Search Results for author: Yang Cao

Found 120 papers, 49 papers with code

Towards Realistic Data Generation for Real-World Super-Resolution

no code implementations11 Jun 2024 Long Peng, Wenbo Li, Renjing Pei, Jingjing Ren, Xueyang Fu, Yang Wang, Yang Cao, Zheng-Jun Zha

Existing image super-resolution (SR) techniques often fail to generalize effectively in complex real-world settings due to the significant divergence between training data and practical scenarios.

Image Super-Resolution

Introducing Competitive Mechanism to Differential Evolution for Numerical Optimization

no code implementations8 Jun 2024 Rui Zhong, Yang Cao, Enzhi Zhang, Masaharu Munetomo

This paper introduces a novel competitive mechanism into differential evolution (DE), presenting an effective DE variant named competitive DE (CDE).

Large Language Model Assisted Adversarial Robustness Neural Architecture Search

1 code implementation8 Jun 2024 Rui Zhong, Yang Cao, Jun Yu, Masaharu Munetomo

Motivated by the potential of large language models (LLMs) as optimizers for solving combinatorial optimization problems, this paper proposes a novel LLM-assisted optimizer (LLMO) to address adversarial robustness neural architecture search (ARNAS), a specific application of combinatorial optimization.

Adversarial Robustness Combinatorial Optimization +3

Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning

1 code implementation5 Jun 2024 Saber Malekmohammadi, YaoLiang Yu, Yang Cao

Furthermore, there is often heterogeneity in batch and/or dataset size of clients, which as shown, results in extra variation in the DP noise level across clients model updates.

Federated Learning

Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection

1 code implementation2 Jun 2024 Yang Cao, Yihan Zeng, Hang Xu, Dan Xu

3D-NOD is further extended with an Enrichment strategy that significantly enriches the novel object distribution in the training scenes, and then enhances the model's ability to localize more novel objects.

3D Object Detection Object +2

Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails

no code implementations27 May 2024 Haichao Sha, Yang Cao, Yong liu, Yuncheng Wu, Ruixuan Liu, Hong Chen

However, recent studies have shown that the gradients in deep learning exhibit a heavy-tail phenomenon, that is, the tails of the gradient have infinite variance, which may lead to excessive clipping loss to the gradients with existing DPSGD mechanisms.

Benchmarking General Purpose In-Context Learning

1 code implementation27 May 2024 Fan Wang, Chuan Lin, Yang Cao, Yu Kang

It is desirable to further enhance the generality and capability of ICL, which gives rise to the concept of general-purpose in-context learning (GPICL).

Benchmarking In-Context Learning +1

Mamba4KT:An Efficient and Effective Mamba-based Knowledge Tracing Model

no code implementations26 May 2024 Yang Cao, Wei zhang

Recognizing the significance of prioritizing model efficiency and resource usage in knowledge tracing, we introduce Mamba4KT.

Knowledge Tracing

5W1H Extraction With Large Language Models

no code implementations25 May 2024 Yang Cao, Yangsong Lan, Feiyan Zhai, Piji Li

The extraction of essential news elements through the 5W1H framework (\textit{What}, \textit{When}, \textit{Where}, \textit{Why}, \textit{Who}, and \textit{How}) is critical for event extraction and text summarization.

Domain Adaptation Event Extraction +1

EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views

no code implementations22 May 2024 Yuhang Yang, Wei Zhai, Chengfeng Wang, Chengjun Yu, Yang Cao, Zheng-Jun Zha

For the egocentric HOI, in addition to perceiving semantics e. g., ''what'' interaction is occurring, capturing ''where'' the interaction specifically manifests in 3D space is also crucial, which links the perception and operation.

Human-Object Interaction Detection Object

HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization

1 code implementation13 May 2024 Shun Takagi, Li Xiong, Fumiyuki Kato, Yang Cao, Masatoshi Yoshikawa

Human mobility data offers valuable insights for many applications such as urban planning and pandemic response, but its use also raises privacy concerns.

Multi-Task Learning

Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution

no code implementations11 May 2024 Long Peng, Yang Cao, Renjing Pei, Wenbo Li, Jiaming Guo, Xueyang Fu, Yang Wang, Zheng-Jun Zha

These convolutions are integrated in parallel with a novel linear weighting mechanism to form an Adaptive Directional Gradient Convolution (DGConv), which adaptively weights and fuses the basic directional gradients to improve the gradient arrangement perception capability for both regular and irregular textures.

Image Super-Resolution

Bidirectional Progressive Transformer for Interaction Intention Anticipation

no code implementations9 May 2024 Zichen Zhang, Hongchen Luo, Wei Zhai, Yang Cao, Yu Kang

Building upon this relationship, a novel Bidirectional prOgressive Transformer (BOT), which introduces a Bidirectional Progressive mechanism into the anticipation of interaction intention is established.

Trajectory Forecasting

MambaPupil: Bidirectional Selective Recurrent model for Event-based Eye tracking

no code implementations18 Apr 2024 Zhong Wang, Zengyu Wan, Han Han, Bohao Liao, Yuliang Wu, Wei Zhai, Yang Cao, Zheng-Jun Zha

Event-based eye tracking has shown great promise with the high temporal resolution and low redundancy provided by the event camera.

