Harnessing heterogeneity in space with statistically guided meta-learning

Xie, Yiqun; Chen, Weiye; He, Erhu; Jia, Xiaowei; Bao, Haikun; Zhou, Xun; Ghosh, Rahul; Ravirathinam, Praveen

doi:10.1007/s10115-023-01847-0

Cited by 2 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Embedding spatial data in the training phase provides a meaningful solution, but its agnostic spatial extent poses a huge challenge. Li et al [254] proposed a spatial moderator to generalize learned spatial patterns and spatialized network structures from the original region to the new region. Meanwhile, the method introduced model-agnostic meta-learning methods to address the issue that the acquisition of deep learning models is limited to individual partitions or locations.…”

Section: Meta Learningmentioning

confidence: 99%

Deep Learning Methods for Semantic Segmentation in Remote Sensing with Small Data: A Survey

Yu,

Quan,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The annotations used during the training process are crucial for the inference results of remote sensing images (RSIs) based on a deep learning framework. Unlabeled RSIs can be obtained relatively easily. However, pixel-level annotation is a process that necessitates a high level of expertise and experience. Consequently, the use of small sample training methods has attracted widespread attention as they help alleviate reliance on large amounts of high-quality labeled data and current deep learning methods. Moreover, research on small sample learning is still in its infancy owing to the unique challenges faced when completing semantic segmentation tasks with RSI. To better understand and stimulate future research that utilizes semantic segmentation tasks with small data, we summarized the supervised learning methods and challenges they face. We also reviewed the supervised approaches with data that are currently popular to help elucidate how to efficiently utilize a limited number of samples to address issues with semantic segmentation in RSI. The main methods discussed are self-supervised learning, semi-supervised learning, weakly supervised learning and few-shot methods. The solution of cross-domain challenges has also been discussed. Furthermore, multi-modal methods, prior knowledge constrained methods, and future research required to help optimize deep learning models for various downstream tasks in relation to RSI have been identified.

show abstract

Section: Meta Learningmentioning

confidence: 99%

Deep Learning Methods for Semantic Segmentation in Remote Sensing with Small Data: A Survey

Yu,

Quan,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Sample-reweighting and self-training approaches (Bickel, Brückner, and Scheffer 2007;An et al 2022a;He et al 2023) also aim to reduce the distribution gap between training and testing sets by assigning higher weights to samples more similar to test samples feature-wise, or include highconfidence pseudo-labels on test samples during training. In addition, heterogeneity-aware learning tackles variability by data partitioning and network branching (Xie et al 2021(Xie et al , 2023. While these methods address distribution shifts, they also do not consider the changes of groups (locations) between training and test for fairness applications.…”

Section: Introductionmentioning

confidence: 99%

“…While these methods address distribution shifts, they also do not consider the changes of groups (locations) between training and test for fairness applications. Meta-learning: Model-agnostic meta learning (MAML)'s gradient-by-gradient training allows it to learn an initial model that can be quickly fine-tuned to the test data with only a small number of observations (Finn, Abbeel, and Levine 2017;Ren et al 2018;Xie et al 2023;Chen et al 2023). Recent developments have also started exploring the use of MAML in fairness-aware learning (Zhao et al 2020(Zhao et al , 2022a.…”

Section: Introductionmentioning

confidence: 99%

Referee-Meta-Learning for Fast Adaptation of Locational Fairness

Chen,

Xie,

Jia

et al. 2024

AAAI

View full text Add to dashboard Cite

When dealing with data from distinct locations, machine learning algorithms tend to demonstrate an implicit preference of some locations over the others, which constitutes biases that sabotage the spatial fairness of the algorithm. This unfairness can easily introduce biases in subsequent decision-making given broad adoptions of learning-based solutions in practice. However, locational biases in AI are largely understudied. To mitigate biases over locations, we propose a locational meta-referee (Meta-Ref) to oversee the few-shot meta-training and meta-testing of a deep neural network. Meta-Ref dynamically adjusts the learning rates for training samples of given locations to advocate a fair performance across locations, through an explicit consideration of locational biases and the characteristics of input data. We present a three-phase training framework to learn both a meta-learning-based predictor and an integrated Meta-Ref that governs the fairness of the model. Once trained with a distribution of spatial tasks, Meta-Ref is applied to samples from new spatial tasks (i.e., regions outside the training area) to promote fairness during the fine-tune step. We carried out experiments with two case studies on crop monitoring and transportation safety, which show Meta-Ref can improve locational fairness while keeping the overall prediction quality at a similar level.

show abstract

Harnessing heterogeneity in space with statistically guided meta-learning

Cited by 2 publications

References 30 publications

Deep Learning Methods for Semantic Segmentation in Remote Sensing with Small Data: A Survey

Deep Learning Methods for Semantic Segmentation in Remote Sensing with Small Data: A Survey

Referee-Meta-Learning for Fast Adaptation of Locational Fairness

Contact Info

Product

Resources

About