The ability to learn new concepts continually is necessary in this ever-changing world.
However, deep neural networks suffer from catastrophic forgetting when learning new …

The heavy reliance on data is one of the major reasons that currently limit the development
of deep learning. Data quality directly dominates the effect of deep learning models, and the …

Question answering (QA) models are well-known to exploit data bias, eg, the language prior
in visual QA and the position bias in reading comprehension. Recent debiasing methods …

Long-tailed image recognition presents massive challenges to deep learning systems since
the imbalance between majority (head) classes and minority (tail) classes severely skews …

Abstract Knowledge distillation is a popular technique that has been shown to produce
remarkable gains in average accuracy. However, recent work has shown that these gains …

This paper presents a novel few-shot proxy modeling approach for the oil and gas industry
to reduce reliance on numerical simulators for reservoir analysis. The strategy introduces a …

Abstract Class-Incremental Learning (CIL) trains a model to continually recognize new
classes from non-stationary data while retaining learned knowledge. A major challenge of …

Nearly all existing scene graph generation (SGG) models have overlooked the ground-truth
annotation qualities of mainstream SGG datasets, ie, they assume: 1) all the manually …

Bronchoscopy plays a crucial role in diagnosing and treating lung diseases. The deep
learning-based diagnostic system for bronchoscopic images can assist physicians in …

Representational transfer from publicly available models is a promising technique for
improving medical image classification, especially in long-tailed datasets with rare diseases …