Related papers: Prototypical Calibration for Few-shot Learning of …

We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low inter-task variance, we consider a more realistic setting,…

Feature quality is paramount for classification performance, particularly in few-shot scenarios. Contrastive learning, a widely adopted technique for enhancing feature quality, leverages sample relations to extract intrinsic features that…

Being cautious is crucial for enhancing the trustworthiness of machine learning systems integrated into decision-making pipelines. Although calibrated probabilities help in optimal decision-making, perfect calibration remains unattainable,…

Few-shot image classification has recently witnessed the rise of representation learning being utilised for models to adapt to new classes using only a few training examples. Therefore, the properties of the representations, such as their…

Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori. This is not ideal because in a realworld zero-shot…

Few-shot classification is a challenging task which aims to formulate the ability of humans to learn concepts from limited prior data and has drawn considerable attention in machine learning. Recent progress in few-shot classification has…

Transductive Few-Shot learning has gained increased attention nowadays considering the cost of data annotations along with the increased accuracy provided by unlabelled samples in the domain of few shot. Especially in Few-Shot…

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…

Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts. Yet, PLMs are unfamiliar with prompt-style expressions during pre-training, which…

Few-shot 3D semantic segmentation aims to generate accurate semantic masks for query point clouds with only a few annotated support examples. Existing prototype-based methods typically construct compact and deterministic prototypes from the…

For downstream applications of vision-language pre-trained models, there has been significant interest in constructing effective prompts. Existing works on prompt engineering, which either require laborious manual designs or optimize the…

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…

Transductive few-shot learning algorithms have showed substantially superior performance over their inductive counterparts by leveraging the unlabeled queries. However, the vast majority of such methods are evaluated on perfectly…

Low-shot image classification is a fundamental task in computer vision, and the emergence of large-scale vision-language models such as CLIP has greatly advanced the forefront of research in this field. However, most existing CLIP-based…

In this paper, we move towards combining large parametric models with non-parametric prototypical networks. We propose prototypical fine-tuning, a novel prototypical framework for fine-tuning pretrained language models (LM), which…

Vision-language models (VLMs) like CLIP are trained with the objective of aligning text and image pairs. To improve CLIP-based few-shot image classification, recent works have observed that, along with text embeddings, image embeddings from…

The goal in label-imbalanced and group-sensitive classification is to optimize relevant metrics such as balanced error and equal opportunity. Classical methods, such as weighted cross-entropy, fail when training deep nets to the terminal…

Class prototype construction and matching are core aspects of few-shot action recognition. Previous methods mainly focus on designing spatiotemporal relation modeling modules or complex temporal alignment algorithms. Despite the promising…

Most supervised machine learning tasks are subject to irreducible prediction errors. Probabilistic predictive models address this limitation by providing probability distributions that represent a belief over plausible targets, rather than…

Relation classification (RC) task is one of fundamental tasks of information extraction, aiming to detect the relation information between entity pairs in unstructured natural language text and generate structured data in the form of…