Search Results for author: Yixin Chen

Found 38 papers, 19 papers with code

One-Class Model for Fabric Defect Detection

1 code implementation20 Apr 2022 Hao Zhou, Yixin Chen, David Troendle, Byunghyun Jang

Our model takes advantage of a well-designed Gabor filter bank to analyze fabric texture.

Defect Detection

Learning Convolutional Neural Networks in the Frequency Domain

1 code implementation14 Apr 2022 Hengyue Pan, Yixin Chen, Xin Niu, Wenbo Zhou, Dongsheng Li

The most important motivation of this research is that we can use the straightforward element-wise multiplication operation to replace the image convolution in the frequency domain based on the Cross-Correlation Theorem, which obviously reduces the computation complexity.

PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs

no code implementations19 Mar 2022 Zehao Dong, Muhan Zhang, Fuhai Li, Yixin Chen

In this work, we propose a Parallelizable Attention-based Computation structure Encoder (PACE) that processes nodes simultaneously and encodes DAGs in parallel.

Neural Architecture Search

SEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment

no code implementations2 Mar 2022 Yixin Chen, Zhuotao Tian, Pengguang Chen, Shu Liu, Jiaya Jia

We revisit the one- and two-stage detector distillation tasks and present a simple and efficient semantic-aware framework to fill the gap between them.

Instance Segmentation Object Detection +1

PartAfford: Part-level Affordance Discovery from 3D Objects

no code implementations28 Feb 2022 Chao Xu, Yixin Chen, He Wang, Song-Chun Zhu, Yixin Zhu, Siyuan Huang

We propose a novel learning framework for PartAfford, which discovers part-level representations by leveraging only the affordance set supervision and geometric primitive regularization, without dense supervision.

Best of Both Worlds: Practical and Theoretically Optimal Submodular Maximization in Parallel

1 code implementation NeurIPS 2021 Yixin Chen, Tonmoy Dey, Alan Kuhnle

For the problem of maximizing a monotone, submodular function with respect to a cardinality constraint $k$ on a ground set of size $n$, we provide an algorithm that achieves the state-of-the-art in both its empirical performance and its theoretical properties, in terms of adaptive complexity, query complexity, and approximation ratio; that is, it obtains, with high probability, query complexity of $O(n)$ in expectation, adaptivity of $O(\log(n))$, and approximation ratio of nearly $1-1/e$.

Training Neural Networks for Solving 1-D Optimal Piecewise Linear Approximation

no code implementations14 Oct 2021 Hangcheng Dong, Jingxiao Liao, Yan Wang, Yixin Chen, Bingguo Liu, Dong Ye, Guodong Liu

Our main contributions are that we propose the theorems to characterize the optimal solution of the PWLA problem and present the LNN method for solving it.

Deep Structured Instance Graph for Distilling Object Detectors

1 code implementation ICCV 2021 Yixin Chen, Pengguang Chen, Shu Liu, LiWei Wang, Jiaya Jia

Effectively structuring deep knowledge plays a pivotal role in transfer from teacher to student, especially in semantic vision tasks.

Instance Segmentation Knowledge Distillation +2

YouRefIt: Embodied Reference Understanding with Language and Gesture

no code implementations ICCV 2021 Yixin Chen, Qing Li, Deqian Kong, Yik Lun Kei, Song-Chun Zhu, Tao Gao, Yixin Zhu, Siyuan Huang

To the best of our knowledge, this is the first embodied reference dataset that allows us to study referring expressions in daily physical scenes to understand referential behavior, human communication, and human-robot interaction.

CIM: Class-Irrelevant Mapping for Few-Shot Classification

no code implementations7 Sep 2021 Shuai Shao, Lei Xing, Yixin Chen, Yan-Jiang Wang, Bao-Di Liu, Yicong Zhou

(2) Use the FEM to extract the features of novel data (with few labeled samples and totally different categories from base data), then classify them with the to-be-designed classifier.

