The ability of artificial agents to increment their capabilities when confronted with new data is
an open challenge in artificial intelligence. The main challenge faced in such cases is …

We present ControlNet, a neural network architecture to add spatial conditioning controls to
large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large …

Large deep learning models are impressive, but they struggle when real-time data is not
available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for …

This work investigates a simple yet powerful adapter for Vision Transformer (ViT). Unlike
recent visual transformers that introduce vision-specific inductive biases into their …

Fine-tuning large pretrained models is an effective transfer mechanism in NLP. However, in
the presence of many downstream tasks, fine-tuning is parameter inefficient: an entire new …

Artificial neural networks thrive in solving the classification problem for a particular rigid task,
acquiring knowledge through generalized learning behaviour from a distinct training phase …

For future learning systems, incremental learning is desirable because it allows for: efficient
resource usage by eliminating the need to retrain from scratch at the arrival of new data; …

We propose a novel multi-task learning architecture, which allows learning of task-specific
feature-level attention. Our design, the Multi-Task Attention Network (MTAN), consists of a …

There is a growing interest in learning data representations that work well for many different
types of problems and data. In this paper, we look in particular at the task of learning a single …

This work presents a method for adapting a single, fixed deep neural network to multiple
tasks without affecting performance on already learned tasks. By building upon ideas from …