Search Results for author: Yu Cao

Found 64 papers, 22 papers with code

Incremental Learning on Food Instance Segmentation

no code implementations28 Jun 2023 Huu-Thanh Nguyen, Yu Cao, Chong-Wah Ngo, Wing-Kwong Chan

The power of the framework is a novel difficulty assessment model, which forecasts how challenging an unlabelled sample is to the latest trained instance segmentation model.

Incremental Learning Instance Segmentation +1

Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training

1 code implementation5 Jun 2023 Yibin Lei, Liang Ding, Yu Cao, Changtong Zan, Andrew Yates, DaCheng Tao

Dense retrievers have achieved impressive performance, but their demand for abundant training data limits their application scenarios.

Contrastive Learning Retrieval

Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations

no code implementations3 Jun 2023 Yu Cao, Jingrun Chen, Yixin Luo, Xiang Zhou

However, when the perturbation occurs earlier, the SDE model outperforms the ODE model, and we demonstrate that the error of sample generation due to pulse-shape error can be exponentially suppressed as the diffusion term's magnitude increases to infinity.

DETR-based Layered Clothing Segmentation and Fine-Grained Attribute Recognition

no code implementations17 Apr 2023 Hao Tian, Yu Cao, P. Y. Mok

Clothing segmentation and fine-grained attribute recognition are challenging tasks at the crossing of computer vision and fashion, which segment the entire ensemble clothing instances as well as recognize detailed attributes of the clothing products from any input human images.

AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models

no code implementations20 Mar 2023 Yu Cao, Xiangqiao Meng, P. Y. Mok, Xueting Liu, Tong-Yee Lee, Ping Li

Through multiple quantitative metrics evaluated on our dataset and a user study, we demonstrate AnimeDiffusion outperforms state-of-the-art GANs-based models for anime face line drawing colorization.

Colorization Image Reconstruction

Attention-Aware Anime Line Drawing Colorization

1 code implementation21 Dec 2022 Yu Cao, Hao Tian, P. Y. Mok

Automatic colorization of anime line drawing has attracted much attention in recent years since it can substantially benefit the animation industry.

Colorization Semantic correspondence

TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack

1 code implementation27 Oct 2022 Yu Cao, Dianqi Li, Meng Fang, Tianyi Zhou, Jun Gao, Yibing Zhan, DaCheng Tao

We present Twin Answer Sentences Attack (TASA), an adversarial attack method for question answering (QA) models that produces fluent and grammatical adversarial contexts while maintaining gold answers.

Adversarial Attack Question Answering

SpikeSim: An end-to-end Compute-in-Memory Hardware Evaluation Tool for Benchmarking Spiking Neural Networks

2 code implementations24 Oct 2022 Abhishek Moitra, Abhiroop Bhattacharjee, Runcong Kuang, Gokul Krishnan, Yu Cao, Priyadarshini Panda

To this end, we propose SpikeSim, a tool that can perform realistic performance, energy, latency and area evaluation of IMC-mapped SNNs.


FEC: Fast Euclidean Clustering for Point Cloud Segmentation

1 code implementation16 Aug 2022 Yu Cao, Yancheng Wang, Yifei Xue, Huiqing Zhang, Yizhen Lao

Segmentation from point cloud data is essential in many applications such as remote sensing, mobile robots, or autonomous cars.

Clustering Instance Segmentation +2

DeePKS+ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials

no code implementations21 Jun 2022 Wenfei Li, Qi Ou, Yixiao Chen, Yu Cao, Renxi Liu, Chunyi Zhang, Daye Zheng, Chun Cai, Xifan Wu, Han Wang, Mohan Chen, Linfeng Zhang

However, for high-level QM methods, such as density functional theory (DFT) at the meta-GGA level and/or with exact exchange, quantum Monte Carlo, etc., generating a sufficient amount of data for training a ML potential has remained computationally challenging due to their high cost.

