Demo Data from EDBT 2026 / reviewers in the wild / expert
Qiuyu Chen
dblp:206/6527
· DBLP profile ↗
14ranked-venue papers
4as first author
9since 2021 · last 2026
—ORCID · conflict
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 10 · 2 first-author · 6 since 2021Graphics, computer vision, multimedia, augmented reality and games · 6 · 3 first-author · 4 since 2021Systems, architecture and hardware · 1 · 1 since 2021Computer networks · 1 · 1 since 2021Security and privacy · 1Databases, data management, data science and information retrieval · 1 · 1 first-author · 1 since 2021Human-computer interaction and ubiquitous computing · 1 · 1 since 2021Applied, interdisciplinary, general and emerging computing · 1 · 1 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
6 papers |
Motion planning and robot control · 26% Image recognition and object detection · 13% Trustworthy machine learning · 13% | |
| Computer graphics and multimedia
3 papers |
Multimedia analysis and retrieval · 56% Image and video coding · 44% |
Topics — the 17 heaviest of 20, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Representation and self-supervised learning › representation learning
disentangled representation learning |
0.8 | 1 | 2024 | Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models · NeurIPS 2024 |
Machine learning › Trustworthy machine learning
fairness |
0.8 | 1 | 2024 | FairRAG: Fair Human Generation via Fair Retrieval Augmentation · CVPR 2024 |
Robotics › Motion planning and robot control › robot learning › robot policy learning
generalist robot policy |
0.8 | 1 | 2024 | Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration · ICRA 2024 |
Robotics › Motion planning and robot control
robot learning |
0.8 | 1 | 2024 | Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration · ICRA 2024 |
Machine learning › Generative modeling › diffusion model
text-to-image generation |
0.8 | 1 | 2024 | FairRAG: Fair Human Generation via Fair Retrieval Augmentation · CVPR 2024 |
Image and video coding › image compression
learned image compression |
0.8 | 1 | 2024 | Rate-Distortion-Cognition Controllable Versatile Neural Image Compression · ECCV (56) 2024 |
Multimedia analysis and retrieval › video summarization
video highlight detection |
0.5 | 1 | 2021 | GIF Thumbnails: Attract More Clicks to Your Videos · AAAI 2021 |
Multimedia analysis and retrieval
video summarization |
0.5 | 1 | 2021 | GIF Thumbnails: Attract More Clicks to Your Videos · AAAI 2021 |
Multimedia analysis and retrieval › video summarization
video thumbnail generation |
0.5 | 1 | 2021 | GIF Thumbnails: Attract More Clicks to Your Videos · AAAI 2021 |
Image and video coding › image quality assessment
image aesthetics assessment |
0.4 | 1 | 2020 | Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment · CVPR 2020 |
Computer vision › Image recognition and object detection
image classification |
0.4 | 1 | 2019 | Embedding Complementary Deep Networks for Image Classification · CVPR 2019 |
Computer vision › Image recognition and object detection › image classification
large-scale image classification |
0.4 | 1 | 2019 | Deep Mixture of Diverse Experts for Large-Scale Visual Recognition · IEEE Trans. Pattern Anal. Mach. Intell. 2019 |
Knowledge, reasoning and agents › Knowledge representation and reasoning › knowledge acquisition
knowledge extraction |
0.2 | 1 | 2024 | Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models · NeurIPS 2024 |
Machine learning › Efficient and distributed learning
model compression |
0.2 | 1 | 2024 | Rate-Distortion-Cognition Controllable Versatile Neural Image Compression · ECCV (56) 2024 |
Computer vision › Vision and language › vision-language model
multimodal large language model |
0.2 | 1 | 2024 | Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models · NeurIPS 2024 |
Recommender systems
click-through rate prediction |
0.1 | 1 | 2021 | GIF Thumbnails: Attract More Clicks to Your Videos · AAAI 2021 |
Machine learning › Deep learning architectures and training
mixture of experts |
0.1 | 1 | 2019 | Deep Mixture of Diverse Experts for Large-Scale Visual Recognition · IEEE Trans. Pattern Anal. Mach. Intell. 2019 |
Methods — techniques the papers use, named apart from their topics