Classification Dictionary Learning +1

Exploring and Improving Mobile Level Vision Transformers

no code implementations30 Aug 2021 Pengguang Chen, Yixin Chen, Shu Liu, MingChang Yang, Jiaya Jia

We analyze the reason behind this phenomenon, and propose a novel irregular patch embedding module and adaptive patch fusion module to improve the performance.

Interpretable Drug Synergy Prediction with Graph Neural Networks for Human-AI Collaboration in Healthcare

no code implementations14 May 2021 Zehao Dong, Heming Zhang, Yixin Chen, Fuhai Li

Though deep learning algorithms are widely used in the drug synergy prediction problem, it is still an open problem to formulate the prediction model with biological meaning to investigate the mysterious mechanisms of synergy (MoS) for the human-AI collaboration in healthcare systems.

(Un)fairness in Post-operative Complication Prediction Models

no code implementations3 Nov 2020 Sandhya Tripathi, Bradley A. Fritz, Mohamed Abdelhack, Michael S. Avidan, Yixin Chen, Christopher R. King

With the current ongoing debate about fairness, explainability and transparency of machine learning models, their application in high-impact clinical decision-making systems must be scrutinized.

Decision Making Fairness

LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities

no code implementations ECCV 2020 Baoxiong Jia, Yixin Chen, Siyuan Huang, Yixin Zhu, Song-Chun Zhu

Understanding and interpreting human actions is a long-standing challenge and a critical indicator of perception in artificial intelligence.

Action Recognition Action Understanding +1

Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning

1 code implementation ICML 2020 Qing Li, Siyuan Huang, Yining Hong, Yixin Chen, Ying Nian Wu, Song-Chun Zhu

In this paper, we address these issues and close the loop of neural-symbolic learning by (1) introducing the \textbf{grammar} model as a \textit{symbolic prior} to bridge neural perception and symbolic reasoning, and (2) proposing a novel \textbf{back-search} algorithm which mimics the top-down human-like learning procedure to propagate the error through the symbolic reasoning module efficiently.

Question Answering Visual Question Answering

DEPARA: Deep Attribution Graph for Deep Knowledge Transferability

1 code implementation CVPR 2020 Jie Song, Yixin Chen, Jingwen Ye, Xinchao Wang, Chengchao Shen, Feng Mao, Mingli Song

In this paper, we propose the DEeP Attribution gRAph (DEPARA) to investigate the transferability of knowledge learned from PR-DNNs.

Model Selection Transfer Learning

PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points

no code implementations NeurIPS 2019 Siyuan Huang, Yixin Chen, Tao Yuan, Siyuan Qi, Yixin Zhu, Song-Chun Zhu

Detecting 3D objects from a single RGB image is intrinsically ambiguous, thus requiring appropriate prior knowledge and intermediate representations as constraints to reduce the uncertainties and improve the consistencies between the 2D image plane and the 3D world coordinate.

Monocular 3D Object Detection

Deep Model Transferability from Attribution Maps

1 code implementation NeurIPS 2019 Jie Song, Yixin Chen, Xinchao Wang, Chengchao Shen, Mingli Song

Exploring the transferability between heterogeneous tasks sheds light on their intrinsic interconnections, and consequently enables knowledge transfer from one task to another so as to reduce the training effort of the latter.

Transfer Learning

Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense

no code implementations ICCV 2019 Yixin Chen, Siyuan Huang, Tao Yuan, Siyuan Qi, Yixin Zhu, Song-Chun Zhu

We propose a new 3D holistic++ scene understanding problem, which jointly tackles two tasks from a single-view image: (i) holistic scene parsing and reconstruction---3D estimations of object bounding boxes, camera pose, and room layout, and (ii) 3D human pose estimation.

3D Human Pose Estimation Human-Object Interaction Detection +1

A Factored Generalized Additive Model for Clinical Decision Support in the Operating Room

1 code implementation29 Jul 2019 Zhicheng Cui, Bradley A Fritz, Christopher R King, Michael S Avidan, Yixin Chen

In this paper, we propose a factored generalized additive model (F-GAM) to preserve the model interpretability for targeted features while allowing a rich model for interaction with features fixed within the individual.

