Generating instance-level prompts for rehearsal-free continual learning

D Jung, D Han, J Bang, H Song - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Abstract We introduce Domain-Adaptive Prompt (DAP), a novel method for continual
learning using Vision Transformers (ViT). Prompt-based continual learning has recently …

Semantic residual prompts for continual learning

M Menabue, E Frascaroli, M Boschini… - … on Computer Vision, 2024 - Springer
Prompt-tuning methods for Continual Learning (CL) freeze a large pre-trained model and
train a few parameter vectors termed prompts. Most of these methods organize these vectors …

CDFSL-V: Cross-domain few-shot learning for videos

S Samarasinghe, MN Rizve… - Proceedings of the …, 2023 - openaccess.thecvf.com
Few-shot video action recognition is an effective approach to recognizing new categories
with only a few labeled examples, thereby reducing the challenges associated with …

Understanding few-shot learning: Measuring task relatedness and adaptation difficulty via attributes

M Hu, H Chang, Z Guo, B Ma… - Advances in Neural …, 2024 - proceedings.neurips.cc
Few-shot learning (FSL) aims to learn novel tasks with very few labeled samples by
leveraging experience from\emph {related} training tasks. In this paper, we try to understand …

Metacoco: A new few-shot classification benchmark with spurious correlation

M Zhang, H Li, F Wu, K Kuang - ar** from Satellite Image Time Series
S Mohammadi, M Belgiu, A Stein - Remote Sensing, 2024 - mdpi.com
Recently, deep learning methods have achieved promising crop map** results. Yet, their
classification performance is constrained by the scarcity of labeled samples. Therefore, the …