Graph-based few-shot learning with transformed feature propagation and optimal class allocation

Zhang, Ruiheng; Yang, Shuo; Zhang, Qi; Xu, Lixin; He, Ya‐Ling; Zhang, Fan

doi:10.1016/j.neucom.2021.10.110

Cited by 59 publications

(26 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Part-based Few-shot Learning. Few-shot learning is a long-lasting important problem and many methods have been proposed to address it from different aspects [6,12,32,36,45,46,49]. Recently, parts have shown to be beneficial to it as the modeling of parts alleviates the scarcity of training data and enables efficient transfer learning between classes.…”

Section: Part-based Modelsmentioning

confidence: 99%

PartImageNet: A Large, High-Quality Dataset of Parts

He¹,

Yang²,

Yang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

A part-based object understanding facilitates efficient compositional learning and knowledge transfer, robustness to occlusion, and has the potential to increase the performance on general recognition and localization tasks. However, research on part-based models is hindered due to the lack of datasets with part annotations, which is caused by the extreme difficulty and high cost of annotating object parts in images. In this paper, we propose PartImageNet, a large, high-quality dataset with part segmentation annotations. It consists of 158 classes from ImageNet with approximately 24 000 images. PartImageNet is unique because it offers part-level annotations on a general set of classes with non-rigid, articulated objects, while having an order of magnitude larger size compared to existing datasets. It can be utilized in multiple vision tasks including but not limited to: Part Discovery, Semantic Segmentation, Fewshot Learning. Comprehensive experiments are conducted to set up a set of baselines on PartImageNet and we find that existing works on part discovery can not always produce satisfactory results during complex variations. The exploit of parts on downstream tasks also remains insufficient. We believe that our PartImageNet will greatly facilitate the research on part-based models and their applications. The dataset and scripts will soon be released at https://github.com/TACJu/PartImageNet.

show abstract

Section: Part-based Modelsmentioning

confidence: 99%

PartImageNet: A Large, High-Quality Dataset of Parts

He¹,

Yang²,

Yang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Numerous research endeavours have, therefore, focused on alleviating the cumbersome training process through constructing small training sets [1,14,7,13,42,31,33,44,45,50]. One classic approach is known as coreset or subset selection [1,31,12], which aims to obtain a subset of salient data points to represent the original dataset of interest.…”

Section: Introductionmentioning

confidence: 99%

CAFE: Learning to Condense Dataset by Aligning Features

Wang¹,

Zhao²,

Peng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one. State-of-the-art approaches largely rely on learning the synthetic data by matching the gradients between the real and synthetic data batches. Despite the intuitive motivation and promising results, such gradient-based methods, by nature, easily overfit to a biased set of samples that produce dominant gradients, and thus lack a global supervision of data distribution. In this paper, we propose a novel scheme to Condense dataset by Aligning FEatures (CAFE), which explicitly attempts to preserve the real-feature distribution as well as the discriminant power of the resulting synthetic set, lending itself to strong generalization capability to various architectures. At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales, while accounting for the classification of real samples. Our scheme is further backed up by a novel dynamic bi-level optimization, which adaptively adjusts parameter updates to prevent over-/under-fitting. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art: on the SVHN dataset, for example, the performance gain is up to 11%. Extensive experiments and analysis verify the effectiveness and necessity of proposed designs.

show abstract

“…Indeed, the objective here is to propose a decision algorithm that, on the one hand, respects the choices and the interests of each actor and, on the other hand, does not require a large data history. This is why we decided to use a reinforcement-learning approach distributed between the actors and not a centralized supervised or unsupervised learning approach (see for example [28,29]).…”

Section: Introductionmentioning

confidence: 99%

Distributed Reinforcement Learning for the Management of a Smart Grid Interconnecting Independent Prosumers

Barth

Cohen-Boulakia²,

Ehounou

2022

Energies

View full text Add to dashboard Cite

In the context of an eco-responsible production and distribution of electrical energy at the local scale of an urban territory, we consider a smart grid as a system interconnecting different prosumers, which all retain their decision-making autonomy and defend their own interests in a comprehensive system where the rules, accepted by all, encourage virtuous behavior. In this paper, we present and analyze a model and a management method for smart grids that is shared between different kinds of independent actors, who respect their own interests, and that encourages each actor to behavior that allows, as much as possible, an energy independence of the smart grid from external energy suppliers. We consider here a game theory model, in which each actor of the smart grid is a player, and we investigate distributed machine-learning algorithms to allow decision-making, thus, leading the game to converge to stable situations, in particular to a Nash equilibrium. We propose a Linear Reward Inaction algorithm that achieves Nash equilibria most of the time, both for a single time slot and across time, allowing the smart grid to maximize its energy independence from external energy suppliers.

show abstract

Graph-based few-shot learning with transformed feature propagation and optimal class allocation

Cited by 59 publications

References 23 publications

PartImageNet: A Large, High-Quality Dataset of Parts

PartImageNet: A Large, High-Quality Dataset of Parts

CAFE: Learning to Condense Dataset by Aligning Features

Distributed Reinforcement Learning for the Management of a Smart Grid Interconnecting Independent Prosumers

Contact Info

Product

Resources

About