We demonstrate that there is significant redundancy in the parameterization of several deep
learning models. Given only a few weight values for each feature it is possible to accurately …

In domains such as health care and finance, shortage of labeled data and computational
resources is a critical issue while develo** machine learning algorithms. To address the …

Animal biometrics is an emerging field that develops quantified approaches for representing
and detecting the phenotypic appearance of species, individuals, behaviors, and …

Scaling up deep learning algorithms has been shown to lead to increased performance in
benchmark tasks and to enable discovery of complex high-level features. Recent efforts to …

Deep learning research aims at discovering learning algorithms that discover multiple levels
of distributed representations, with higher levels representing more abstract concepts …

Despite their ability to memorize large datasets, deep neural networks often achieve good
generalization performance. However, the differences between the learned solutions of …

Visual animal biometrics is an emerging research discipline in computer vision, pattern
recognition and cognitive science. It is a promising research field that encourages new …

In this paper, we propose an approach to learn hierarchical features for visual object
tracking. First, we offline learn features robust to diverse motion patterns from auxiliary video …

Transformer-based pre-trained language models have demonstrated superior performance
on various natural language processing tasks. However, it remains unclear how the skills …

I present my work towards learning a better computer vision system that learns and
generalizes object categories better, and behaves in ways closer to what human behave …