The basic goal of Automatic Check-Out (ACO) task is to accurately predict the categories and quantities of products selected by customers in the check-out images. However, there is a significant ...domain gap between the single-product exemplars as training data and the check-out images as testing data. To mitigate the domain gap, we propose a novel method termed as Prototype Learning for Automatic Check-Out (PLACO). In PLACO, prototype learning is designed to reach the goal in two ways. Specifically, in the prototype-based classifier learning module, to fully exploit the invariance of category prototypes, the prototypes obtained from the single-product exemplars are employed to generate classifiers for classifying the proposals of check-out image. On the other side, in prototype alignment module, prototypes for both the single-product exemplar and check-out image domains are entered simultaneously to ensure intra-category compactness and inter-category sparsity. Moreover, to further improve the performance of PLACO, we develop a discriminative re-ranking module to both adjust the predicted scores of product proposals for bringing more discriminative ability in classifier learning and provide a reasonable sorting possibility by considering the fine-grained nature. Experiments are conducted on the large-scale RPC dataset for evaluations. Our PLACO obtains the optimal results in both traditional ACO task setting and incremental task setting.
Deep learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have ...been devoted to domain adaptive semantic segmentation that focuses on transferring semantic knowledge from a labeled source domain to an unlabeled target domain. Existing self-training methods typically require multiple rounds of training, while another popular framework based on adversarial training is known to be sensitive to hyper-parameters. We propose an easy-to-train framework that learns domain-invariant prototypes for domain adaptive semantic segmentation. In particular, we show that domain adaptation shares a common character with few-shot learning in that both aim to recognize some types of unseen data with knowledge learned from large amounts of seen data. Thus, we propose a unified framework for domain adaptation and few-shot learning. The core idea is to use the class prototypes extracted from few-shot annotated target images to classify pixels of both source images and target images. Our method involves only one-stage training and does not need to be trained on large-scale un-annotated target images. Moreover, our method can be extended to variants of both domain adaptation and few-shot learning. Competitive performances achieved on GTA5-to-Cityscapes and SYNTHIA-to-Cityscapes adaptation tasks show the effectiveness of the proposed novel while simple domain adaptation framework. The source code used in this paper is available at https://github.com/zgyang-hnu/DIP-hunnu.
In typical unsupervised domain adaptive object detection, it is assumed that extensive unlabeled training data from the target domain can be easily obtained. However, in some access-constrained ...scenarios, massive target data cannot be guaranteed, but acquiring only a few target samples and annotating them may costs less. Therefore, inspired by the meta-learning success in few-shot tasks, we propose an Instance-level Prototype learning Network (IPNet) for solving the domain adaptive object detection under the supervised few-shot scenario in this work. To compensate for the target domain data deficiency, we fuse cropped instances from labeled images in both domains to learn a representative prototype for each class, by enforcing features of the same class's instances but from different domains to be as close as possible. These prototypes are further employed to discriminate various features' salience in an image, and separate foreground and background regions for respective domain alignment. Extensive experiments are conducted on several cross-domain scenarios, and their results show the consistent accuracy gains of the IPNet over state-of-the-art methods, e.g ., 10.4% mAP increase on Cityscapes-to-FoggyCityscapes setting and 3.0% mAP increase on Sim10k-to-Cityscapes setting.
With the rapid development of optoelectronic fields, electrochromic (EC) materials and devices have received remarkable attention and have shown attractive potential for use in emerging wearable and ...portable electronics, electronic papers/billboards, see-through displays, and other new-generation displays, due to the advantages of low power consumption, easy viewing, flexibility, stretchability, etc. Despite continuous progress in related fields, determining how to make electrochromics truly meet the requirements of mature displays (e.g., ideal overall performance) has been a long-term problem. Therefore, the commercialization of relevant high-quality products is still in its infancy. In this review, we will focus on the progress in emerging EC materials and devices for potential displays, including two mainstream EC display prototypes (segmented displays and pixel displays) and their commercial applications. Among these topics, the related materials/devices, EC performance, construction approaches, and processing techniques are comprehensively disscussed and reviewed. We also outline the current barriers with possible solutions and discuss the future of this field.
The nearest neighbor classifier is one of the most used and well-known techniques for performing recognition tasks. It has also demonstrated itself to be one of the most useful algorithms in data ...mining in spite of its simplicity. However, the nearest neighbor classifier suffers from several drawbacks such as high storage requirements, low efficiency in classification response, and low noise tolerance. These weaknesses have been the subject of study for many researchers and many solutions have been proposed. Among them, one of the most promising solutions consists of reducing the data used for establishing a classification rule (training data) by means of selecting relevant prototypes. Many prototype selection methods exist in the literature and the research in this area is still advancing. Different properties could be observed in the definition of them, but no formal categorization has been established yet. This paper provides a survey of the prototype selection methods proposed in the literature from a theoretical and empirical point of view. Considering a theoretical point of view, we propose a taxonomy based on the main characteristics presented in prototype selection and we analyze their advantages and drawbacks. Empirically, we conduct an experimental study involving different sizes of data sets for measuring their performance in terms of accuracy, reduction capabilities, and runtime. The results obtained by all the methods studied have been verified by nonparametric statistical tests. Several remarks, guidelines, and recommendations are made for the use of prototype selection for nearest neighbor classification.
