Few-shot learning (FSL) has emerged as an effective learning method and shows great potential. Despite the recent creative works in tackling FSL tasks, learning valid information rapidly from just a ...few or even zero samples remains a serious challenge. In this context, we extensively investigated 200+ FSL papers published in top journals and conferences in the past three years, aiming to present a timely and comprehensive overview of the most recent advances in FSL with a fresh perspective and to provide an impartial comparison of the strengths and weaknesses of existing work. To avoid conceptual confusion, we first elaborate and contrast a set of relevant concepts including few-shot learning, transfer learning, and meta-learning. Then, we inventively extract prior knowledge related to few-shot learning in the form of a pyramid, which summarizes and classifies previous work in detail from the perspective of challenges. Furthermore, to enrich this survey, we present in-depth analysis and insightful discussions of recent advances in each subsection. What is more, taking computer vision as an example, we highlight the important application of FSL, covering various research hotspots. Finally, we conclude the survey with unique insights into technology trends and potential future research opportunities to guide FSL follow-up research.
Motion Shot friert Bewegungen ein Ivanjek, Lana; Hopf, Martin; Wilhelm, Thomas
Physik in unserer Zeit,
01/2019, Letnik:
50, Številka:
1
Journal Article
Mit der App Motion Shot können ganz einfach Stroboskop‐ und Serienfotos erstellt und Bewegungen qualitativ analysiert werden. Dazu führt die App verschiedene Bilder eines Videofilms in einem Bild ...zusammen.
Generalizing from a Few Examples Wang, Yaqing; Yao, Quanming; Kwok, James T. ...
ACM computing surveys,
06/2020, Letnik:
53, Številka:
3
Journal Article
Recenzirano
Machine learning has been highly successful in data-intensive applications but is often hampered when the data set is small. Recently, Few-shot Learning (FSL) is proposed to tackle this problem. ...Using prior knowledge, FSL can rapidly generalize to new tasks containing only a few samples with supervised information. In this article, we conduct a thorough survey to fully understand FSL. Starting from a formal definition of FSL, we distinguish FSL from several relevant machine learning problems. We then point out that the core issue in FSL is that the empirical risk minimizer is unreliable. Based on how prior knowledge can be used to handle this core issue, we categorize FSL methods from three perspectives: (i) data, which uses prior knowledge to augment the supervised experience; (ii) model, which uses prior knowledge to reduce the size of the hypothesis space; and (iii) algorithm, which uses prior knowledge to alter the search for the best hypothesis in the given hypothesis space. With this taxonomy, we review and discuss the pros and cons of each category. Promising directions, in the aspects of the FSL problem setups, techniques, applications, and theories, are also proposed to provide insights for future research.
1
Prevalent techniques in zero-shot learning do not generalize well to other related problem scenarios. Here, we present a unified approach for conventional zero-shot, generalized zero-shot, and ...few-shot learning problems. Our approach is based on a novel class adapting principal directions' (CAPDs) concept that allows multiple embeddings of image features into a semantic space. Given an image, our method produces one principal direction for each seen class. Then, it learns how to combine these directions to obtain the principal direction for each unseen class such that the CAPD of the test image is aligned with the semantic embedding of the true class and opposite to the other classes. This allows efficient and class-adaptive information transfer from seen to unseen classes. In addition, we propose an automatic process for the selection of the most useful seen classes for each unseen class to achieve robustness in zero-shot learning. Our method can update the unseen CAPD taking the advantages of few unseen images to work in a few-shot learning scenario. Furthermore, our method can generalize the seen CAPDs by estimating seen-unseen diversity that significantly improves the performance of generalized zero-shot learning. Our extensive evaluations demonstrate that the proposed approach consistently achieves superior performance in zero-shot, generalized zero-shot, and few/one-shot learning problems.
A CFD-FEM numerical study on shot peening Lin, Qinjie; Wei, Peitang; Liu, Huaiju ...
International journal of mechanical sciences,
06/2022, Letnik:
223
Journal Article
Recenzirano
•A CFD-FEM shot peening model was developed to correlate machine parameters with surface integrity.•As the air pressure increases, the shot velocity increases and then becomes stable.•The influences ...of shot velocity and diameter on surface integrity were studied.•Double shot peening introduces a considerable compressive stress layer.
Surface integrity after shot peening is affected by various parameters. Improper selection of shot peening parameters brings challenges in improving the component's fatigue life or even damages the original surface. An insight into the effects of shot peening parameters on surface integrity is a prerequisite for the appropriate setting of process parameters. This study used the computational fluid dynamics (CFD) method to establish a two-phase flow model describing relationships between shot velocity and pneumatic shot peening machine parameters, such as air pressure and peening distance. A random multi-shots finite element model (FEM) was established to study the effects of shot velocity and shot diameter on surface integrity. Results indicate that the peening distance and air pressure significantly affect shot velocity. Compared to increasing shot velocity, peening with larger diameter shots is more effective in generating compressive residual stress (CRS) and dislocation cell refinement layers. However, it results in a decline in the magnitude of surface compressive residual stress (SCRS). Double shot peening combines the characteristics of different diameter shots, which introduces high SCRS and considerable CRS layer thickness.
Display omitted
State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results and hardly work on unseen classes without fine-tuning. Few-shot segmentation is thus proposed to ...tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information of training classes and spatial inconsistency between query and support targets. To alleviate these issues, we propose the Prior Guided Feature Enrichment Network (PFENet). It consists of novel designs of (1) a training-free prior mask generation method that not only retains generalization power but also improves model performance and (2) Feature Enrichment Module (FEM) that overcomes spatial inconsistency by adaptively enriching query features with support features and prior masks. Extensive experiments on PASCAL-5<inline-formula><tex-math notation="LaTeX">^i</tex-math> <mml:math><mml:msup><mml:mrow/><mml:mi>i</mml:mi></mml:msup></mml:math><inline-graphic xlink:href="tian-ieq1-3013717.gif"/> </inline-formula> and COCO prove that the proposed prior generation method and FEM both improve the baseline method significantly. Our PFENet also outperforms state-of-the-art methods by a large margin without efficiency loss. It is surprising that our model even generalizes to cases without labeled support samples.
Object detection has achieved a huge breakthrough with deep neural networks and massive annotated data. However, current detection methods cannot be directly transferred to the scenario where the ...annotated data is scarce due to the severe overfitting problem. Although few-shot learning and zero-shot learning have been extensively explored in the field of image classification, it is indispensable to design new methods for object detection in the data-scarce scenario, since object detection has an additional challenging localization task. Low-Shot Object Detection (LSOD) is an emerging research topic of detecting objects from a few or even no annotated samples, consisting of One-Shot Object Localization (OSOL), Few-Shot Object Detection (FSOD), and Zero-Shot Object Detection (ZSOD). This survey provides a comprehensive review of LSOD methods. First, we propose a thorough taxonomy of LSOD methods and analyze them systematically, comprising some extensional topics of LSOD (semi-supervised LSOD, weakly supervised LSOD, and incremental LSOD). Then, we indicate the pros and cons of current LSOD methods with a comparison of their performance.Finally, we discuss the challenges and promising directions of LSOD to provide guidance for future works.