neural image compression · 1.5variational autoencoder · 1.0learning-based generation · 1.0β-VAE · 0.8weighted graph · 0.8transformer policy · 0.8retrieval-augmented generation · 0.8multimodal large language model · 0.8large-scale pretraining · 0.8debiasing · 0.8dual-encoder · 0.5dual encoder · 0.5grouping strategy · 0.4fractional dilated convolution · 0.4ensemble learning · 0.4deep embedding · 0.4
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2026 | Dynamic Weight-Enhanced Contrastive Learning for Partially View-Aligned ClusteringabstractDeep contrastive multi-view clustering has attracted considerable attention for its ability to extract shared representations across heterogeneous views. Despite its effectiveness, existing approaches usually assume full cross-view alignment, an assumption often violated in practice due to sensor noise, transmission loss, or inconsistent data augmentation. This partial view alignment substantially degrades performance, while current solutions relying on fixed pair selection or uniform weighting fail to resolve the semantic ambiguity of unaligned samples. Consequently, latent cross-view semantic relationships remain underutilized, while erroneous positive pairs unduly dominate the contrastive objective, compromising robustness under low alignment rates or noisy conditions. To address these challenges, we propose Dynamic Weight-Enhanced InfoNCE (DW-InfoNCE), a contrastive learning framework designed for partially view-aligned clustering. The framework introduces a cross-view positive pair mining strategy that iteratively identifies reliable pairs from unaligned samples through quantile-adaptive thresholds and uniqueness constraints, enabling recovery of latent semantic structures obscured by incomplete alignment. In addition, an adaptive faulty pair suppression mechanism is developed to identify semantically inconsistent pairs via temporal loss smoothing and global statistics, while attenuating their impact with Gaussian-based adaptive weights. Extensive experiments on five benchmarks demonstrate DW-InfoNCE consistently outperforms state-of-the-art methods across alignment rates, with significant gains under severe misalignment. The code of DW-InfoNCE can be publicly downloaded at https://github.com/qiuyu99627/ DWInfoNCE.git. Qiuyu Chen, Xihong Yang, Zhibing Dong, Qian Qu, En Zhu, Xinwang Liu 0002 |
IEEE Trans. Circuits Syst. Video Technol. | 1 |
| 2025 | CHARM: Considering Human Attributes for Reinforcement ModelingabstractReinforcement Learning from Human Feedback has recently achieved significant success in various fields, and its performance is highly related to feedback quality. While much prior work acknowledged that human teachers’ characteristics would affect human feedback patterns, there is little work that has closely investigated the actual effects. In this work, we designed an exploratory study investigating how human feedback patterns are associated with human characteristics. We conducted a public space study with two long-horizon tasks and 46 participants. We found that feedback patterns are not only correlated with task statistics, such as rewards, but also correlated with participants’ characteristics, especially robot experience and educational background. Additionally, we demonstrated that human feedback value can be more accurately predicted with human characteristics compared to only using task statistics. All human feedback and characteristics we collected, and codes for our data collection and predicting more accurate human feedback are available at https://github.com/AABL-Lab/CHARM. Qidi Fang, Shijie Fang, Jindan Huang, Qiuyu Chen, Reuben M. Aronson, Elaine Short |
RO-MAN | 5 |
| 2025 | Dual Routes of Training on Information Security Policy ComplianceabstractThis study aims to explore the mechanisms by which training influences employees’ information security policy compliance (ISPC) through the mediating roles of compliance knowledge and social pressure. An empirical model is conceptualized on the theoretical basis of the Elaboration Likelihood Model (ELM). Based on a survey conducted in China, a sample of 304 participants was used to test the impact of training on ISPC as well as the mediating effects of compliance knowlgedge (as a central route) and social pressure (as a peripheral route). The results revealed that training had a positive effect on ISPC, and the mediating effects of compliance knowledge and social pressure were both positive and complementary. The results also indicated that the mediating effect of compliance knowledge was stronger than that of social pressure, which was consistent with the judgment of ELM. Qiuyu Chen, Yuxiang Hong |