Data Augmentation

The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report

3 code implementations16 Apr 2024 Bin Ren, Nancy Mehta, Radu Timofte, Hongyuan Yu, Cheng Wan, Yuxin Hong, Bingnan Han, Zhuoyuan Wu, Yajun Zou, Yuqing Liu, Jizhe Li, Keji He, Chao Fan, Heng Zhang, Xiaolin Zhang, Xuanwu Yin, Kunlong Zuo, Bohao Liao, Peizhe Xia, Long Peng, Zhibo Du, Xin Di, Wangkai Li, Yang Wang, Wei Zhai, Renjing Pei, Jiaming Guo, Songcen Xu, Yang Cao, ZhengJun Zha, Yan Wang, Yi Liu, Qing Wang, Gang Zhang, Liou Zhang, Shijie Zhao, Long Sun, Jinshan Pan, Jiangxin Dong, Jinhui Tang, Xin Liu, Min Yan, Menghan Zhou, Yiqiang Yan, Yixuan Liu, Wensong Chan, Dehua Tang, Dong Zhou, Li Wang, Lu Tian, Barsoum Emad, Bohan Jia, Junbo Qiao, Yunshuai Zhou, Yun Zhang, Wei Li, Shaohui Lin, Shenglong Zhou, Binbin Chen, Jincheng Liao, Suiyi Zhao, Zhao Zhang, Bo wang, Yan Luo, Yanyan Wei, Feng Li, Mingshen Wang, Yawei Li, Jinhan Guan, Dehua Hu, Jiawei Yu, Qisheng Xu, Tao Sun, Long Lan, Kele Xu, Xin Lin, Jingtong Yue, Lehan Yang, Shiyi Du, Lu Qi, Chao Ren, Zeyu Han, YuHan Wang, Chaolin Chen, Haobo Li, Mingjun Zheng, Zhongbao Yang, Lianhong Song, Xingzhuo Yan, Minghan Fu, Jingyi Zhang, Baiang Li, Qi Zhu, Xiaogang Xu, Dan Guo, Chunle Guo, Jiadi Chen, Huanhuan Long, Chunjiang Duanmu, Xiaoyan Lei, Jie Liu, Weilin Jia, Weifeng Cao, Wenlong Zhang, Yanyu Mao, Ruilong Guo, Nihao Zhang, Qian Wang, Manoj Pandey, Maksym Chernozhukov, Giang Le, Shuli Cheng, Hongyuan Wang, Ziyan Wei, Qingting Tang, Liejun Wang, Yongming Li, Yanhui Guo, Hao Xu, Akram Khatami-Rizi, Ahmad Mahmoudi-Aznaveh, Chih-Chung Hsu, Chia-Ming Lee, Yi-Shiuan Chou, Amogh Joshi, Nikhil Akalwadi, Sampada Malagi, Palani Yashaswini, Chaitra Desai, Ramesh Ashok Tabib, Ujwala Patil, Uma Mudenagudi

In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.

Image Super-Resolution

PROMPT-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression

no code implementations30 Mar 2024 Muhammad Asif Ali, ZhengPing Li, Shu Yang, Keyuan Cheng, Yang Cao, Tianhao Huang, Lijie Hu, Lu Yu, Di Wang

Large language models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks.

GSM8K Relation

TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models

no code implementations CVPR 2024 Zhongwei Zhang, Fuchen Long, Yingwei Pan, Zhaofan Qiu, Ting Yao, Yang Cao, Tao Mei

Next, TRIP executes a residual-like dual-path scheme for noise prediction: 1) a shortcut path that directly takes image noise prior as the reference noise of each frame to amplify the alignment between the first frame and subsequent frames; 2) a residual path that employs 3D-UNet over noised video and static image latent codes to enable inter-frame relational reasoning, thereby easing the learning of the residual noise for each frame.

Image to Video Generation Relational Reasoning +1

Anomaly Detection Based on Isolation Mechanisms: A Survey

no code implementations16 Mar 2024 Yang Cao, Haolong Xiang, Hang Zhang, Ye Zhu, Kai Ming Ting

Anomaly detection is a longstanding and active research area that has many applications in domains such as finance, security, and manufacturing.

Unsupervised Anomaly Detection

Intention-driven Ego-to-Exo Video Generation

no code implementations14 Mar 2024 Hongchen Luo, Kai Zhu, Wei Zhai, Yang Cao

Finally, the inferred human movement and high-level action descriptions jointly guide the generation of exocentric motion and interaction content (i. e., corresponding optical flow and occlusion maps) in the backward process of the diffusion model, ultimately warping them into the corresponding exocentric video.

Optical Flow Estimation Stereo Matching +1

Event-based Asynchronous HDR Imaging by Temporal Incident Light Modulation

no code implementations14 Mar 2024 Yuliang Wu, Ganchao Tan, Jinze Chen, Wei Zhai, Yang Cao, Zheng-Jun Zha

In this paper, we propose AsynHDR, a Pixel-Asynchronous HDR imaging system, based on key insights into the challenges in HDR imaging and the unique event-generating mechanism of Dynamic Vision Sensors (DVS).

