Learning to Compare: Relation Network for Few-Shot Learning

Sung, Flood; Yang, Yongxin; Zhang, Li; Xiang, Tao; Torr, Philip H. S.; Hospedales, Timothy M.

doi:10.1109/cvpr.2018.00131

Cited by 3,744 publications

(2,757 citation statements)

References 26 publications

Supporting

Mentioning

2,749

Contrasting

Unclassified

Order By: Relevance

“…Few-shot classification predicts image class labels with access to few training examples. Prior work can be broadly divided into three groups: transfer learning of models trained on classes similar to the target classes [28,22,29,30], meta-learning approaches that learn how to effectively learn new classes from small datasets [8,18], and generative approaches aimed at data-augmentation [31,25].…”

Section: Related Workmentioning

confidence: 99%

Feature Weighting and Boosting for Few-Shot Segmentation

Nguyen

Todorovic

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

297

173

View full text Add to dashboard Cite

This paper is about few-shot segmentation of foreground objects in images. We train a CNN on small subsets of training images, each mimicking the few-shot setting. In each subset, one image serves as the query and the other(s) as support image(s) with ground-truth segmentation. The CNN first extracts feature maps from the query and support images. Then, a class feature vector is computed as an average of the support's feature maps over the known foreground. Finally, the target object is segmented in the query image by using a cosine similarity between the class feature vector and the query's feature map. We make two contributions by: (1) Improving discriminativeness of features so their activations are high on the foreground and low elsewhere; and (2) Boosting inference with an ensemble of experts guided with the gradient of loss incurred when segmenting the support images in testing. Our evaluations on the PASCAL-5 i and COCO-20 i datasets demonstrate that we significantly outperform existing approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Feature Weighting and Boosting for Few-Shot Segmentation

Nguyen

Todorovic

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

297

173

View full text Add to dashboard Cite

show abstract

“…Current meta-learning approaches that find a modelweight initialization are typically evaluated by applying them to few-shot classification problems, because it is generally easier to generate the necessary number of tasks required for meta-learning when dealing with few-shot tasks. Few-shot learning [6,21,4] strives to achieve the highest possible classification performance when faced with a new task that comprises only a handful of samples per class. This can be achieved by learning an initialization that converges fast, even when only few instances are given, but also through the application of other meta-learning approaches.…”

Section: Related Workmentioning

confidence: 99%

“…Another category of meta-learning approaches is referred to as Transfer Learning [20,14]. It describes the process of training a model on different auxiliary tasks and then using the learned model to actually fit to the target problem to improve performance.…”

Section: Related Workmentioning

confidence: 99%

HIDRA: Head Initialization across Dynamic targets for Robust Architectures

Drumond¹,

Brinkmeyer²,

Grabocka³

et al. 2020

Proceedings of the 2020 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

The performance of gradient-based optimization strategies depends heavily on the initial weights of the parametric model. Recent works show that there exist weight initializations from which optimization procedures can find the taskspecific parameters faster than from uniformly random initializations, and that such a weight initialization can be learned by optimizing a specific model architecture across similar tasks via maml (Model-Agnostic Meta-Learning). Current methods are limited to populations of classification tasks that share the same number of classes due to the static model architectures used during meta-learning. In this paper, we present hidra, a meta-learning approach that enables training and evaluating across tasks with any number of target variables. We show that Model-Agnostic Meta-Learning trains a distribution for all the neurons in the output layer and a specific weight initialization for the ones in the hidden layers. Hydra explores this by learning one master neuron which is used to initialize any number of output neurons for a new task. Extensive experiments on the Miniimagenet and Omniglot data sets demonstrate that hidra improves over standard approaches while generalizing to tasks with any number of target variables. Moreover, our approach is shown to robustify low-capacity models in learning across complex tasks with a high number of classes for which regular MAML fails to learn any feasible initialization.

show abstract

“…1) Model: The few-shot learning-based classifier is trained within the framework of meta-learning [17]. The key idea is to learn the transferred knowledge among a large number of similar few-shot tasks, which can be further used for the new tasks [17], [45], [46]. Each few-shot task includes a support set and a query set.…”

Section: B Food Item Recognitionmentioning

confidence: 99%

An Artificial Intelligence-Based System for Nutrient Intake Assessment of Hospitalised Patients

Stathopoulou

Vasiloglou

et al. 2019

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

Regular monitoring of nutrient intake in hospitalised patients plays a critical role in reducing the risk of disease-related malnutrition. Although several methods to estimate nutrient intake have been developed, there is still a clear demand for a more reliable and fully automated technique, as this could improve data accuracy and reduce both the burden on participants and health costs. In this paper, we propose a novel system based on artificial intelligence (AI) to accurately estimate nutrient intake, by simply processing RGB Depth (RGB-D) image pairs captured before and after meal consumption. The system includes a novel multi-task contextual network for food segmentation, a few-shot learning-based classifier built by limited training samples for food recognition, and an algorithm for 3D surface construction. This allows sequential food segmentation, recognition, and estimation of the consumed food volume, permitting fully automatic estimation of the nutrient intake for each meal. For the development and evaluation of the system, a dedicated new database containing images and nutrient recipes of 322 meals is assembled, coupled to data annotation using innovative strategies. Experimental results demonstrate that the estimated nutrient intake is highly correlated (> 0.91) to the ground truth and shows very small mean relative errors (< 20%), outperforming existing techniques proposed for nutrient intake assessment.

show abstract

Learning to Compare: Relation Network for Few-Shot Learning

Cited by 3,744 publications

References 26 publications

Feature Weighting and Boosting for Few-Shot Segmentation

Feature Weighting and Boosting for Few-Shot Segmentation

HIDRA: Head Initialization across Dynamic targets for Robust Architectures

An Artificial Intelligence-Based System for Nutrient Intake Assessment of Hospitalised Patients

Contact Info

Product

Resources

About