J. Comput. Inf. Syst. | 1 |
| 2025 | Semi-Supervised Learning for Anomaly Traffic Detection via Bidirectional Normalizing FlowsabstractWith the rapid development of the Internet, various types of anomaly traffic are threatening network security. However, the difficulty of collecting and labelling anomalous traffic is a significant challenge, so this paper proposes a semi-supervised anomaly detection framework. Considering normal and abnormal traffic have different data distributions, our framework can generate pseudo anomaly samples without prior knowledge of anomalies to achieve the detection of anomaly data. The framework comprises three principal components. Firstly, a pre-trained feature extractor is employed to extract a feature representation of the network traffic. Secondly, a bidirectional normalizing flow module establishes a reversible transformation between the latent data distribution and a Gaussian space. Through this bidirectional mapping, samples first undergo transformation manipulation within the Gaussian distribution space, and are then transported through the generative direction of normalizing flows, translating mathematical transformations into semantic feature evolutions in the latent data space. Finally, a simple classifier explicitly learns the potential differences between anomaly and normal samples to facilitate better anomaly detection. During inference, our framework requires only two modules to detect anomalous samples, leading to a considerable reduction in model size. According to the experiments, our method achieves the state-of-the-art results on the common benchmarking datasets of anomaly network traffic detection. Furthermore, it exhibits good generalisation performance across datasets. Zhangxuan Dang, Yu Zheng 0006, Xinglin Lian, Chunlei Peng, Qiuyu Chen, Xinbo Gao 0001 |
IEEE Trans. Netw. Serv. Manag. | 5 |
| 2024 | FairRAG: Fair Human Generation via Fair Retrieval AugmentationabstractExisting text-to-image generative models reflect or even amplify societal biases ingrained in their training data. This is especially concerning for human image generation where models are biased against certain demographic groups. Existing attempts to rectify this issue are hindered by the inherent limitations of the pre-trained models and fail to substantially improve demographic diversity. In this work, we introduce Fair Retrieval Augmented Generation (FairRAG), a novel framework that conditions pre-trained generative models on reference images retrieved from an external image database to improve fairness in human generation. FairRAG enables conditioning through a lightweight linear module that projects reference images into the textual space. To enhance fairness, FairRAG applies simple-yet-effective debiasing strategies, providing images from diverse demographic groups during the generative process. Extensive experiments demonstrate that FairRAG outper-forms existing methods in terms of demographic diversity, image-text alignment and image fidelity while incurring minimal computational overhead during inference. Robik Shrestha, Qiuyu Chen, Yusheng Xie, Siqi Deng |
CVPR | 3 |
| 2024 | Rate-Distortion-Cognition Controllable Versatile Neural Image Compression
Jinming Liu 0001, Ruoyu Feng 0001, Yunpeng Qi, Qiuyu Chen, Zhibo Chen 0001, Wenjun Zeng 0001, Xin Jin 0014 |
ECCV (56) | 4 |
| 2024 | Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment CollaborationabstractLarge, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x.github.io. Abigail O'Neill, Abhiram Maddukuri, Abhishek Gupta 0004, Abhishek Padalkar, Abraham Lee, Acorn Pooley, Agrim Gupta, Ajay Mandlekar, Ajinkya Jain, Albert Tung, Alex Bewley, Alex Irpan, Alexander Khazatsky, Anant Rai, Anchit Gupta, Andrew E. Wang, Anikait Singh, Animesh Garg, Aniruddha Kembhavi, Annie Xie, Anthony Brohan, Antonin Raffin, Archit Sharma, Arefeh Yavary, Arhan Jain, Ashwin Balakrishna, Ayzaan Wahid, Ben Burgess-Limerick, Bernhard Schölkopf, Blake Wulfe, Brian Ichter, Cewu Lu, Charles Xu 0003, Charlotte Le, Chelsea Finn, Chen Wang 0053, Chenfeng Xu, Cheng Chi 0001, Chenguang Huang, Christine Chan, Christopher Agia, Chuer Pan, Chuyuan Fu, Coline Devin, Danfei Xu, Daniel Morton, Danny Drieß, Daphne Chen, Deepak Pathak, Dhruv Shah, Dieter Büchler, Dinesh Jayaraman, Dmitry Kalashnikov, Dorsa Sadigh, Edward Johns, Ethan Paul Foster, Fangchen Liu, Federico Ceola, Fei Xia 0002, Feiyu Zhao, Freek Stulp, Gaoyue Zhou, Gaurav S. Sukhatme, Gautam Salhotra, Gilbert Feng, Giulio Schiavi, Glen Berseth, Gregory Kahn, Guanzhi Wang, Hao Su 0001, Haoshu Fang, Henghui Bao, Heni Ben Amor, Henrik I. Christensen, Hiroki Furuta, Homer Walke, Hongjie Fang, Huy Ha, Igor Mordatch, Ilija Radosavovic, Isabel Leal, Jacky Liang, Jad Abou-Chakra, Jaehyung Kim 0001, Jaimyn Drake, Jan Peters 0001, Jan Schneider 0007, Jasmine Hsu, Jeannette Bohg, Jeffrey T. Bingham, Jensen Gao, Jiaheng Hu, Jiajun Wu 0001, Jiankai Sun, Jianlan Luo, Jiayuan Gu, Jie Tan 0001, Jihoon Oh, Jimmy Wu, Jingpei Lu, Jitendra Malik, João Silvério, Joey Hejna, Jonathan Booher, Jonathan Tompson, Jonathan Yang, Jordi Salvador, Joseph J. Lim, Junhyek Han, Kanishka Rao, Karl Pertsch, Karol Hausman, Keegan Go, Keerthana Gopalakrishnan, Kenneth Y. Goldberg, Kendra Byrne, Kenneth Oslund, Kento Kawaharazuka, Kevin Black, Kevin Zhang 0002, Kiana Ehsani, Kiran Lekkala, Kirsty Ellis, Krishan Rana, Krishnan Srinivasan, Kuan Fang, Kunal Pratap Singh, Kuo-Hao Zeng, Kyle Hatch, Kyle Hsu, Laurent Itti, Yunliang Chen 0001, Lerrel Pinto, Li Fei-Fei 0001, Liam Tan, Linxi Fan, Lionel Ott, Lisa Lee, Luca Weihs, Magnum Chen, Marion Lepert, Marius Memmel, Masayoshi Tomizuka, Masha Itkina, Mateo Guaman Castro, Max Spero, Maximilian Du, Michael Ahn, Michael C. Yip, Mingtong Zhang 0003, Mingyu Ding, Minho Heo, Mohan Kumar Srirama, Mohit Sharma 0001, Moo Jin Kim, Naoaki Kanazawa, Nicklas Hansen 0001, Nicolas Heess, Nikhil J. Joshi, Niko Sünderhauf, Norman Di Palo, Nur Muhammad Shafiullah, Oier Mees, Oliver Kroemer, Osbert Bastani, Pannag R. Sanketi, Patrick Tree Miller, Patrick Yin, Paul Wohlhart, Peng Xu 0010, Peter David Fagan, Peter Mitrano, Pierre Sermanet, Pieter Abbeel, Priya Sundaresan, Qiuyu Chen, Rafael Rafailov, Ria Doshi, Roberto Martin Martin, Rohan Baijal, Rosario Scalise, Rose Hendrix, Roy Lin, Runjia Qian, Russell Mendonca, Rutav Shah, Ryan Hoque, Ryan Julian, Samuel Bustamante-Gomez, Sean Kirmani, Sergey Levine, Sherry Moore, Shikhar Bahl, Shivin Dass, Shubham D. Sonawani, Shuran Song, Sichun Xu, Siddhant Haldar, Siddharth Karamcheti, Simeon Adebola, Simon Guist, Soroush Nasiriany, Stefan Schaal, Stefan Welker, Stephen Tian, Subramanian Ramamoorthy, Sudeep Dasari, Suneel Belkhale, Sungjae Park, Suraj Nair 0003, Suvir Mirchandani, Takayuki Osa, Tanmay Gupta, Tatsuya Harada, Tatsuya Matsushima, Ted Xiao, Thomas Kollar, Tianhe Yu, Tianli Ding, Todor Davchev, Tony Z. Zhao, Travis Armstrong, Trevor Darrell, Trinity Chung, Vidhi Jain, Vincent Vanhoucke, Wolfram Burgard, Xiaolong Wang 0004, Xinghao Zhu, Xinyang Geng, Liangwei Xu, Yecheng Jason Ma 0001, Yejin Kim 0003, Yevgen Chebotar, Yilin Wu 0003, Yonatan Bisk, Yoonyoung Cho, Youngwoon Lee, Yuchen Cui, Yueh-Hua Wu, Yujin Tang, Yuke Zhu, Yunchu Zhang, Yunfan Jiang 0001, Yunshuang Li, Yunzhu Li, Yusuke Iwasawa, Yutaka Matsuo, Zehan Ma, Zichen Jeff Cui, Zichen Zhang 0016, Zipeng Lin |
ICRA | 187 |
| 2024 | Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language ModelsabstractDisentangled representation learning (DRL) aims to identify and decompose underlying factors behind observations, thus facilitating data perception and generation. However, current DRL approaches often rely on the unrealistic assumption that semantic factors are statistically independent. In reality, these factors may exhibit correlations, which off-the-shelf solutions have yet to properly address. To tackle this challenge, we introduce a bidirectional weighted graph-based framework, to learn factorized attributes and their interrelations within complex data. Specifically, we propose a $\beta$-VAE based module to extract factors as the initial nodes of the graph, and leverage the multimodal large language model (MLLM) to discover and rank latent correlations, thereby updating the weighted edges. By integrating these complementary modules, our model successfully achieves fine-grained, practical and unsupervised disentanglement. Experiments demonstrate our method's superior performance in disentanglement and reconstruction. Furthermore, the model inherits enhanced interpretability and generalizability from MLLMs. Baao Xie, Qiuyu Chen, Yunnan Wang, Zequn Zhang, Xin Jin 0014, Wenjun Zeng 0001 |