Knowledge Graph Assisted Automatic Sports News Writing

no code implementations17 Feb 2024 Yang Cao, Xinyi Chen, Xin Zhang, Siying Li

In this paper, we present a novel method for automatically generating sports news, which employs a unique algorithm that extracts pivotal moments from live text broadcasts and uses them to create an initial draft of the news.

Knowledge Graph Completion

Collaborative Computing in Non-Terrestrial Networks: A Multi-Time-Scale Deep Reinforcement Learning Approach

no code implementations7 Feb 2024 Yang Cao, Shao-Yu Lien, Ying-Chang Liang, Dusit Niyato, Xuemin, Shen

To address the above challenges, in this paper, a multi-time-scale deep reinforcement learning (DRL) scheme is developed for achieving the radio resource optimization in NTNs, in which the LEO satellite and user equipment (UE) collaborate with each other to perform individual decision-making tasks with different control cycles.

Decision Making

Collaborative Deep Reinforcement Learning for Resource Optimization in Non-Terrestrial Networks

no code implementations6 Feb 2024 Yang Cao, Shao-Yu Lien, Ying-Chang Liang, Dusit Niyato, Xuemin, Shen

Non-terrestrial networks (NTNs) with low-earth orbit (LEO) satellites have been regarded as promising remedies to support global ubiquitous wireless services.

Decision Making

ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization

no code implementations13 Jan 2024 Kourosh Darvish, Marta Skreta, Yuchi Zhao, Naruki Yoshikawa, Sagnik Som, Miroslav Bogdanovic, Yang Cao, Han Hao, Haoping Xu, Alán Aspuru-Guzik, Animesh Garg, Florian Shkurti

Despite the many benefits incurred by the integration of advanced and special-purpose lab equipment, many aspects of experimentation are still manually conducted by chemists, for example, polishing an electrode in electrochemistry experiments.

Scheduling

Lightweight Adaptive Feature De-drifting for Compressed Image Classification

no code implementations3 Jan 2024 Long Peng, Yang Cao, Yuejin Sun, Yang Wang

However, it is not an ideal choice to use these JPEG artifact removal methods as a pre-processing for compressed image classification for the following reasons: 1.

Classification Image Classification +1

TMP: Temporal Motion Propagation for Online Video Super-Resolution

1 code implementation15 Dec 2023 Zhengqiang Zhang, Ruihuang Li, Shi Guo, Yang Cao, Lei Zhang

Online video super-resolution (online-VSR) highly relies on an effective alignment module to aggregate temporal information, while the strict latency requirement makes accurate and efficient alignment very challenging.

Video Super-Resolution

LEMON: Learning 3D Human-Object Interaction Relation from 2D Images

no code implementations CVPR 2024 Yuhang Yang, Wei Zhai, Hongchen Luo, Yang Cao, Zheng-Jun Zha

Which underexploit certain correlations between the interaction counterparts (human and object), and struggle to address the uncertainty in interactions.

Human-Object Interaction Detection Object +1

TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learning

no code implementations7 Dec 2023 Shuangmei Wang, Yang Cao, Tieru Wu

Few-shot class-incremental learning (FSCIL) struggles to incrementally recognize novel classes from few examples without catastrophic forgetting of old classes or overfitting to new classes.

Few-Shot Class-Incremental Learning Incremental Learning +1

Likelihood-Aware Semantic Alignment for Full-Spectrum Out-of-Distribution Detection

1 code implementation4 Dec 2023 Fan Lu, Kai Zhu, Kecheng Zheng, Wei Zhai, Yang Cao

Full-spectrum out-of-distribution (F-OOD) detection aims to accurately recognize in-distribution (ID) samples while encountering semantic and covariate shifts simultaneously.

Out-of-Distribution Detection

GhostVec: A New Threat to Speaker Privacy of End-to-End Speech Recognition System

no code implementations17 Nov 2023 Xiaojiao Chen, Sheng Li, Jiyi Li, Hao Huang, Yang Cao, Liang He

This paper demonstrates that an attacker can extract speaker information by querying speaker-adapted speech recognition (ASR) systems.

Decoder Privacy Preserving +3

Reprogramming Self-supervised Learning-based Speech Representations for Speaker Anonymization

no code implementations17 Nov 2023 Xiaojiao Chen, Sheng Li, Jiyi Li, Hao Huang, Yang Cao, Liang He

Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity.

Self-Supervised Learning

Edge-assisted U-Shaped Split Federated Learning with Privacy-preserving for Internet of Things

no code implementations8 Nov 2023 Hengliang Tang, Zihang Zhao, Detian Liu, Yang Cao, Shiqiang Zhang, Siqing You

To address these challenges, we present an innovative Edge-assisted U-Shaped Split Federated Learning (EUSFL) framework, which harnesses the high-performance capabilities of edge servers to assist IoT devices in model training and optimization process.

Federated Learning Privacy Preserving

Integrated Distributed Semantic Communication and Over-the-air Computation for Cooperative Spectrum Sensing

no code implementations8 Nov 2023 Peng Yi, Yang Cao, Xin Kang, Ying-Chang Liang

Extensive simulations verify the superiority of ICC-CSS compared with various conventional CSS schemes in terms of detection performance, robustness to SNR variations in both sensing and reporting channels, as well as scalability with respect to the number of samples and sensors.

Deep Learning-Empowered Semantic Communication Systems with a Shared Knowledge Base

no code implementations6 Nov 2023 Peng Yi, Yang Cao, Xin Kang, Ying-Chang Liang

With the aid of the shared knowledge base, the proposed system integrates the message and corresponding knowledge from the shared knowledge base to obtain the residual information, which enables the system to transmit fewer symbols without semantic performance degradation.

Sentence Sentence Similarity

CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection

1 code implementation NeurIPS 2023 Yang Cao, Yihan Zeng, Hang Xu, Dan Xu

Open-vocabulary 3D Object Detection (OV-3DDet) aims to detect objects from an arbitrary list of categories within a 3D scene, which remains seldom explored in the literature.

3D Object Detection Object +3

Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation

2 code implementations22 Sep 2023 Wei Zhai, Pingyu Wu, Kai Zhu, Yang Cao, Feng Wu, Zheng-Jun Zha

In addition, our method also achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets.

Object Weakly-Supervised Object Localization +2

ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy

1 code implementation23 Aug 2023 Fumiyuki Kato, Li Xiong, Shun Takagi, Yang Cao, Masatoshi Yoshikawa

In this study, we present Uldp-FL, a novel FL framework designed to guarantee user-level DP in cross-silo FL where a single user's data may belong to multiple silos.

Federated Learning

Cones 2: Customizable Image Synthesis with Multiple Subjects

1 code implementation30 May 2023 Zhiheng Liu, Yifei Zhang, Yujun Shen, Kecheng Zheng, Kai Zhu, Ruili Feng, Yu Liu, Deli Zhao, Jingren Zhou, Yang Cao

Synthesizing images with user-specified subjects has received growing attention due to its practical applications.

Image Generation

Ripple Knowledge Graph Convolutional Networks For Recommendation Systems

no code implementations2 May 2023 Chen Li, Yang Cao, Ye Zhu, Debo Cheng, Chengyuan Li, Yasuhiko Morimoto

Using knowledge graphs to assist deep learning models in making recommendation decisions has recently been proven to effectively improve the model's interpretability and accuracy.

Knowledge Graphs Recommendation Systems

E-MLB: Multilevel Benchmark for Event-Based Camera Denoising

1 code implementation21 Mar 2023 Saizhe Ding, Jinze Chen, Yang Wang, Yu Kang, Weiguo Song, Jie Cheng, Yang Cao

Event cameras, such as dynamic vision sensors (DVS), are biologically inspired vision sensors that have advanced over conventional cameras in high dynamic range, low latency and low power consumption, showing great application potential in many fields.

Denoising

Spatial-Aware Token for Weakly Supervised Object Localization

1 code implementation ICCV 2023 Pingyu Wu, Wei Zhai, Yang Cao, Jiebo Luo, Zheng-Jun Zha

Specifically, a spatial token is first introduced in the input space to aggregate representations for localization task.

Object Weakly-Supervised Object Localization

Grounding 3D Object Affordance from 2D Interactions in Images

1 code implementation ICCV 2023 Yuhang Yang, Wei Zhai, Hongchen Luo, Yang Cao, Jiebo Luo, Zheng-Jun Zha

Comprehensive experiments on PIAD demonstrate the reliability of the proposed task and the superiority of our method.

Object

Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection

1 code implementation CVPR 2023 Fan Lu, Kai Zhu, Wei Zhai, Kecheng Zheng, Yang Cao

Semantically coherent out-of-distribution (SCOOD) detection aims to discern outliers from the intended data distribution with access to unlabeled extra set.

Out-of-Distribution Detection

Cones: Concept Neurons in Diffusion Models for Customized Generation

1 code implementation9 Mar 2023 Zhiheng Liu, Ruili Feng, Kai Zhu, Yifei Zhang, Kecheng Zheng, Yu Liu, Deli Zhao, Jingren Zhou, Yang Cao

Concatenating multiple clusters of concept neurons can vividly generate all related concepts in a single image.

P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classification

1 code implementation2 Jan 2023 Shuangmei Wang, Rui Ma, Tieru Wu, Yang Cao

Inspired by the distribution calibration technique which utilizes the distribution or statistics of the base classes to calibrate the data for few-shot tasks, we propose a novel discrete data calibration operation which is more suitable for NN-based few-shot classification.

Classification Few-Shot Learning

Leverage Interactive Affinity for Affordance Learning

1 code implementation CVPR 2023 Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, DaCheng Tao

Perceiving potential "action possibilities" (i. e., affordance) regions of images and learning interactive functionalities of objects from human demonstration is a challenging task due to the diversity of human-object interactions.

Human-Object Interaction Detection Object

Decoupling-and-Aggregating for Image Exposure Correction

no code implementations CVPR 2023 Yang Wang, Long Peng, Liang Li, Yang Cao, Zheng-Jun Zha

To this end, we inject the addition/difference operation into the convolution process and devise a Contrast Aware (CA) unit and a Detail Aware (DA) unit to facilitate the statistical and structural regularities modeling.