Domain Adaptation Without Source Data Kim, Youngeun; Cho, Donghyeon; Han, Kyeongtak ...
IEEE transactions on artificial intelligence,
2021-Dec., 2021-12-00, Letnik:
2, Številka:
6
Journal Article
Recenzirano
Odprti dostop
Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such an assumption is rarely plausible in the real world and possibly ...causes data privacy issues, especially when the label of the source domain can be a sensitive attribute as an identifier. To avoid accessing source data that could contain sensitive information, we introduce source data free domain adaptation (SFDA). Our key idea is to leverage a pretrained model from the source domain and progressively update the target model in a self-learning manner. We observe that target samples with lower self-entropy measured by the pretrained source model are more likely to be classified correctly. From this, we select the reliable samples with the self-entropy criterion and define these as class prototypes. We then assign pseudolabels for every target sample based on the similarity score with class prototypes. We further propose point-to-set distance-based filtering, which does not require any tunable hyperparameters to reduce uncertainty from the pseudolabeling process. Finally, we train the target model with the filtered pseudolabels with regularization from the pretrained source model. Surprisingly, without direct usage of labeled source samples, our SFDA outperforms conventional domain adaptation methods on benchmark datasets.
Impact Statement -This study addresses the data privacy issue, especially in unsupervised domain adaptation. Based on our privacy-preserving domain adaptation, various stakeholders, including enterprises and government organizations, can be free of concern about privacy issues with their labeled source dataset. Furthermore, the proposed data-free approach can contribute to creating a positive social impact, especially in large-scale datasets. Recently, since the size of data across various fields has been scaling up, it is almost incapable for individual researchers to directly utilize a large scale of data during training. For this reason, a new social trend of sharing pretrained models, e.g., EfficientNet and BERT, led by global enterprises with their huge amount of resources has been rising up. From this viewpoint, our approach thus enables more people to participate in the domain adaptation field specifically when the source data are large scale and contain sensitive attributes.
In-Network Key-Value Cache with Linearizability Qin, Yuxuan; Gao, Weize; Lao, ChonLam ...
2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS),
2023-Dec.-17
Conference Proceeding
Recently, In-Network Cache (INC) systems have been proposed to promote the performance of remote storage systems. INC offloads cache onto programmable switches between the clients and the servers, ...responding to clients' data queries within a sub-RTT time. However, most existing INC solutions do not take applications' linearizability requirement into consideration, which could lead to query errors and storage state errors in the runtime. We propose a new INC system - NetKV-L, which preserves the high-performance I/O without compromising the linearizability. NetKV-L devises a sequentiality enforcement mechanism, a PSN correction mechanism, and a response memorization mechanism to guarantee linearizability under possible unreliable network conditions. Our prototype and experiments show that NetKV-L could achieve almost the same performance as the state-of-the-art systems while additionally guaranteeing linearizability.
Fast Multi-View Clustering via Prototype Graph Shi, Shaojun; Nie, Feiping; Wang, Rong ...
IEEE transactions on knowledge and data engineering,
01/2023, Letnik:
35, Številka:
1
Journal Article
Recenzirano
Odprti dostop
Multi-view clustering attracts considerable attention due to its effectiveness in unsupervised learning. However, previous multi-view spectral clustering methods include two separated steps: 1) ...Obtaining a spectral embedding; 2) Performing classical clustering methods. Although these methods have achieved promising performance, there is still some limitations. First, in computing spectral embedding, multi-view spectral clustering approaches exist high computational complexity since they usually need eigenvalue decomposition on laplacian matrix <inline-formula><tex-math notation="LaTeX">L</tex-math> <mml:math><mml:mi>L</mml:mi></mml:math><inline-graphic xlink:href="shi-ieq1-3078728.gif"/> </inline-formula>; Second, in constructing similarity matrices, previous methods need to compute similarity between any two samples; Third, the two-stage approach only can obtain the sub-optimal solution; Fourth, treating equally all views is unreasonable. To address these issues, we propose a Fast Multi-view Clustering via Prototype Graph (FMVPG) method. Specifically, the prototype graph is first constructed, and then simultaneously perform spectral embedding to obtain the real matrix and spectral rotation to get the indicator matrix. In addition, the alternative optimization strategy is used to solve the proposed model. Further, we conduct extensive experiments to evaluate the proposed FMVPG approach. These experimental results show the comparable or even better clustering performance than the state-of-the-art approaches.