Related papers: Active Few-Shot Learning with FASL
Human learning benefits from multi-modal inputs that often appear as rich semantics (e.g., description of an object's attributes while learning about it). This enables us to learn generalizable concepts from very limited visual examples.…
Text classification is a well-studied and versatile building block for many NLP applications. Yet, existing approaches require either large annotated corpora to train a model with or, when using large language models as a base, require…
Classification algorithms to mine data stream have been extensively studied in recent years. However, a lot of these algorithms are designed for supervised learning which requires labeled instances. Nevertheless, the labeling of the data is…
Medical image analysis faces two critical challenges: scarcity of labeled data and lack of model interpretability, both hindering clinical AI deployment. Few-shot learning (FSL) addresses data limitations but lacks transparency in…
Deep convolutional neural networks generally perform well in underwater object recognition tasks on both optical and sonar images. Many such methods require hundreds, if not thousands, of images per class to generalize well to unseen…
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…
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…
While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing…
Few-Shot Learning (FSL) is a challenging task, which aims to recognize novel classes with few examples. Recently, lots of methods have been proposed from the perspective of meta-learning and representation learning. However, few works focus…
Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled…
Object recognition in the real-world requires handling long-tailed or even open-ended data. An ideal visual system needs to recognize the populated head visual concepts reliably and meanwhile efficiently learn about emerging new tail…
Prompt-based approaches are strong at few-shot learning. However, Perez et al. (2021) have recently cast doubt on their performance because they had difficulty getting good results in a "true" few-shot setting in which prompts and…
Most existing studies on few-shot learning focus on unimodal settings, where models are trained to generalize to unseen data using a limited amount of labeled examples from a single modality. However, real-world data are inherently…
The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a…
Meta-learning (ML) has emerged as a promising learning method under resource constraints such as few-shot learning. ML approaches typically propose a methodology to learn generalizable models. In this work-in-progress paper, we put the…
Vision-language models (VLMs) have demonstrated remarkable zero-shot performance across various classification tasks. Nonetheless, their reliance on hand-crafted text prompts for each task hinders efficient adaptation to new tasks. While…
A particularly successful class of approaches for few-shot learning combines language models with prompts -- hand-crafted task descriptions that complement data samples. However, designing prompts by hand for each task commonly requires…
Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a novel active learning approach that utilizes self-supervised…
Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor. However, this mixing…
Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks. In-Context Learning (ICL) typically achieves better accuracy than the 0-shot setting, but it pays in terms of…