Detecting Change Intervals with Isolation Distributional Kernel

2 code implementations30 Dec 2022 Yang Cao, Ye Zhu, Kai Ming Ting, Flora D. Salim, Hong Xian Li, Luxing Yang, Gang Li

Detecting abrupt changes in data distribution is one of the most significant tasks in streaming data analysis.

Change Point Detection

Local Differential Privacy Image Generation Using Flow-based Deep Generative Models

no code implementations20 Dec 2022 Hisaichi Shibata, Shouhei Hanaoka, Yang Cao, Masatoshi Yoshikawa, Tomomi Takenaga, Yukihiro Nomura, Naoto Hayashi, Osamu Abe

To release and use medical images, we need an algorithm that can simultaneously protect privacy and preserve pathologies in medical images.

Image Generation

Application of Data Encryption in Chinese Named Entity Recognition

no code implementations31 Aug 2022 Kaifang Long, Jikun Dong, Shengyu Fan, Yanfang Geng, Yang Cao, Han Zhao, Hui Yu, Weizhi Xu

Recently, with the continuous development of deep learning, the performance of named entity recognition tasks has been dramatically improved.

Chinese Named Entity Recognition named-entity-recognition +1

Grounded Affordance from Exocentric View

2 code implementations28 Aug 2022 Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, DaCheng Tao

Due to the diversity of interactive affordance, the uniqueness of different individuals leads to diverse interactions, which makes it difficult to establish an explicit link between object parts and affordance labels.

Human-Object Interaction Detection Object +1

PrivateRec: Differentially Private Training and Serving for Federated News Recommendation

no code implementations18 Apr 2022 Ruixuan Liu, Yanlin Wang, Yang Cao, Lingjuan Lyu, Weike Pan, Yun Chen, Hong Chen

Collecting and training over sensitive personal data raise severe privacy concerns in personalized recommendation systems, and federated learning can potentially alleviate the problem by training models over decentralized user data. However, a theoretically private solution in both the training and serving stages of federated recommendation is essential but still lacking. Furthermore, naively applying differential privacy (DP) to the two stages in federated recommendation would fail to achieve a satisfactory trade-off between privacy and utility due to the high-dimensional characteristics of model gradients and hidden representations. In this work, we propose a federated news recommendation method for achieving a better utility in model training and online serving under a DP guarantee. We first clarify the DP definition over behavior data for each round in the life-circle of federated recommendation systems. Next, we propose a privacy-preserving online serving mechanism under this definition based on the idea of decomposing user embeddings with public basic vectors and perturbing the lower-dimensional combination coefficients.

Federated Learning News Recommendation +2

Network Shuffling: Privacy Amplification via Random Walks

no code implementations8 Apr 2022 Seng Pei Liew, Tsubasa Takahashi, Shun Takagi, Fumiyuki Kato, Yang Cao, Masatoshi Yoshikawa

However, introducing a centralized entity to the originally local privacy model loses some appeals of not having any centralized entity as in local differential privacy.

FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization

no code implementations24 Mar 2022 Kecheng Zheng, Yang Cao, Kai Zhu, Ruijing Zhao, Zheng-Jun Zha

However, its generalization performance to heterogeneous tasks is inferior to other architectures (e. g., CNNs and transformers) due to the extensive retention of domain information.

Domain Generalization

ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation

no code implementations22 Mar 2022 Jinze Chen, Yang Wang, Yang Cao, Feng Wu, Zheng-Jun Zha

Dynamic Vision Sensor (DVS) can asynchronously output the events reflecting apparent motion of objects with microsecond resolution, and shows great application potential in monitoring and other fields.

Denoising Motion Estimation +1

Location-Free Camouflage Generation Network

1 code implementation18 Mar 2022 Yangyang Li, Wei Zhai, Yang Cao, Zheng-Jun Zha

However, these methods struggle in 1) efficiently generating camouflage images using foreground and background with arbitrary structure; 2) camouflaging foreground objects to regions with multiple appearances (e. g. the junction of the vegetation and the mountains), which limit their practical application.

Learning Affordance Grounding from Exocentric Images

2 code implementations CVPR 2022 Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, DaCheng Tao

To empower an agent with such ability, this paper proposes a task of affordance grounding from exocentric view, i. e., given exocentric human-object interaction and egocentric object images, learning the affordance knowledge of the object and transferring it to the egocentric image using only the affordance label as supervision.

Human-Object Interaction Detection Object +1

Towards Data-Efficient Detection Transformers

2 code implementations17 Mar 2022 Wen Wang, Jing Zhang, Yang Cao, Yongliang Shen, DaCheng Tao

Besides, we introduce a simple yet effective label augmentation method to provide richer supervision and improve data efficiency.

Phrase-Based Affordance Detection via Cyclic Bilateral Interaction

4 code implementations24 Feb 2022 Liangsheng Lu, Wei Zhai, Hongchen Luo, Yu Kang, Yang Cao

In this paper, we explore to perceive affordance from a vision-language perspective and consider the challenging phrase-based affordance detection problem, i. e., given a set of phrases describing the action purposes, all the object regions in a scene with the same affordance should be detected.