Efficient Neural Network

Learning Optimal Flows for Non-Equilibrium Importance Sampling

1 code implementation20 Jun 2022 Yu Cao, Eric Vanden-Eijnden

On the theory side, we discuss how to tailor the velocity field to the target and establish general conditions under which the proposed estimator is a perfect estimator with zero-variance.

Phrase-level Textual Adversarial Attack with Label Preservation

1 code implementation Findings (NAACL) 2022 Yibin Lei, Yu Cao, Dianqi Li, Tianyi Zhou, Meng Fang, Mykola Pechenizkiy

Generating high-quality textual adversarial examples is critical for investigating the pitfalls of natural language processing (NLP) models and further promoting their robustness.

Adversarial Attack

Interpretable Proof Generation via Iterative Backward Reasoning

1 code implementation NAACL 2022 Hanhao Qu, Yu Cao, Jun Gao, Liang Ding, Ruifeng Xu

We present IBR, an Iterative Backward Reasoning model to solve the proof generation tasks on rule-based Question Answering (QA), where models are required to reason over a series of textual rules and facts to find out the related proof path and derive the final answer.

Question Answering

COIN: Communication-Aware In-Memory Acceleration for Graph Convolutional Networks

no code implementations15 May 2022 Sumit K. Mandal, Gokul Krishnan, A. Alper Goksoy, Gopikrishnan Ravindran Nair, Yu Cao, Umit Y. Ogras

Besides accelerating the computation using custom compute elements (CE) and in-memory computing, COIN aims at minimizing the intra- and inter-CE communication in GCN operations to optimize the performance and energy efficiency.

A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation

1 code implementation ACL 2022 Yu Cao, Wei Bi, Meng Fang, Shuming Shi, DaCheng Tao

To alleviate the above data issues, we propose a data manipulation method, which is model-agnostic to be packed with any persona-based dialogue generation model to improve its performance.

Dialogue Generation

Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and Understanding

1 code implementation16 Apr 2022 Changtong Zan, Liang Ding, Li Shen, Yu Cao, Weifeng Liu, DaCheng Tao

For multilingual sequence-to-sequence pretrained language models (multilingual Seq2Seq PLMs), e. g. mBART, the self-supervised pretraining task is trained on a wide range of monolingual languages, e. g. 25 languages from CommonCrawl, while the downstream cross-lingual tasks generally progress on a bilingual language subset, e. g. English-German, making there exists the data discrepancy, namely domain discrepancy, and cross-lingual learning objective discrepancy, namely task discrepancy, between the pretraining and finetuning stages.

Cross-Lingual Natural Language Inference Text Generation +2

A Knowledge-Based Decision Support System for In Vitro Fertilization Treatment

no code implementations27 Jan 2022 Xizhe Wang, Ning Zhang, Jia Wang, Jing Ni, Xinzi Sun, John Zhang, Zitao Liu, Yu Cao, Benyuan Liu

To improve the IVF success rate, we propose a knowledge-based decision support system that can provide medical advice on the treatment protocol and medication adjustment for each patient visit during IVF treatment cycle.


Swin-Pose: Swin Transformer Based Human Pose Estimation

no code implementations19 Jan 2022 Zinan Xiong, Chenxi Wang, Ying Li, Yan Luo, Yu Cao

We are interested in exploring its capability in human pose estimation, and thus propose a novel model based on transformer architecture, enhanced with a feature pyramid fusion structure.

Pose Estimation

A Joint Beamforming Design and Integrated CPM-LFM Signal for Dual-functional Radar-communication Systems

no code implementations18 Dec 2021 Yu Cao, QiYue Yu

Similarly to the conception of communication rate, this paper defines radar rate to unify the DFRC system.

Plurality and Quantification in Graph Representation of Meaning

1 code implementation13 Dec 2021 Yu Cao

In this thesis we present a semantic representation formalism based on directed graphs and explore its linguistic adequacy and explanatory benefits in the semantics of plurality and quantification.

