检索结果-内蒙古大学图书馆

Class-Aware Feature Perturbation for Long-Tailed Visual Recognition

学校读者我要写书评

暂无评论

Class-Aware Feature Perturbation for Long-Tailed Visual Reco...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xicheng Chen Haibo Ye Fangyu Zhou College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China Collaborative Innovation Center of Novel Software Technology and Industrialization

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

The distribution of data in the real world is often imbalanced, with a small number of classes having a large number of instances, while most other classes have relatively few sample instances, resulting in a long-tailed distribution. Supervised contrastive learning still tends to favor classes with more samples, making it challenging to learn discriminative and robust features in imbalanced settings. In our work, we theoretically analyze the advantages of hard samples in contrastive learning and propose an end-to-end training framework based on class-aware perturbation. Specifically, we introduce different levels of perturbation based on class priors to construct hard samples, improve the disadvantaged position of tail classes, balance the feature space distribution, and dynamically adjust the classifier output with a combination of local batch priors and global priors. Experimental results show that our method achieves competitive performance across multiple long-tailed benchmark datasets.

关键词： Training Visualization Technological innovation Perturbation methods Contrastive learning Tail Benchmark testing

ACRM: Attention Cascade R-CNN with Mix-NMS for Metallic Surface Defect Detection

学校读者我要写书评

暂无评论

ACRM: Attention Cascade R-CNN with Mix-NMS for Metallic Surf...

International Conference on pattern Recognition

作者： Junting Fang Xiaoyang Tan Yuhui Wang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China

Metallic surface defect detection is of great significance in quality control for production. However, this task is very challenging due to the noise disturbance, large appearance variation, and the ambiguous definition of the defect individual. Traditional image processing methods are unable to detect the damaged region effectively and efficiently. In this paper, we propose a new defect detection method, Attention Cascade R-CNN with Mix-NMS (ACRM), to classify and locate defects robustly. Three submodules are developed to achieve this goal: 1) a lightweight attention block is introduced, which can improve the ability in capture global and local feature both in the spatial and channel dimension; 2) we firstly apply the cascade R-CNN to our task, which exploits multiple detectors to sequentially refine the detection result robustly; 3) we introduce a new method named Mix Non-Maximum Suppression (Mix-NMS), which can significantly improve its ability in filtering the redundant detection result in our task. Extensive experiments on a real industrial dataset show that ACRM achieves state-of-the-art results compared to the existing methods, demonstrating the effectiveness and robustness of our detection method.

关键词： Filtering Quality control Production Detectors Feature extraction Robustness pattern recognition

Detail-recovery Image Deraining via Context Aggregation Networks

学校读者我要写书评

暂无评论

Detail-recovery Image Deraining via Context Aggregation Netw...

Conference on Computer Vision and pattern Recognition (CVPR)

作者： Sen Deng Mingqiang Wei Jun Wang Yidan Feng Luming Liang Haoran Xie Fu Lee Wang Meng Wang Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Microsoft Applied Sciences Group Lingnan University The Open University of Hong Kong Hefei University of Technology

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

This paper looks at this intriguing question: are single images with their details lost during deraining, reversible to their artifact-free status? We propose an end-to-end detail-recovery image deraining network (termed a DRDNet) to solve the problem. Unlike existing image deraining approaches that attempt to meet the conflicting goal of simultaneously deraining and preserving details in a unified framework, we propose to view rain removal and detail recovery as two seperate tasks, so that each part could specialize rather than trade-off between two conflicting goals. Specifically, we introduce two parallel sub-networks with a comprehensive loss function which synergize to derain and recover the lost details caused by deraining. For complete rain removal, we present a rain residual network with the squeeze-and-excitation (SE) operation to remove rain streaks from the rainy images. For detail recovery, we construct a specialized detail repair network consisting of welldesigned blocks, named structure detail context aggregation block (SDCAB), to encourage the lost details to return for eliminating image degradations. Moreover, the detail recovery branch of our proposed detail repair framework is detachable and can be incorporated into existing deraining methods to boost their performances. DRD-Net has been validated on several well-known benchmark datasets in terms of deraining robustness and detail accuracy. Comparisons show clear visual and numerical improvements of our method over the state-of-the-arts.

关键词： Rain Maintenance engineering Task analysis Degradation Training Feature extraction Visualization

Active learning for multiple target models 22

学校读者我要写书评

暂无评论

Active learning for multiple target models

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Ying-Peng Tang Sheng-Jun Huang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Collaborative Innovation Center of Novel Software Technology and Industrialization MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (纸本)9781713871088

We describe and explore a novel setting of active learning (AL), where there are multiple target models to be learned simultaneously. In many real applications, the machine learning system is required to be deployed on diverse devices with varying computational resources (e.g., workstation, mobile phone, edge devices), which leads to the demand of training multiple target models on the same labeled dataset. However, it is generally believed that AL is model-dependent and untransferable, i.e., the data queried by one model may be less effective for training another model. This phenomenon naturally raises a question "Does there exist an AL method that is effective for multiple target models?"". In this paper, we answer this question by theoretically analyzing the label complexity of active and passive learning under the setting with multiple target models, and conclude that AL does have potential to achieve better label complexity under this novel setting. Based on this insight, we further propose an agnostic AL sampling strategy to select the examples located in the joint disagreement regions of different target models. The experimental results on the OCR benchmarks show that the proposed method can significantly surpass the traditional active and passive learning methods under this challenging setting.