Affordance Detection

OLIVE: Oblivious Federated Learning on Trusted Execution Environment against the risk of sparsification

1 code implementation15 Feb 2022 Fumiyuki Kato, Yang Cao, Masatoshi Yoshikawa

First, we theoretically analyze the leakage of memory access patterns, revealing the risk of sparsified gradients, which are commonly used in FL to enhance communication efficiency and model accuracy.

Federated Learning Inference Attack +1

NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data Release

1 code implementation14 Feb 2022 Donghao Li, Yang Cao, Yuan YAO

To further enhance the utility and address the label collapse issue when the mixup degree is large, we propose a Hierarchical sampling method to stratify the mixup samples on a small number of classes.

Data Augmentation Privacy Preserving +1

Self-Paced Imbalance Rectification for Class Incremental Learning

no code implementations8 Feb 2022 Zhiheng Liu, Kai Zhu, Yang Cao

Exemplar-based class-incremental learning is to recognize new classes while not forgetting old ones, whose samples can only be saved in limited memory.

Class Incremental Learning Incremental Learning +1

Dreaming To Prune Image Deraining Networks

no code implementations CVPR 2022 Weiqi Zou, Yang Wang, Xueyang Fu, Yang Cao

It is based on our observation that deep degradation representations can be clustered by degradation characteristics (types of rain) while independent of image content.

Model Compression Rain Removal

Multi-Grained Spatio-Temporal Features Perceived Network for Event-Based Lip-Reading

no code implementations CVPR 2022 Ganchao Tan, Yang Wang, Han Han, Yang Cao, Feng Wu, Zheng-Jun Zha

To recognize words from the event data, we propose a novel Multi-grained Spatio-Temporal Features Perceived Network (MSTP) to perceive fine-grained spatio-temporal features from microsecond time-resolved event data.

Action Recognition Lip Reading

Background Activation Suppression for Weakly Supervised Object Localization

2 code implementations CVPR 2022 Pingyu Wu, Wei Zhai, Yang Cao

Existing FPM-based methods use cross-entropy (CE) to evaluate the foreground prediction map and to guide the learning of generator.

Object Weakly-Supervised Object Localization

FP-DETR: Detection Transformer Advanced by Fully Pre-training

no code implementations ICLR 2022 Wen Wang, Yang Cao, Jing Zhang, DaCheng Tao

To this end, we propose the task adapter which leverages self-attention to model the contextual relation between object query embedding.

Object object-detection +2

Do What Nature Did To Us: Evolving Plastic Recurrent Neural Networks For Generalized Tasks

no code implementations29 Sep 2021 Fan Wang, Hao Tian, Haoyi Xiong, Hua Wu, Yang Cao, Yu Kang, Haifeng Wang

While artificial neural networks (ANNs) have been widely adopted in machine learning, researchers are increasingly obsessed by the gaps between ANNs and natural neural networks (NNNs).

Meta-Learning

Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning

2 code implementations8 Sep 2021 Fan Wang, Hao Tian, Haoyi Xiong, Hua Wu, Jie Fu, Yang Cao, Yu Kang, Haifeng Wang

In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e. g., meta-learning.

Memorization Meta-Learning

Learning Visual Affordance Grounding from Demonstration Videos

no code implementations12 Aug 2021 Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, DaCheng Tao

For the object branch, we introduce a semantic enhancement module (SEM) to make the network focus on different parts of the object according to the action classes and utilize a distillation loss to align the output features of the object branch with that of the video branch and transfer the knowledge in the video branch to the object branch.

Action Recognition Object +1

One-Shot Object Affordance Detection in the Wild

1 code implementation8 Aug 2021 Wei Zhai, Hongchen Luo, Jing Zhang, Yang Cao, DaCheng Tao

To empower robots with this ability in unseen scenarios, we first study the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.

Action Recognition Affordance Detection +3

Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

1 code implementation27 Jul 2021 Wen Wang, Yang Cao, Jing Zhang, Fengxiang He, Zheng-Jun Zha, Yonggang Wen, DaCheng Tao

In DQFA, a novel domain query is used to aggregate and align global context from the token sequence of both domains.

Decoder Domain Adaptation +3

One-Shot Affordance Detection

2 code implementations28 Jun 2021 Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, DaCheng Tao

To empower robots with this ability in unseen scenarios, we consider the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.

4k Affordance Detection

Understanding the Interplay between Privacy and Robustness in Federated Learning

no code implementations13 Jun 2021 Yaowei Han, Yang Cao, Masatoshi Yoshikawa

Federated Learning (FL) is emerging as a promising paradigm of privacy-preserving machine learning, which trains an algorithm across multiple clients without exchanging their data samples.

Adversarial Robustness Federated Learning +1

FL-Market: Trading Private Models in Federated Learning

1 code implementation8 Jun 2021 Shuyuan Zheng, Yang Cao, Masatoshi Yoshikawa, Huizhong Li, Qiang Yan

FL-Market decouples ML from the need to centrally gather training data on the broker's side using federated learning, an emerging privacy-preserving ML paradigm in which data owners collaboratively train an ML model by uploading local gradients (to be aggregated into a global gradient for model updating).