NeurIPS | 2 |
| 2021 | GIF Thumbnails: Attract More Clicks to Your VideosabstractWith the rapid increase of mobile devices and online media, more and more people prefer posting/viewing videos online. Generally, these videos are presented on video streaming sites with image thumbnails and text titles. While facing huge amounts of videos, a viewer clicks through a certain video with high probability because of its eye-catching thumbnail. However, current video thumbnails are created manually, which is time-consuming and quality-unguaranteed. And static image thumbnails contain very limited information of the corresponding videos, which prevents users from successfully clicking what they really want to view. In this paper, we address a novel problem, namely GIF thumbnail generation, which aims to automatically generate GIF thumbnails for videos and consequently boost their Click-Through-Rate (CTR). Here, a GIF thumbnail is an animated GIF file consisting of multiple segments from the video, containing more information of the target video than a static image thumbnail. To support this study, we build the first GIF thumbnails benchmark dataset that consists of 1070 videos covering a total duration of 69.1 hours, and 5394 corresponding manually-annotated GIFs. To solve this problem, we propose a learning-based automatic GIF thumbnail generation model, which is called Generative Variational Dual-Encoder (GEVADEN). As not relying on any user interaction information (e.g. time-sync comments and real-time view counts), this model is applicable to newly-uploaded/rarely-viewed videos. Experiments on our built dataset show that GEVADEN significantly outperforms several baselines, including video-summarization and highlight-detection based ones. Furthermore, we develop a pilot application of the proposed model on an online video platform with 9814 videos covering 1231 hours, which shows that our model achieves a 37.5% CTR improvement over traditional image thumbnails. This further validates the effectiveness of the proposed model and the promising application prospect of GIF thumbnails. Yi Xu 0003, Fan Bai 0001, Yingxuan Shi, Qiuyu Chen, Longwen Gao, Kai Tian 0001, Shuigeng Zhou, Huyang Sun |
AAAI | 4 |
| 2020 | Adaptive Fractional Dilated Convolution Network for Image Aesthetics AssessmentabstractTo leverage deep learning for image aesthetics assessment, one critical but unsolved issue is how to seamlessly incorporate the information of image aspect ratios to learn more robust models. In this paper, an adaptive fractional dilated convolution (AFDC), which is aspect-ratio-embedded, composition-preserving and parameter-free, is developed to tackle this issue natively in convolutional kernel level. Specifically, the fractional dilated kernel is adaptively constructed according to the image aspect ratios, where the interpolation of nearest two integer dilated kernels are used to cope with the misalignment of fractional sampling. Moreover, we provide a concise formulation for mini-batch training and utilize a grouping strategy to reduce computational overhead. As a result, it can be easily implemented by common deep learning libraries and plugged into popular CNN architectures in a computation-efficient manner. Our experimental results demonstrate that our proposed method achieves state-of-the-art performance on image aesthetics assessment over the AVA dataset. Qiuyu Chen, Wei Zhang 0016, Yi Xu 0003, Yu Zheng 0006, Jianping Fan 0001 |
CVPR | 1 |
| 2020 | Hierarchical convolutional neural network via hierarchical cluster validity based visual tree learning
Yu Zheng 0006, Qiuyu Chen, Jianping Fan 0001, Xinbo Gao 0001 |
Neurocomputing | 2 |
