, Sihan Wang, Yi Sun, Xiaohong Ma

Traditional methods for RGB hand mesh recovery usually need to train a separate model for each dataset with the corresponding ground truth and are hardly adapted to new scenarios without the ground truth for supervision.

Transfer Learning

How Data Augmentation affects Optimization for Linear Regression

no code implementations NeurIPS 2021 Boris Hanin, Yi Sun

Our results apply to arbitrary augmentation schemes, revealing complex interactions between learning rates and augmentations even in the convex setting.

Data Augmentation Stochastic Optimization

Data augmentation as stochastic optimization

no code implementations28 Sep 2020 Boris Hanin, Yi Sun

We present a theoretical framework recasting data augmentation as stochastic optimization for a sequence of time-varying proxy losses.

Data Augmentation Stochastic Optimization

Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings

no code implementations25 Jun 2020 Liang Yu, Yi Sun, Zhanbo Xu, Chao Shen, Dong Yue, Tao Jiang, Xiaohong Guan

In this paper, we intend to minimize the energy cost of an HVAC system in a multi-zone commercial building under dynamic pricing with the consideration of random zone occupancy, thermal comfort, and indoor air quality comfort.

reinforcement-learning

Multi-objective Ranking via Constrained Optimization

1 code implementation13 Feb 2020 Michinari Momma, Alireza Bagheri Garakani, Nanxun Ma, Yi Sun

In this paper, we introduce an Augmented Lagrangian based method to incorporate the multiple objectives (MO) in a search ranking algorithm.

Sem-LSD: A Learning-based Semantic Line Segment Detector

1 code implementation14 Sep 2019 Yi Sun, Xushen Han, Kai Sun, Boren Li, Yongjiang Chen, Mingyang Li

Combined with high-level semantics, Sem-LS is more robust under cluttered environment compared with existing line-shaped representations.

Line Segment Detection Loop Closure Detection

Evolving the Olfactory System

no code implementations NeurIPS Workshop Neuro_AI 2019 Robert Guangyu Yang, Peter Yiliu Wang, Yi Sun, Ashok Litwin-Kumar, Richard Axel, LF Abbott

In this study, we address the optimality of evolutionary design in olfactory circuits by studying artificial neural networks trained to sense odors.

Testing Robustness Against Unforeseen Adversaries

2 code implementations21 Aug 2019 Daniel Kang, Yi Sun, Dan Hendrycks, Tom Brown, Jacob Steinhardt

Adversaries adapt and evolve their attacks; hence adversarial defenses must be robust to a broad range of unforeseen attacks.

Adversarial Defense

Towards Reducing Biases in Combining Multiple Experts Online

no code implementations19 Aug 2019 Yi Sun, Ivan Ramirez, Alfredo Cuesta-Infante, Kalyan Veeramachaneni

In many real life situations, including job and loan applications, gatekeepers must make justified and fair real-time decisions about a person's fitness for a particular opportunity.

Decision Making Fairness

Transfer of Adversarial Robustness Between Perturbation Types

no code implementations3 May 2019 Daniel Kang, Yi Sun, Tom Brown, Dan Hendrycks, Jacob Steinhardt

We study the transfer of adversarial robustness of deep neural networks between different perturbation types.

Adversarial Robustness

Learning Vine Copula Models For Synthetic Data Generation

no code implementations4 Dec 2018 Yi Sun, Alfredo Cuesta-Infante, Kalyan Veeramachaneni

Moreover, we demonstrate that the model is able to generate high-quality samples in a variety of applications, making it a good candidate for synthetic data generation.

Model Selection reinforcement-learning +1

Limited Gradient Descent: Learning With Noisy Labels

no code implementations20 Nov 2018 Yi Sun, Yan Tian, Yiping Xu, Jianxiang Li

We modified the labels of a few samples in a noisy dataset to obtain false labels and to create a reverse pattern.

Learning with noisy labels

HBE: Hand Branch Ensemble Network for Real-time 3D Hand Pose Estimation

no code implementations ECCV 2018 Yidan Zhou, Jian Lu, Kuo Du, Xiangbo Lin, Yi Sun, Xiaohong Ma

The structural design inspiration of the HBE network comes from the understanding of the differences in the functional importance of different fingers.

3D Hand Pose Estimation Frame

An automatic taxonomy of galaxy morphology using unsupervised machine learning

1 code implementation18 Sep 2017 Alex Hocking, James E. Geach, Yi Sun, Neil Davey

We then apply the technique to the HST CANDELS fields, creating a catalogue of approximately 60, 000 classifications.

Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies

Sparsifying Neural Network Connections for Face Recognition

no code implementations CVPR 2016 Yi Sun, Xiaogang Wang, Xiaoou Tang

This paper proposes to learn high-performance deep ConvNets with sparse neural connections, referred to as sparse ConvNets, for face recognition.

Face Recognition

From random walks to distances on unweighted graphs

no code implementations NeurIPS 2015 Tatsunori B. Hashimoto, Yi Sun, Tommi S. Jaakkola

Using these techniques we generalize results on the degeneracy of hitting times and analyze a metric based on the Laplace transformed hitting time (LTHT).

DeepID3: Face Recognition with Very Deep Neural Networks

2 code implementations3 Feb 2015 Yi Sun, Ding Liang, Xiaogang Wang, Xiaoou Tang

Very deep neural networks recently achieved great success on general object recognition because of their superb learning capacity.

Face Identification Face Recognition +2

Metric recovery from directed unweighted graphs

no code implementations20 Nov 2014 Tatsunori B. Hashimoto, Yi Sun, Tommi S. Jaakkola

We demonstrate empirically that the estimator performs well on simulated examples as well as on real-world co-purchasing graphs even with a small number of points and degree scaling as low as $\log(n)$.

Deep Learning Face Representation from Predicting 10,000 Classes

no code implementations Conference 2014 Yi Sun, Xiaogang Wang, Xiaoou Tang

When learned as classifiers to recognize about 10, 000 face identities in the training set and configured to keep reducing the neuron numbers along the feature extraction hierarchy, these deep ConvNets gradually form compact identity-related features in the top layers with only a small number of hidden neurons.

Face Identification Face Verification

Deep Learning Face Representation from Predicting 10,000 Classes

3 code implementations1 Jan 2014 Yi Sun, Xiaogang Wang, Xiaoou Tang

When learned as classifiers to recognize about 10, 000 face identities in the training set and configured to keep reducing the neuron numbers along the feature extraction hierarchy, these deep ConvNets gradually form compact identity-related features in the top layers with only a small number of hidden neurons.

Face Identification Face Verification

Deep Convolutional Network Cascade for Facial Point Detection

no code implementations CVPR 2013 Yi Sun, Xiaogang Wang, Xiaoou Tang

At each level, the outputs of multiple networks are fused for robust and accurate estimation.

Natural Evolution Strategies

1 code implementation22 Jun 2011 Daan Wierstra, Tom Schaul, Tobias Glasmachers, Yi Sun, Jürgen Schmidhuber

This paper presents Natural Evolution Strategies (NES), a recent family of algorithms that constitute a more principled approach to black-box optimization than established evolutionary algorithms.

Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices

no code implementations NeurIPS 2010 Yi Sun, Jürgen Schmidhuber, Faustino J. Gomez

We present a new way of converting a reversible finite Markov chain into a nonreversible one, with a theoretical guarantee that the asymptotic variance of the MCMC estimator based on the non-reversible chain is reduced.

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