arXiv research

New method to estimate doctors' effort in annotating medical images.

The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create such large annotated datasets, as annotating medical images is not only tedious…

ECN framework improves training on noisy structured labels.

Coarse ground truth improves semantic segmentation accuracy for some classes.

Nowadays, how to effectively evaluate visual properties has become a popular topic for fine-grained visual comprehension. In this paper we study the problem of how to estimate such visual properties from a ranking perspective with the help of the annotators from online crowdsourcing platforms. The main challenges of ou…

This study evaluates zero-shot LLMs in finance, finding ChatGPT performs well but fine-tuned models are better.

SPIN converts weak LLMs to strong ones using self-play.

The rapid development of deep learning, a family of machine learning techniques, has spurred much interest in its application to medical imaging problems. Here, we develop a deep learning algorithm that can accurately detect breast cancer on screening mammograms using an "end-to-end" training approach that efficiently …

New method uses artificial data to improve biomedical text tagging.

This paper fine-tunes BERT for stock market sentiment analysis and improves trading performance.

Study shows annotation instrument design affects model performance in hate speech detection.

Paper tackles cross-granularity few-shot learning with meta-embedder.

New framework analyzes LLM personalization trade-offs under congestion.

System identifies related passages for easier text comprehension.

Improves biomedical entity linking with latent type modeling.

With the rapid growth of crowdsourcing platforms it has become easy and relatively inexpensive to collect a dataset labeled by multiple annotators in a short time. However due to the lack of control over the quality of the annotators, some abnormal annotators may be affected by position bias which can potentially degra…

Predicts fine-grained OD matrices for ridesharing platforms to optimize supply-demand balance.

New method uses image-level and pixel-level annotations for brain tumor segmentation.

D$^2$-City is a diverse traffic dataset for AI development.

Method makes non-interpretable models more intervenable.

Social media analytics allows us to extract, analyze, and establish semantic from user-generated contents in social media platforms. This study utilized a mixed method including a three-step process of data collection, topic modeling, and data annotation for recognizing exercise related patterns. Based on the findings,…

Novel unsupervised relation extraction framework using BERT.

The paper proposes incentivizing human annotators with 'golden questions' to improve data quality.

Paper tackles noisy annotations by considering workers' attention levels.

Crowdsourcing and active learning reduce manual annotation in social media event classification.

Study tackles hate speech against journalists on social media.

As a new classification platform, deep learning has recently received increasing attention from researchers and has been successfully applied to many domains. In some domains, like bioinformatics and robotics, it is very difficult to construct a large-scale well-annotated dataset due to the expense of data acquisition …

New method uses predictions to infer causal effects without labeled data.

UBM transfers bias mitigation from upstream to downstream tasks efficiently.

This work fine-tunes GPT-2 for generating patent claims.

Paper fine-tunes LLaMA-3-8B for financial NER using instruction and LoRA.

This work improves medical image segmentation with limited annotations using contrastive learning.

Efficient algorithms learn from coarse labels instead of fine grained ones.

Few-shot cell segmentation from diverse sources to target domain.

On-device CNN inference for real-time computer vision applications can result in computational demands that far exceed the energy budgets of mobile devices. This paper proposes FixyNN, a co-designed hardware accelerator platform which splits a CNN model into two parts: a set of layers that are fixed in the hardware pla…

Improved object detection for scientific document images.

Researchers analyze tagging patterns on Stack Exchange communities.

EmTract extracts emotions from financial social media text.

New methods for graph completion improve image annotation and neuroimaging.

BERT models can classify multilingual party manifestos across different dimensions.

Unified framework for semi-supervised learning reduces annotation needs.

Paper proposes PP-GCN for fine-grained social event categorization.

We address the problem of \emph{instance label stability} in multiple instance learning (MIL) classifiers. These classifiers are trained only on globally annotated images (bags), but often can provide fine-grained annotations for image pixels or patches (instances). This is interesting for computer aided diagnosis (CAD…

The paper tackles the issue of preferential attachment in targeted display advertising by developing domain-adaptation approaches.

Framework ranks sectors influenced by Indian Union Budgets.

Neural pedagogical agent updates user models in real-time for mobile education apps.

Study improves breast lesion segmentation with limited in vivo data using simulated and natural images.

Improves few-shot learning for real-world recognition with novel methods.