| 2020 | Android Malware Detection Based on a Hybrid Deep Learning ModelabstractIn recent years, the number of malware on the Android platform has been increasing, and with the widespread use of code obfuscation technology, the accuracy of antivirus software and traditional detection algorithms is low. Current state-of-the-art research shows that researchers started applying deep learning methods for malware detection. We proposed an Android malware detection algorithm based on a hybrid deep learning model which combines deep belief network (DBN) and gate recurrent unit (GRU). First of all, analyze the Android malware; in addition to extracting static features, dynamic behavioral features with strong antiobfuscation ability are also extracted. Then, build a hybrid deep learning model for Android malware detection. Because the static features are relatively independent, the DBN is used to process the static features. Because the dynamic features have temporal correlation, the GRU is used to process the dynamic feature sequence. Finally, the training results of DBN and GRU are input into the BP neural network, and the final classification results are output. Experimental results show that, compared with the traditional machine learning algorithms, the Android malware detection model based on hybrid deep learning algorithms has a higher detection accuracy, and it also has a better detection effect on obfuscated malware. Tianliang Lu, Yanhui Du, Li Ouyang, Qiuyu Chen, Xirui Wang |
Secur. Commun. Networks | 4 |
| 2019 | Embedding Complementary Deep Networks for Image ClassificationabstractIn this paper, a deep embedding algorithm is developed to achieve higher accuracy rates on large-scale image classification. By adapting the importance of the object classes to their error rates, our deep embedding algorithm can train multiple complementary deep networks sequentially, where each of them focuses on achieving higher accuracy rates for different subsets of object classes in an easy-to-hard way. By integrating such complementary deep networks to generate an ensemble network, our deep embedding algorithm can improve the accuracy rates for the hard object classes (which initially have higher error rates) at certain degrees while effectively preserving high accuracy rates for the easy object classes. Our deep embedding algorithm has achieved higher overall accuracy rates on large scale image classification. Qiuyu Chen, Wei Zhang 0016, Jun Yu 0002, Jianping Fan 0001 |
CVPR | 1 |
| 2019 | Deep Mixture of Diverse Experts for Large-Scale Visual RecognitionabstractIn this paper, a deep mixture of diverse experts algorithm is developed to achieve more efficient learning of a huge (mixture) network for large-scale visual recognition application. First, a two-layer ontology is constructed to assign large numbers of atomic object classes into a set of task groups according to the similarities of their learning complexities, where certain degrees of inter-group task overlapping are allowed to enable sufficient inter-group message passing. Second, one particular base deep CNNs with M+1 outputs is learned for each task group to recognize its M atomic object classes and identify one special class of "not-in-group", where the network structure (numbers of layers and units in each layer) of the well-designed deep CNNs (such as AlexNet, VGG, GoogleNet, ResNet) is directly used to configure such base deep CNNs. For enhancing the separability of the atomic object classes in the same task group, two approaches are developed to learn more discriminative base deep CNNs: (a) our deep multi-task learning algorithm that can effectively exploit the inter-class visual similarities; (b) our two-layer network cascade approach that can improve the accuracy rates for the hard object classes at certain degrees while effectively maintaining the high accuracy rates for the easy ones. Finally, all these complementary base deep CNNs with diverse but overlapped outputs are seamlessly combined to generate a mixture network with larger outputs for recognizing tens of thousands of atomic object classes. Our experimental results have demonstrated that our deep mixture of diverse experts algorithm can achieve very competitive results on large-scale visual recognition. Qiuyu Chen, Zhenzhong Kuang, Jun Yu 0002, Wei Zhang 0016, Jianping Fan 0001 |
IEEE Trans. Pattern Anal. Mach. Intell. | 2 |