English
Related papers

Related papers: Low-Shot Validation: Active Importance Sampling fo…

200 papers

We introduce a new framework for sample-efficient model evaluation that we call active testing. While approaches like active learning reduce the number of labels needed for model training, existing literature largely ignores the cost of…

Machine Learning · Statistics 2021-06-15 Jannik Kossen , Sebastian Farquhar , Yarin Gal , Tom Rainforth

In tabular biomedical data analysis, tuning models to high accuracy is considered a prerequisite for discussing feature importance, as medical practitioners expect the validity of feature importance to correlate with performance. In this…

Machine Learning · Statistics 2025-10-20 Youngro Lee , Giacomo Baruzzo , Jeonghwan Kim , Jongmo Seo , Barbara Di Camillo

In this paper we propose strategies for estimating performance of a classifier when labels cannot be obtained for the whole test set. The number of test instances which can be labeled is very small compared to the whole test data size. The…

Machine Learning · Computer Science 2018-02-21 Anurag Kumar , Bhiksha Raj

Learning with few samples is a major challenge for parameter-rich models like deep networks. In contrast, people learn complex new concepts even from very few examples, suggesting that the sample complexity of learning can often be reduced.…

Machine Learning · Computer Science 2019-06-11 Roman Visotsky , Yuval Atzmon , Gal Chechik

Modern deep learning requires large-scale extensively labelled datasets for training. Few-shot learning aims to alleviate this issue by learning effectively from few labelled examples. In previously proposed few-shot visual classifiers, it…

Computer Vision and Pattern Recognition · Computer Science 2022-12-13 Peyman Bateni , Jarred Barber , Raghav Goyal , Vaden Masrani , Jan-Willem van de Meent , Leonid Sigal , Frank Wood

Rare properties remain a challenge for statistical model checking (SMC) due to the quadratic scaling of variance with rarity. We address this with a variance reduction framework based on lightweight importance splitting observers. These…

Logic in Computer Science · Computer Science 2015-04-29 Cyrille Jegourel , Axel Legay , Sean Sedwards , Louis-Marie Traonouez

Data is the engine of modern computer vision, which necessitates collecting large-scale datasets. This is expensive, and guaranteeing the quality of the labels is a major challenge. In this paper, we investigate efficient annotation…

Computer Vision and Pattern Recognition · Computer Science 2021-04-27 Yuan-Hong Liao , Amlan Kar , Sanja Fidler

Learning accurate classifiers for novel categories from very few examples, known as few-shot image classification, is a challenging task in statistical machine learning and computer vision. The performance in few-shot classification suffers…

Computer Vision and Pattern Recognition · Computer Science 2022-04-18 Saba Ghaffari , Ehsan Saleh , David Forsyth , Yu-xiong Wang

The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Yonglong Tian , Yue Wang , Dilip Krishnan , Joshua B. Tenenbaum , Phillip Isola

Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Many sophisticated methods have been developed to address the challenges this…

Computer Vision and Pattern Recognition · Computer Science 2022-09-29 Xiu-Shen Wei , He-Yang Xu , Faen Zhang , Yuxin Peng , Wei Zhou

Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require…

Computer Vision and Pattern Recognition · Computer Science 2016-11-24 Anna Khoreva , Rodrigo Benenson , Jan Hosang , Matthias Hein , Bernt Schiele

We propose a novel sample selection method for image classification in the presence of noisy labels. Existing methods typically consider small-loss samples as correctly labeled. However, some correctly labeled samples are inherently…

Computer Vision and Pattern Recognition · Computer Science 2025-04-25 Weiran Pan , Wei Wei , Feida Zhu , Yong Deng

Importance sampling has been reported to produce algorithms with excellent empirical performance in counting problems. However, the theoretical support for its efficiency in these applications has been very limited. In this paper, we…

Probability · Mathematics 2009-08-10 Jose H. Blanchet

While many active learning papers assume that the learner can simply ask for a label and receive it, real annotation often presents a mismatch between the form of a label (say, one among many classes), and the form of an annotation…

Machine Learning · Computer Science 2019-07-10 Peiyun Hu , Zachary C. Lipton , Anima Anandkumar , Deva Ramanan

Few-shot learning (FSL) methods typically assume clean support sets with accurately labeled samples when training on novel classes. This assumption can often be unrealistic: support sets, no matter how small, can still include mislabeled…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Kevin J Liang , Samrudhdhi B. Rangrej , Vladan Petrovic , Tal Hassner

Transductive inference is widely used in few-shot learning, as it leverages the statistics of the unlabeled query set of a few-shot task, typically yielding substantially better performances than its inductive counterpart. The current…

Machine Learning · Computer Science 2022-04-26 Olivier Veilleux , Malik Boudiaf , Pablo Piantanida , Ismail Ben Ayed

Large-scale pre-trained Vision-Language Models (VLMs) have exhibited impressive zero-shot performance and transferability, allowing them to adapt to downstream tasks in a data-efficient manner. However, when only a few labeled samples are…

Computer Vision and Pattern Recognition · Computer Science 2024-11-11 Ce Zhang , Simon Stepputtis , Katia Sycara , Yaqi Xie

In a standard classification framework a set of trustworthy learning data are employed to build a decision rule, with the final aim of classifying unlabelled units belonging to the test set. Therefore, unreliable labelled observations,…

Applications · Statistics 2019-11-20 Andrea Cappozzo , Francesca Greselin , Thomas Brendan Murphy

Few-shot learning aims to recognize new categories using very few labeled samples. Although few-shot learning has witnessed promising development in recent years, most existing methods adopt an average operation to calculate prototypes,…

Computer Vision and Pattern Recognition · Computer Science 2021-08-26 Minglei Yuan , Wenhai Wang , Tao Wang , Chunhao Cai , Qian Xu , Tong Lu

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Qian-Wei Wang , Yuqiu Xie , Letian Zhang , Zimo Liu , Shu-Tao Xia