Context. Electroencephalography (EEG) is a complex signal and can require several years
of training, as well as advanced signal processing and feature extraction methodologies to …

Visual target tracking is one of the most sought-after yet challenging research topics in
computer vision. Given the ill-posed nature of the problem and its popularity in a broad …

In this paper, we explore a novel knowledge-transfer task, termed as Deep Model
Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous …

When transferring a pretrained model to a downstream task, two popular methods are full
fine-tuning (updating all the model parameters) and linear probing (updating only the last …

Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of
data distributions when performing zero-shot inference (ie, without fine-tuning on a specific …

A common approach to transfer learning under distribution shift is to fine-tune the last few
layers of a pre-trained model, preserving learned features while also adapting to the new …

In this paper, we tackle the problem of few-shot class incremental learning (FSCIL). FSCIL
aims to incrementally learn new classes with only a few samples in each class. Most existing …

Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety
of benchmarks. However, recent works (Kumar et al., 2022; Wortsman et al., 2021) have …

Transfer of pre-trained representations improves sample efficiency and simplifies
hyperparameter tuning when training deep neural networks for vision. We revisit the …

Abstract Domain generalization (DG) aims to learn a generalized model to an unseen target
domain using only limited source domains. Previous attempts to DG fail to learn domain …