Related papers: STENCIL: Submodular Mutual Information Based Weak …
Model-Agnostic Meta-Learning (MAML) is one of the most successful meta-learning techniques for few-shot learning. It uses gradient descent to learn commonalities between various tasks, enabling the model to learn the meta-initialization of…
State-of-the-art audio event detection (AED) systems rely on supervised learning using strongly labeled data. However, this dependence severely limits scalability to large-scale datasets where fine resolution annotations are too expensive…
Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality,…
For machine learning models trained with limited labeled training data, validation stands to become the main bottleneck to reducing overall annotation costs. We propose a statistical validation algorithm that accurately estimates the…
Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either rely on model uncertainty to select the most uncertain…
The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e.g.…
Universal models for medical image segmentation, such as interactive and in-context learning (ICL) models, offer strong generalization but require extensive annotations. Interactive models need repeated user prompts for each image, while…
Federated active learning (FAL) seeks to reduce annotation cost under privacy constraints, yet its effectiveness degrades in realistic settings with severe global class imbalance and highly heterogeneous clients. We conduct a systematic…
Few-shot classification (FSC) requires training models using a few (typically one to five) data points per class. Meta learning has proven to be able to learn a parametrized model for FSC by training on various other classification tasks.…
Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label. A basic promise of…
Few-shot class-incremental learning (FSCIL) aims to incrementally learn models from a small amount of novel data, which requires strong representation and adaptation ability of models learned under few-example supervision to avoid…
Active learning (AL) reduces labeling cost by querying informative samples, but in tabular settings its cold-start gains are often limited because uncertainty estimates are unreliable when models are trained on very few labels. Tabular…
Fine-grained annotations---e.g. dense image labels, image segmentation and text tagging---are useful in many ML applications but they are labor-intensive to generate. Moreover there are often systematic, structured errors in these…
In many review classification applications, a fine-grained analysis of the reviews is desirable, because different segments (e.g., sentences) of a review may focus on different aspects of the entity in question. However, training supervised…
In-context learning (ICL) enables large language models to perform few-shot learning by conditioning on labeled examples in the prompt. Despite its flexibility, ICL suffers from instability -- especially as prompt length increases with more…
Evaluating clustering quality with reliable evaluation metrics like normalized mutual information (NMI) requires labeled data that can be expensive to annotate. We focus on the underexplored problem of estimating clustering quality with…
Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…
Existing prompt learning for VLMs exhibits a modality asymmetry, predominantly optimizing text tokens while still relying on frozen visual encoder as holistic extractor and neglecting the spectral granularity essential for fine-grained…
For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…
Deep neural networks are powerful, massively parameterized machine learning models that have been shown to perform well in supervised learning tasks. However, very large amounts of labeled data are usually needed to train deep neural…