Federated Learning Privacy Preserving

FakeMix Augmentation Improves Transparent Object Detection

1 code implementation24 Mar 2021 Yang Cao, Zhengqiang Zhang, Enze Xie, Qibin Hou, Kai Zhao, Xiangui Luo, Jian Tuo

However, these methods usually encounter boundary-related imbalance problem, leading to limited generation capability.

Data Augmentation Object +3

FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation

no code implementations9 Feb 2021 Chuhan Wu, Fangzhao Wu, Yang Cao, Yongfeng Huang, Xing Xie

To incorporate high-order user-item interactions, we propose a user-item graph expansion method that can find neighboring users with co-interacted items and exchange their embeddings for expanding the local user-item graphs in a privacy-preserving way.

Graph Neural Network Privacy Preserving

Transparent Contribution Evaluation for Secure Federated Learning on Blockchain

no code implementations26 Jan 2021 Shuaicheng Ma, Yang Cao, Li Xiong

In this work, we propose a blockchain-based federated learning framework and a protocol to transparently evaluate each participant's contribution.

BIG-bench Machine Learning Federated Learning

Quantifying the Privacy-Utility Trade-offs in COVID-19 Contact Tracing Apps

no code implementations24 Dec 2020 Patrick Ocheja, Yang Cao, Shiyao Ding, Masatoshi Yoshikawa

How to contain the spread of the COVID-19 virus is a major concern for most countries.

Computers and Society Cryptography and Security 68P27 H.3.4

PCT-TEE: Trajectory-based Private Contact Tracing System with Trusted Execution Environment

1 code implementation7 Dec 2020 Fumiyuki Kato, Yang Cao, Yoshikawa Masatoshi

To this end, we design a TEE-based system with flexible trajectory data encoding algorithms.

Cryptography and Security Computers and Society

FLAME: Differentially Private Federated Learning in the Shuffle Model

1 code implementation17 Sep 2020 Ruixuan Liu, Yang Cao, Hong Chen, Ruoyang Guo, Masatoshi Yoshikawa

In this work, by leveraging the \textit{privacy amplification} effect in the recently proposed shuffle model of differential privacy, we achieve the best of two worlds, i. e., accuracy in the curator model and strong privacy without relying on any trusted party.

Federated Learning

Finding Acceptable Parameter Regions of Stochastic Hill functions for Multisite Phosphorylation Mechanism

no code implementations14 Sep 2020 Minghan Chen, Mansooreh Ahmadian, Layne Watson, Yang Cao

To reduce model complexity, this work aims to simplify the multisite phosphorylation mechanism by a stochastic Hill function model.

Stochastic Optimization valid

Nighttime Dehazing with a Synthetic Benchmark

1 code implementation10 Aug 2020 Jing Zhang, Yang Cao, Zheng-Jun Zha, DaCheng Tao

To address this issue, we propose a novel synthetic method called 3R to simulate nighttime hazy images from daytime clear images, which first reconstructs the scene geometry, then simulates the light rays and object reflectance, and finally renders the haze effects.

Decoder

P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model

2 code implementations22 Jun 2020 Shun Takagi, Tsubasa Takahashi, Yang Cao, Masatoshi Yoshikawa

The state-of-the-art approach for this problem is to build a generative model under differential privacy, which offers a rigorous privacy guarantee.

Privacy Preserving

PGLP: Customizable and Rigorous Location Privacy through Policy Graph

3 code implementations4 May 2020 Yang Cao, Yonghui Xiao, Shun Takagi, Li Xiong, Masatoshi Yoshikawa, Yilin Shen, Jinfei Liu, Hongxia Jin, Xiaofeng Xu

Third, we design a private location trace release framework that pipelines the detection of location exposure, policy graph repair, and private trajectory release with customizable and rigorous location privacy.

Cryptography and Security Computers and Society

PANDA: Policy-aware Location Privacy for Epidemic Surveillance

3 code implementations1 May 2020 Yang Cao, Shun Takagi, Yonghui Xiao, Li Xiong, Masatoshi Yoshikawa

Our system has three primary functions for epidemic surveillance: location monitoring, epidemic analysis, and contact tracing.

Databases Cryptography and Security

Self-Supervised Tuning for Few-Shot Segmentation

no code implementations12 Apr 2020 Kai Zhu, Wei Zhai, Zheng-Jun Zha, Yang Cao

Few-shot segmentation aims at assigning a category label to each image pixel with few annotated samples.

Meta-Learning Segmentation

FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection

no code implementations24 Mar 2020 Ruixuan Liu, Yang Cao, Masatoshi Yoshikawa, Hong Chen

To prevent privacy leakages from gradients that are calculated on users' sensitive data, local differential privacy (LDP) has been considered as a privacy guarantee in federated SGD recently.

Federated Learning

Sensor-Augmented Neural Adaptive Bitrate Video Streaming on UAVs

no code implementations23 Sep 2019 Xuedou Xiao, Wei Wang, Taobin Chen, Yang Cao, Tao Jiang, Qian Zhang

In this paper, we present SA-ABR, a new sensor-augmented system that generates ABR video streaming algorithms with the assistance of various kinds of inherent sensor data that are used to pilot UAVs.