SIAM: Chiplet-based Scalable In-Memory Acceleration with Mesh for Deep Neural Networks

no code implementations14 Aug 2021 Gokul Krishnan, Sumit K. Mandal, Manvitha Pannala, Chaitali Chakrabarti, Jae-sun Seo, Umit Y. Ogras, Yu Cao

In-memory computing (IMC) on a monolithic chip for deep learning faces dramatic challenges on area, yield, and on-chip interconnection cost due to the ever-increasing model sizes.


Underwater inspection and intervention dataset

no code implementations28 Jul 2021 Tomasz Luczynski, Jonatan Scharff Willners, Elizabeth Vargas, Joshua Roe, Shida Xu, Yu Cao, Yvan Petillot, Sen Wang

This paper presents a novel dataset for the development of visual navigation and simultaneous localisation and mapping (SLAM) algorithms as well as for underwater intervention tasks.

Visual Navigation

Impact of On-Chip Interconnect on In-Memory Acceleration of Deep Neural Networks

no code implementations6 Jul 2021 Gokul Krishnan, Sumit K. Mandal, Chaitali Chakrabarti, Jae-sun Seo, Umit Y. Ogras, Yu Cao

In this technique, we use analytical models of NoC to evaluate end-to-end communication latency of any given DNN.

Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems

no code implementations4 May 2021 Xiaocong Du, Bhargav Bhushanam, Jiecao Yu, Dhruv Choudhary, Tianxiang Gao, Sherman Wong, Louis Feng, Jongsoo Park, Yu Cao, Arun Kejariwal

Our method leverages structured sparsification to reduce computational cost without hurting the model capacity at the end of offline training so that a full-size model is available in the recurring training stage to learn new data in real-time.

Recommendation Systems

Financial Markets Prediction with Deep Learning

no code implementations5 Apr 2021 Jia Wang, Tong Sun, Benyuan Liu, Yu Cao, Degang Wang

Financial markets are difficult to predict due to its complex systems dynamics.

BIG-bench Machine Learning

DAGN: Discourse-Aware Graph Network for Logical Reasoning

2 code implementations NAACL 2021 Yinya Huang, Meng Fang, Yu Cao, LiWei Wang, Xiaodan Liang

The model encodes discourse information as a graph with elementary discourse units (EDUs) and discourse relations, and learns the discourse-aware features via a graph network for downstream QA tasks.

Logical Reasoning

Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation

1 code implementation2 Mar 2021 Yu Cao, Liang Ding, Zhiliang Tian, Meng Fang

Dialogue generation models face the challenge of producing generic and repetitive responses.

Dialogue Generation

A Learning-Based Tune-Free Control Framework for Large Scale Autonomous Driving System Deployment

no code implementations9 Nov 2020 Yu Wang, Shu Jiang, Weiman Lin, Yu Cao, Longtao Lin, Jiangtao Hu, Jinghao Miao, Qi Luo

This paper presents the design of a tune-free (human-out-of-the-loop parameter tuning) control framework, aiming at accelerating large scale autonomous driving system deployed on various vehicles and driving environments.

Autonomous Driving Bayesian Optimization

A Progressive Sub-Network Searching Framework for Dynamic Inference

no code implementations11 Sep 2020 Li Yang, Zhezhi He, Yu Cao, Deliang Fan

Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently.

Model Compression

Retinopathy of Prematurity Stage Diagnosis Using Object Segmentation and Convolutional Neural Networks

no code implementations3 Apr 2020 Alexander Ding, Qilei Chen, Yu Cao, Benyuan Liu

This paper builds upon the success of previous models and develops a novel architecture, which combines object segmentation and convolutional neural networks (CNN) to construct an effective classifier of ROP stages 1-3 based on neonatal retinal images.