关键词：

InfoDiffusion: Information Entropy Aware Diffusion Process for Non-Autoregressive Text Generation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Renzhi Li, Jing Li, Piji College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China Department of Computing The Hong Kong Polytechnic University China

Diffusion models have garnered considerable interest in the field of text generation. Several studies have explored text diffusion models with different structures and applied them to various tasks, including named entity recognition and summarization. However, there exists a notable disparity between the "easy-first" text generation process of current diffusion models and the "keyword-first" natural text generation process of humans, which has received limited attention. To bridge this gap, we propose InfoDiffusion, a non-autoregressive text diffusion model. Our approach introduces a "keyinfo-first" generation strategy and incorporates a noise schedule based on the amount of text information. In addition, InfoDiffusion combines self-conditioning with a newly proposed partially noising model structure. Experimental results show that InfoDiffusion outperforms the baseline model in terms of generation quality and diversity, as well as exhibiting higher sampling efficiency.1 Copyright © 2023, The Authors. All rights reserved.

关键词： Character recognition

A Tailored Physics-informed Neural Network Method for Solving Singularly Perturbed Differential Equations 22

学校读者我要写书评

暂无评论

A Tailored Physics-informed Neural Network Method for Solvin...

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial intelligence

作者： Yiwen Pang Ye Li Sheng-Jun Huang College of Computer Science and Technology/Artificial Intelligence Nanjing University of Aeronautics and Astronautics China College of Computer Science and Technology/Artificial Intelligence Nanjing University of Aeronautics and Astronautics China and MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

ISBN: (纸本)9781450398336

Physics-informed neural networks (PINNs) have recently been demonstrated to be effective for the numerical solution of differential equations, with the advantage of small real labelled data needed. However, the performance of PINN greatly depends on the differential equation. The solution of singularly perturbed differential equations (SPDEs) usually contains a boundary layer, which makes it difficult for PINN to approximate the solution of SPDEs. In this paper, we analyse the reasons for the failure of PINN in solving SPDE and provide a feasible solution by adding prior knowledge of the boundary layer to the neural network. The new method is called the tailored physics-informed neural network (TPINN) since the network is tailored to some particular properties of the problem. Numerical experiments show that our method can effectively improve both the training speed and accuracy of neural networks.

关键词： physics-informed neural network prior knowledge boundary layer singularly perturbed differential equation

Improving model robustness by adaptively correcting perturbation levels with active queries

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ning, Kun-Peng Tao, Lue Chen, Songcan Huang, Sheng-Jun College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing211106 China

In addition to high accuracy, robustness is becoming increasingly important for machine learning models in various applications. Recently, much research has been devoted to improving the model robustness by training with noise perturbations. Most existing studies assume a fixed perturbation level for all training examples, which however hardly holds in real tasks. In fact, excessive perturbations may destroy the discriminative content of an example, while deficient perturbations may fail to provide helpful information for improving the robustness. Motivated by this observation, we propose to adaptively adjust the perturbation levels for each example in the training process. Specifically, a novel active learning framework is proposed to allow the model to interactively query the correct perturbation level from human experts. By designing a cost-effective sampling strategy along with a new query type, the robustness can be significantly improved with a few queries. Both theoretical analysis and experimental studies validate the effectiveness of the proposed approach. © 2021, CC BY.

关键词： Cost effectiveness

MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liang, Dong Zhang, Jing-Wei Tang, Ying-Peng Huang, Sheng-Jun The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing211106 China

Recent aerial object detection models rely on a large amount of labeled training data, which requires unaffordable manual labeling costs in large aerial scenes with dense objects. Active learning effectively reduces the data labeling cost by selectively querying the informative and representative unlabelled samples. However, existing active learning methods are mainly with class-balanced settings and image-based querying for generic object detection tasks, which are less applicable to aerial object detection scenarios due to the long-tailed class distribution and dense small objects in aerial scenes. In this paper, we propose a novel active learning method for cost-effective aerial object detection. Specifically, both object-level and image-level informativeness are considered in the object selection to refrain from redundant and myopic querying. Besides, an easy-to-use class-balancing criterion is incorporated to favor the minority objects to alleviate the long-tailed class distribution problem in model training. We further devise a training loss to mine the latent knowledge in the unlabeled image regions. Extensive experiments are conducted on the DOTA-v1.0 and DOTA-v2.0 benchmarks to validate the effectiveness of the proposed method. For the ReDet, KLD, and SASM detectors on the DOTAv2.0 dataset, the results show that our proposed MUS-CDB method can save nearly 75% of the labeling cost while achieving comparable performance to other active learning methods in terms of mAP. Code is publicly online. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

Truly proximal policy optimization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Yuhui He, Hao Wen, Chao Tan, Xiaoyang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing210016 China

Proximal policy optimization (PPO) is one of the most successful deep reinforcement-learning methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, its optimization behavior is still far from being fully understood. In this paper, we show that PPO could neither strictly restrict the likelihood ratio as it attempts to do nor enforce a well-defined trust region constraint, which means that it may still suffer from the risk of performance instability. To address this issue, we present an enhanced PPO method, named Truly PPO. Two critical improvements are made in our method: 1) it adopts a new clipping function to support a rollback behavior to restrict the difference between the new policy and the old one;2) the triggering condition for clipping is replaced with a trust region-based one, such that optimizing the resulted surrogate objective function provides guaranteed monotonic improvement of the ultimate policy performance. It seems, by adhering more truly to making the algorithm proximal - confining the policy within the trust region, the new algorithm improves the original PPO on both sample efficiency and performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning