English
Related papers

Related papers: Strong Baselines for Parameter Efficient Few-Shot …

200 papers

The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research…

Computer Vision and Pattern Recognition · Computer Science 2018-04-26 Spyros Gidaris , Nikos Komodakis

The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ neural networks to learn a feature similarity comparison…

Computer Vision and Pattern Recognition · Computer Science 2020-04-17 Xiaomeng Li , Lequan Yu , Chi-Wing Fu , Meng Fang , Pheng-Ann Heng

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

Pre-trained language models (PLMs) have ignited a surge in demand for effective fine-tuning techniques, particularly in low-resource domains and languages. Active learning (AL), a set of algorithms designed to decrease labeling costs by…

Computation and Language · Computer Science 2023-10-24 Josip Jukić , Jan Šnajder

Previous research has shown that the principal singular vectors of a pre-trained model's weight matrices capture critical knowledge. In contrast, those associated with small singular values may contain noise or less reliable information. As…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-10 Zhe Li , Man-wai Mak , Mert Pilanci , Hung-yi Lee , Helen Meng

Fine-tuning large language models (LLMs) on downstream tasks requires substantial computational resources. Selective PEFT, a class of parameter-efficient fine-tuning (PEFT) methodologies, aims to mitigate these computational challenges by…

Computation and Language · Computer Science 2025-06-24 Aradhye Agarwal , Suhas K Ramesh , Ayan Sengupta , Tanmoy Chakraborty

Recent progress on few-shot learning largely relies on annotated data for meta-learning: base classes sampled from the same domain as the novel classes. However, in many applications, collecting data for meta-learning is infeasible or…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Yunhui Guo , Noel C. Codella , Leonid Karlinsky , James V. Codella , John R. Smith , Kate Saenko , Tajana Rosing , Rogerio Feris

The performance of meta-learning approaches for few-shot learning generally depends on three aspects: features suitable for comparison, the classifier ( base learner ) suitable for low-data scenarios, and valuable information from the…

Machine Learning · Computer Science 2020-09-15 Haoqing Wang , Zhi-Hong Deng

Generalized Few-shot Semantic Segmentation (GFSS) aims to segment each image pixel into either base classes with abundant training examples or novel classes with only a handful of (e.g., 1-5) training images per class. Compared to the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-28 Zhihe Lu , Sen He , Da Li , Yi-Zhe Song , Tao Xiang

Food images present unique challenges for few-shot learning models due to their visual complexity and variability. For instance, a pasta dish might appear with various garnishes on different plates and in diverse lighting conditions and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Javier Rodenas , Eduardo Aguilar , Petia Radeva

The few-shot learning ability of vision transformers (ViTs) is rarely investigated though heavily desired. In this work, we empirically find that with the same few-shot learning frameworks, \eg~Meta-Baseline, replacing the widely used CNN…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Bowen Dong , Pan Zhou , Shuicheng Yan , Wangmeng Zuo

Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection…

Computer Vision and Pattern Recognition · Computer Science 2024-02-15 Jie Mei , Mingyuan Jiu , Hichem Sahbi , Xiaoheng Jiang , Mingliang Xu

Driven by the rapid growth of model parameters, parameter-efficient fine-tuning (PEFT) has become essential for adapting large models to diverse downstream tasks under constrained computational resources. Within this paradigm, orthogonal…

Machine Learning · Computer Science 2026-02-20 Fei Wu , Jia Hu , Geyong Min , Shiqiang Wang

Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper,…

Machine Learning · Computer Science 2023-06-02 Xu Luo , Hao Wu , Ji Zhang , Lianli Gao , Jing Xu , Jingkuan Song

This article focuses on large language models (LLMs) fine-tuning in the scarce data regime (also known as the "few-shot" learning setting). We propose a method to increase the generalization capabilities of LLMs based on neural network…

Machine Learning · Computer Science 2023-10-25 Louis Falissard , Vincent Guigue , Laure Soulier

Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. A recent research direction for improving few-shot classifiers involves augmenting the labelled samples with synthetic…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Victor G. Turrisi da Costa , Nicola Dall'Asen , Yiming Wang , Nicu Sebe , Elisa Ricci

Existing few-shot segmentation (FSS) methods mainly focus on designing novel support-query matching and self-matching mechanisms to exploit implicit knowledge in pre-trained backbones. However, the performance of these methods is often…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Shijie Chang , Lihe Zhang , Huchuan Lu

Adapting pretrained language models to novel domains, such as clinical applications, traditionally involves retraining their entire set of parameters. Parameter-Efficient Fine-Tuning (PEFT) techniques for fine-tuning language models…

Computation and Language · Computer Science 2024-06-11 Aryo Pradipta Gema , Pasquale Minervini , Luke Daines , Tom Hope , Beatrice Alex

Parameter-efficient fine-tuning (PEFT) aims to adapt pre-trained vision models to downstream tasks. Among PEFT paradigms, sparse tuning achieves remarkable performance by adjusting only the weights most relevant to downstream tasks, rather…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Shufan Shen , Junshu Sun , Shuhui Wang , Qingming Huang

Learning to recognize novel visual categories from a few examples is a challenging task for machines in real-world industrial applications. In contrast, humans have the ability to discriminate even similar objects with little supervision.…

Computer Vision and Pattern Recognition · Computer Science 2020-06-02 Xin Sun , Hongwei Xv , Junyu Dong , Qiong Li , Changrui Chen