Semantic Segmentation

Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images

2 code implementations ECCV 2020 Heming Zhu, Yu Cao, Hang Jin, Weikai Chen, Dong Du, Zhangye Wang, Shuguang Cui, Xiaoguang Han

High-fidelity clothing reconstruction is the key to achieving photorealism in a wide range of applications including human digitization, virtual try-on, etc.

Virtual Try-on

Pseudo-Labeling for Small Lesion Detection on Diabetic Retinopathy Images

no code implementations26 Mar 2020 Qilei Chen, Ping Liu, Jing Ni, Yu Cao, Benyuan Liu, Honggang Zhang

The first one is that our dataset is not fully labeled, i. e., only a subset of all lesion instances are marked.

Lesion Detection object-detection +1

3D Aggregated Faster R-CNN for General Lesion Detection

no code implementations29 Jan 2020 Ning Zhang, Yu Cao, Benyuan Liu, Yan Luo

This classifier branch is equipped with Feature Aggregation and Local Magnification Layers to enhance the classifier branch.

Computed Tomography (CT) Lesion Detection +2

Colorectal Polyp Segmentation by U-Net with Dilation Convolution

no code implementations26 Dec 2019 Xinzi Sun, Pengfei Zhang, Dechun Wang, Yu Cao, Benyuan Liu

The model we design consists of an encoder to extract multi-scale semantic features and a decoder to expand the feature maps to a polyp segmentation map.

Mini Lesions Detection on Diabetic Retinopathy Images via Large Scale CNN Features

no code implementations19 Nov 2019 Qilei Chen, Xinzi Sun, Ning Zhang, Yu Cao, Benyuan Liu

We analyze the lesion-vs-image scale carefully and propose a large-size feature pyramid network (LFPN) to preserve more image details for mini lesion instance detection.

Lesion Detection object-detection +2

Unsupervised Domain Adaptation on Reading Comprehension

1 code implementation13 Nov 2019 Yu Cao, Meng Fang, Baosheng Yu, Joey Tianyi Zhou

On the other hand, it further reduces domain distribution discrepancy through conditional adversarial learning across domains.

Reading Comprehension Unsupervised Domain Adaptation

Structural Pruning in Deep Neural Networks: A Small-World Approach

no code implementations11 Nov 2019 Gokul Krishnan, Xiaocong Du, Yu Cao

Inspired by the observation that brain networks follow the Small-World model, we propose a novel structural pruning scheme, which includes (1) hierarchically trimming the network into a Small-World model before training, (2) training the network for a given dataset, and (3) optimizing the network for accuracy.

AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy

no code implementations5 Sep 2019 Dechun Wang, Ning Zhang, Xinzi Sun, Pengfei Zhang, Chenxi Zhang, Yu Cao, Benyuan Liu

Though challenging, with the great advances in object detection techniques, automated polyp detection still demonstrates a great potential in reducing the false negative rate while maintaining a high precision.

object-detection Object Detection

A Deep Reinforcement Learning Approach to Multi-component Job Scheduling in Edge Computing

no code implementations26 Aug 2019 Zhi Cao, Honggang Zhang, Yu Cao, Benyuan Liu

We are interested in the optimal scheduling of a collection of multi-component application jobs in an edge computing system that consists of geo-distributed edge computing nodes connected through a wide area network.

Edge-computing reinforcement-learning +2

Multi-Stream Single Shot Spatial-Temporal Action Detection

no code implementations22 Aug 2019 Pengfei Zhang, Yu Cao, Benyuan Liu

We present a 3D Convolutional Neural Networks (CNNs) based single shot detector for spatial-temporal action detection tasks.

Action Detection Optical Flow Estimation

Automatic Compiler Based FPGA Accelerator for CNN Training

no code implementations15 Aug 2019 Shreyas Kolala Venkataramanaiah, Yufei Ma, Shihui Yin, Eriko Nurvithadhi, Aravind Dasu, Yu Cao, Jae-sun Seo

Training of convolutional neural networks (CNNs)on embedded platforms to support on-device learning is earning vital importance in recent days.

