English
Related papers

Related papers: Differentiable Entailment for Parameter Efficient …

200 papers

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Taolin Zhang , Jiawang Bai , Zhihe Lu , Dongze Lian , Genping Wang , Xinchao Wang , Shu-Tao Xia

Few-shot Learning has been studied to mimic human visual capabilities and learn effective models without the need of exhaustive human annotation. Even though the idea of meta-learning for adaptation has dominated the few-shot learning…

Computer Vision and Pattern Recognition · Computer Science 2021-09-17 Jiawei Ma , Hanchen Xie , Guangxing Han , Shih-Fu Chang , Aram Galstyan , Wael Abd-Almageed

The training of deep-learning-based text classification models relies heavily on a huge amount of annotation data, which is difficult to obtain. When the labeled data is scarce, models tend to struggle to achieve satisfactory performance.…

Computation and Language · Computer Science 2020-04-07 Dianbo Sui , Yubo Chen , Binjie Mao , Delai Qiu , Kang Liu , Jun Zhao

Pre-trained Language Models (PLMs) can be accurately fine-tuned for downstream text processing tasks. Recently, researchers have introduced several parameter-efficient fine-tuning methods that optimize input prompts or adjust a small number…

Computation and Language · Computer Science 2024-06-07 Saeed Najafi , Alona Fyshe

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

Few-shot in-context learning (ICL) enables pre-trained language models to perform a previously-unseen task without any gradient-based training by feeding a small number of training examples as part of the input. ICL incurs substantial…

Machine Learning · Computer Science 2022-08-29 Haokun Liu , Derek Tam , Mohammed Muqeeth , Jay Mohta , Tenghao Huang , Mohit Bansal , Colin Raffel

Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for…

Machine Learning · Computer Science 2023-05-18 Wenfang Sun , Yingjun Du , Xiantong Zhen , Fan Wang , Ling Wang , Cees G. M. Snoek

Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing works take the meta-learning approach, constructing a few-shot learner that can learn from few-shot examples to generate a classifier.…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Han-Jia Ye , Lu Ming , De-Chuan Zhan , Wei-Lun Chao

Few-shot learning and parameter-efficient fine-tuning (PEFT) are crucial to overcome the challenges of data scarcity and ever growing language model sizes. This applies in particular to specialized scientific domains, where researchers…

Computation and Language · Computer Science 2025-09-18 Jonas Rieger , Mattes Ruckdeschel , Gregor Wiedemann

Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods.…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Linglan Zhao , Dashan Guo , Yunlu Xu , Liang Qiao , Zhanzhan Cheng , Shiliang Pu , Yi Niu , Xiangzhong Fang

Few-shot learning aims to learn classifiers for new classes with only a few training examples per class. Most existing few-shot learning approaches belong to either metric-based meta-learning or optimization-based meta-learning category,…

Machine Learning · Computer Science 2019-08-28 Duo Wang , Yu Cheng , Mo Yu , Xiaoxiao Guo , Tao Zhang

When training data is scarce, it is common to make use of a feature extractor that has been pre-trained on a large base dataset, either by fine-tuning its parameters on the ``target'' dataset or by directly adopting its representation as…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Raphael Lafargue , Yassir Bendou , Bastien Pasdeloup , Jean-Philippe Diguet , Ian Reid , Vincent Gripon , Jack Valmadre

Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones. In contrast to both extremes, real world recognition problems exhibit…

Computer Vision and Pattern Recognition · Computer Science 2019-07-03 Davis Wertheimer , Bharath Hariharan

Autonomous agents interacting with the real world need to learn new concepts efficiently and reliably. This requires learning in a low-data regime, which is a highly challenging problem. We address this task by introducing a fast…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Ardhendu Shekhar Tripathi , Martin Danelljan , Luc Van Gool , Radu Timofte

Few-shot learning allows machines to classify novel classes using only a few labeled samples. Recently, few-shot segmentation aiming at semantic segmentation on low sample data has also seen great interest. In this paper, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2022-02-17 Jun Seo , Young-Hyun Park , Sung Whan Yoon , Jaekyun Moon

Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in…

Computer Vision and Pattern Recognition · Computer Science 2021-08-03 Guansong Pang , Choubo Ding , Chunhua Shen , Anton van den Hengel

Recent advances in natural language processing (NLP) have led to strong text classification models for many tasks. However, still often thousands of examples are needed to train models with good quality. This makes it challenging to quickly…

Computation and Language · Computer Science 2022-05-18 Thomas Müller , Guillermo Pérez-Torró , Angelo Basile , Marc Franco-Salvador

We are interested in developing a unified machine learning model over many mobile devices for practical learning tasks, where each device only has very few training data. This is a commonly encountered situation in mobile computing…

Machine Learning · Computer Science 2021-04-02 Chenyou Fan , Jianwei Huang

Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm. In this paper we propose the trainable prototypes for distance measure instead of the artificial ones within…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Jianyi Li , Guizhong Liu

We develop a novel approach to conformal prediction when the target task has limited data available for training. Conformal prediction identifies a small set of promising output candidates in place of a single prediction, with guarantees…

Machine Learning · Computer Science 2021-07-21 Adam Fisch , Tal Schuster , Tommi Jaakkola , Regina Barzilay