Related papers: EZLearn: Exploiting Organic Supervision in Large-S…

This study investigates the use of unsupervised word embeddings and sequence features for sample representation in an active learning framework built to extract clinical concepts from clinical free text. The objective is to further reduce…

Active learning improves annotation efficiency by selecting the most informative samples for annotation and model training. While most prior work has focused on selecting informative images for classification tasks, we investigate the more…

Segmentation is essential for medical image analysis tasks such as intervention planning, therapy guidance, diagnosis, treatment decisions. Deep learning is becoming increasingly prominent for segmentation, where the lack of annotations,…

Learning an object detector or retrieval requires a large data set with manual annotations. Such data sets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose to exploit…

Conventional multimedia annotation/retrieval systems such as Normalized Continuous Relevance Model (NormCRM) [16] require a fully labeled training data for a good performance. Active Learning, by determining an order for labeling the…

Accurately annotated ultrasonic images are vital components of a high-quality medical report. Hospitals often have strict guidelines on the types of annotations that should appear on imaging results. However, manually inspecting these…

Supervised deep learning methods for segmentation require large amounts of labelled training data, without which they are prone to overfitting, not generalizing well to unseen images. In practice, obtaining a large number of annotations…

We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest…

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

Data lies at the core of modern deep learning. The impressive performance of supervised learning is built upon a base of massive accurately labeled data. However, in some real-world applications, accurate labeling might not be viable;…

Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples,…

Medical image segmentation is a fundamental and critical step in many image-guided clinical approaches. Recent success of deep learning-based segmentation methods usually relies on a large amount of labeled data, which is particularly…

Research in bioacoustics, neuroscience, and linguistics often uses birdsong as a proxy to acquire knowledge across diverse areas. This requires audio models to annotate and parse the birdsong. Developing such models requires precise,…

Pixel-wise segmentation is one of the most data and annotation hungry tasks in our field. Providing representative and accurate annotations is often mission-critical especially for challenging medical applications. In this paper, we propose…

We introduce DsDs: a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low-resource languages. The model exploits annotation projection, instance…

Prevalent supervised learning methods in natural language processing (NLP) are notoriously data-hungry, which demand large amounts of high-quality annotated data. In practice, acquiring such data is a costly endeavor. Recently, the superior…

Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support…

Scaling robot policy learning is bottlenecked by the cost of collecting demonstrations, while language annotations for existing demonstrations are comparatively cheap. We study language density as a lever for extracting more signal from a…

Machine Learning and Inference methods have become ubiquitous in our attempt to induce more abstract representations of natural language text, visual scenes, and other messy, naturally occurring data, and support decisions that depend on…

Automatic medical image segmentation plays a critical role in scientific research and medical care. Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are…