EGNet:Edge Guidance Network for Salient Object Detection

3 code implementations22 Aug 2019 Jia-Xing Zhao, Jiang-Jiang Liu, Den-Ping Fan, Yang Cao, Jufeng Yang, Ming-Ming Cheng

In the second step, we integrate the local edge information and global location information to obtain the salient edge features.

Object object-detection +2

One-Shot Texture Retrieval with Global Context Metric

no code implementations16 May 2019 Kai Zhu, Wei Zhai, Zheng-Jun Zha, Yang Cao

In this paper, we tackle one-shot texture retrieval: given an example of a new reference texture, detect and segment all the pixels of the same texture category within an arbitrary image.

Relation Relation Network +2

Deep Time-Frequency Representation and Progressive Decision Fusion for ECG Classification

no code implementations19 Jan 2019 Jing Zhang, Jing Tian, Yang Cao, Yuxiang Yang, Xiaobin Xu

Early recognition of abnormal rhythms in ECG signals is crucial for monitoring and diagnosing patients' cardiac conditions, increasing the success rate of the treatment.

ECG Classification General Classification

Enhanced-alignment Measure for Binary Foreground Map Evaluation

2 code implementations26 May 2018 Deng-Ping Fan, Cheng Gong, Yang Cao, Bo Ren, Ming-Ming Cheng, Ali Borji

The existing binary foreground map (FM) measures to address various types of errors in either pixel-wise or structural ways.

Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit

no code implementations11 Feb 2018 Yang Cao, Zheng Wen, Branislav Kveton, Yao Xie

Multi-armed bandit (MAB) is a class of online learning problems where a learning agent aims to maximize its expected cumulative reward while repeatedly selecting to pull arms with unknown reward distributions.

Change Detection

Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images

no code implementations19 Jan 2018 Jing Zhang, Yang Cao, Yang Wang, Chenglin Wen, Chang Wen Chen

Specifically, we propose to randomly shuffle the pixels in the origin images and leverage the shuffled image as input to make CNN more concerned with the statistical properties.

Color Constancy Image Dehazing

Quantifying Differential Privacy in Continuous Data Release under Temporal Correlations

2 code implementations29 Nov 2017 Yang Cao, Masatoshi Yoshikawa, Yonghui Xiao, Li Xiong

Our analysis reveals that, the event-level privacy loss of a DP mechanism may \textit{increase over time}.

Databases

Fast Haze Removal for Nighttime Image Using Maximum Reflectance Prior

no code implementations CVPR 2017 Jing Zhang, Yang Cao, Shuai Fang, Yu Kang, Chang Wen Chen

Then, we propose a simple but effective image prior, maximum reflectance prior, to estimate the varying ambient illumination.

Computational Efficiency

Nearly second-order asymptotic optimality of sequential change-point detection with one-sample updates

no code implementations19 May 2017 Yang Cao, Liyan Xie, Yao Xie, Huan Xu

Our proof is achieved by making a connection between sequential change-point and online convex optimization and leveraging the logarithmic regret bound property of online mirror descent algorithm.

Change Point Detection

Quantifying Differential Privacy under Temporal Correlations

2 code implementations24 Oct 2016 Yang Cao, Masatoshi Yoshikawa, Yonghui Xiao, Li Xiong

Our analysis reveals that the privacy leakage of a DP mechanism may accumulate and increase over time.

Databases Cryptography and Security

Nighttime Haze Removal with Illumination Correction

no code implementations5 Jun 2016 Jing Zhang, Yang Cao, Zengfu Wang

ii) Then it achieves a color-balance result by performing a color correction step after estimating the color characteristics of the incident light.

Multi-Sensor Slope Change Detection

no code implementations1 Sep 2015 Yang Cao, Yao Xie, Nagi Gebraeel

Observations are assumed to be initially normal random variables with known constant means and variances.

Change Detection

Categorical Matrix Completion

no code implementations2 Jul 2015 Yang Cao, Yao Xie

We recover a low-rank matrix $X$ by maximizing the likelihood ratio with a constraint on the nuclear norm of $X$, and the observations are mapped from entries of $X$ through multiple link functions.

Matrix Completion

Sketching for Sequential Change-Point Detection

no code implementations25 May 2015 Yang Cao, Andrew Thompson, Meng Wang, Yao Xie

We study sequential change-point detection procedures based on linear sketches of high-dimensional signal vectors using generalized likelihood ratio (GLR) statistics.

Change Point Detection

Poisson Matrix Recovery and Completion

no code implementations20 Apr 2015 Yang Cao, Yao Xie

We extend the theory of low-rank matrix recovery and completion to the case when Poisson observations for a linear combination or a subset of the entries of a matrix are available, which arises in various applications with count data.

Matrix Completion

Poisson Matrix Completion

no code implementations26 Jan 2015 Yang Cao, Yao Xie

We extend the theory of matrix completion to the case where we make Poisson observations for a subset of entries of a low-rank matrix.

Matrix Completion

Fast Algorithm for Low-rank matrix recovery in Poisson noise

no code implementations2 Jul 2014 Yang Cao, Yao Xie

This paper describes a fast algorithm for recovering low-rank matrices from their linear measurements contaminated with Poisson noise: the Poisson noise Maximum Likelihood Singular Value thresholding (PMLSV) algorithm.

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