CDFSL-V: Cross-Domain Few-Shot Learning for Videos

by   Sarinda Samarasinghe, et al.

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 collecting and annotating large-scale video datasets. Existing methods in video action recognition rely on large labeled datasets from the same domain. However, this setup is not realistic as novel categories may come from different data domains that may have different spatial and temporal characteristics. This dissimilarity between the source and target domains can pose a significant challenge, rendering traditional few-shot action recognition techniques ineffective. To address this issue, in this work, we propose a novel cross-domain few-shot video action recognition method that leverages self-supervised learning and curriculum learning to balance the information from the source and target domains. To be particular, our method employs a masked autoencoder-based self-supervised training objective to learn from both source and target data in a self-supervised manner. Then a progressive curriculum balances learning the discriminative information from the source dataset with the generic information learned from the target domain. Initially, our curriculum utilizes supervised learning to learn class discriminative features from the source data. As the training progresses, we transition to learning target-domain-specific features. We propose a progressive curriculum to encourage the emergence of rich features in the target domain based on class discriminative supervised features in the source domain. with this transition. We evaluate our method on several challenging benchmark datasets and demonstrate that our approach outperforms existing cross-domain few-shot learning techniques. Our code is available at


page 2

page 6


Understanding Cross-Domain Few-Shot Learning: An Experimental Study

Cross-domain few-shot learning has drawn increasing attention for handli...

Cross-domain few-shot learning with unlabelled data

Few shot learning aims to solve the data scarcity problem. If there is a...

How Well Do Self-Supervised Methods Perform in Cross-Domain Few-Shot Learning?

Cross-domain few-shot learning (CDFSL) remains a largely unsolved proble...

DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition

Domain alignment in convolutional networks aims to learn the degree of l...

Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition

In this work, we consider the problem of cross-domain 3D action recognit...

Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning

Previous few-shot learning (FSL) works mostly are limited to natural ima...

Domain-Specific Priors and Meta Learning for Low-shot First-Person Action Recognition

The lack of large-scale real datasets with annotationsmakes transfer lea...

Please sign up or login with your details

Forgot password? Click here to reset