Single-Net Continual Learning with Progressive Segmented Training (PST)

no code implementations28 May 2019 Xiaocong Du, Gouranga Charan, Frank Liu, Yu Cao

Such a system requires learning from the data stream, training the model to preserve previous information and adapt to a new task, and generating a single-headed vector for future inference.

Continual Learning

Efficient Network Construction through Structural Plasticity

no code implementations27 May 2019 Xiaocong Du, Zheng Li, Yufei Ma, Yu Cao

A typical training pipeline to mitigate over-parameterization is to pre-define a DNN structure first with redundant learning units (filters and neurons) under the goal of high accuracy, then to prune redundant learning units after training with the purpose of efficient inference.

CGaP: Continuous Growth and Pruning for Efficient Deep Learning

no code implementations27 May 2019 Xiaocong Du, Zheng Li, Yu Cao

Today a canonical approach to reduce the computation cost of Deep Neural Networks (DNNs) is to pre-define an over-parameterized model before training to guarantee the learning capacity, and then prune unimportant learning units (filters and neurons) during training to improve model compactness.

BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering

1 code implementation NAACL 2019 Yu Cao, Meng Fang, DaCheng Tao

Graph convolutional networks are used to obtain a relation-aware representation of nodes for entity graphs built from documents with multi-level features.

Question Answering

Large-Scale Neuromorphic Spiking Array Processors: A quest to mimic the brain

no code implementations23 May 2018 Chetan Singh Thakur, Jamal Molin, Gert Cauwenberghs, Giacomo Indiveri, Kundan Kumar, Ning Qiao, Johannes Schemmel, Runchun Wang, Elisabetta Chicca, Jennifer Olson Hasler, Jae-sun Seo, Shimeng Yu, Yu Cao, André van Schaik, Ralph Etienne-Cummings

Neuromorphic engineering (NE) encompasses a diverse range of approaches to information processing that are inspired by neurobiological systems, and this feature distinguishes neuromorphic systems from conventional computing systems.

Generative Sensing: Transforming Unreliable Sensor Data for Reliable Recognition

no code implementations8 Jan 2018 Lina Karam, Tejas Borkar, Yu Cao, Junseok Chae

The proposed generative sensing framework aims at transforming low-end, low-quality sensor data into higher quality sensor data in terms of achieved classification accuracy.

Image Generation

DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning

1 code implementation9 Jan 2017 Tian Zhao, Xiaobing Huang, Yu Cao

In this paper, we present DeepDSL, a domain specific language (DSL) embedded in Scala, that compiles deep networks written in DeepDSL to Java source code.

DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment

1 code implementation17 Jun 2016 Chang Liu, Yu Cao, Yan Luo, Guanling Chen, Vinod Vokkarane, Yunsheng Ma

We applied our proposed approach to two real-world food image data sets (UEC-256 and Food-101) and achieved impressive results.

Cloud Computing Fine-Grained Image Recognition

Reducing the Model Order of Deep Neural Networks Using Information Theory

no code implementations16 May 2016 Ming Tu, Visar Berisha, Yu Cao, Jae-sun Seo

In this paper, we propose a method to compress deep neural networks by using the Fisher Information metric, which we estimate through a stochastic optimization method that keeps track of second-order information in the network.

General Classification Network Pruning +2

Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces

no code implementations5 Sep 2015 Yuewei Lin, Jing Chen, Yu Cao, Youjie Zhou, Lingfeng Zhang, Yuan Yan Tang, Song Wang

By adopting a natural and widely used assumption -- "the data samples from the same class should lay on a low-dimensional subspace, even if they come from different domains", the proposed method circumvents the limitation of the global domain shift, and solves the cross-domain recognition by finding the compact joint subspaces of source and target domain.

Domain Adaptation Object Recognition +2

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