Additive models Respiratory Failure

Graph Neural Lasso for Dynamic Network Regression

1 code implementation25 Jul 2019 Yixin Chen, Lin Meng, Jiawei Zhang

Experimental results provided on two networked sequence datasets, i. e., Nasdaq-100 and METR-LA, show that GNL can address the network regression problem very well and is also very competitive among the existing approaches.

Estimating Feature-Label Dependence Using Gini Distance Statistics

1 code implementation5 Jun 2019 Silu Zhang, Xin Dang, Dao Nguyen, Dawn Wilkins, Yixin Chen

Uniform convergence bounds and asymptotic bounds are derived for the test statistics.

Density Estimation

Inductive Matrix Completion Based on Graph Neural Networks

3 code implementations ICLR 2020 Muhan Zhang, Yixin Chen

Under the extreme setting where not any side information is available other than the matrix to complete, can we still learn an inductive matrix completion model?

Matrix Completion Recommendation Systems +1

Inferring Shared Attention in Social Scene Videos

no code implementations CVPR 2018 Lifeng Fan, Yixin Chen, Ping Wei, Wenguan Wang, Song-Chun Zhu

We collect a new dataset VideoCoAtt from public TV show videos, containing 380 complex video sequences with more than 492, 000 frames that include diverse social scenes for shared attention study.

Frame Scene Understanding

Link Prediction Based on Graph Neural Networks

6 code implementations NeurIPS 2018 Muhan Zhang, Yixin Chen

The theory unifies a wide range of heuristics in a single framework, and proves that all these heuristics can be well approximated from local subgraphs.

Link Prediction

Weisfeiler-lehman neural machine for link prediction

1 code implementation KDD 2017 Muhan Zhang, Yixin Chen

Compared with traditional link prediction methods, Wlnm does not assume a particular link formation mechanism (such as common neighbors), but learns this mechanism from the graph itself.

Link Prediction

Extracting Actionability from Machine Learning Models by Sub-optimal Deterministic Planning

no code implementations3 Nov 2016 Qiang Lyu, Yixin Chen, Zhaorong Li, Zhicheng Cui, Ling Chen, Xing Zhang, Haihua Shen

Our work represents a new application of automated planning on an emerging and challenging machine learning paradigm.

Multi-Scale Convolutional Neural Networks for Time Series Classification

2 code implementations22 Mar 2016 Zhicheng Cui, Wenlin Chen, Yixin Chen

These methods are ad-hoc and separate the feature extraction part with the classification part, which limits their accuracy performance.

Classification Dynamic Time Warping +3

Optimal Action Extraction for Random Forests and Boosted Trees

1 code implementation13 Aug 2015 Zhicheng Cui, Wenlin Chen, Yujie He, Yixin Chen

To address this problem, we present a novel framework to post-process any ATM classifier to extract an optimal actionable plan that can change a given input to a desired class with a minimum cost.

Compressing Convolutional Neural Networks

no code implementations14 Jun 2015 Wenlin Chen, James T. Wilson, Stephen Tyree, Kilian Q. Weinberger, Yixin Chen

Convolutional neural networks (CNN) are increasingly used in many areas of computer vision.

Compressing Neural Networks with the Hashing Trick

2 code implementations19 Apr 2015 Wenlin Chen, James T. Wilson, Stephen Tyree, Kilian Q. Weinberger, Yixin Chen

As deep nets are increasingly used in applications suited for mobile devices, a fundamental dilemma becomes apparent: the trend in deep learning is to grow models to absorb ever-increasing data set sizes; however mobile devices are designed with very little memory and cannot store such large models.

SAS+ Planning as Satisfiability

no code implementations18 Jan 2014 Ruoyun Huang, Yixin Chen, Weixiong Zhang

We prove the correctness of the new encoding by establishing an isomorphism between the solution plans of SASE and that of STRIPS based encodings.

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