Self-Supervision & Meta-Learning for One-Shot Unsupervised Cross-Domain Detection

2021-06-07 · F. Cappio Borlino, S. Polizzotto, B. Caputo, T. Tommasi

Deep detection approaches are powerful in controlled conditions, but appear brittle and fail when source models are used off-the-shelf on unseen domains. Most of the existing works on domain adaptation simplify the setting and access jointly both a large source dataset and a sizable amount of target samples. However this scenario is unrealistic in many practical cases as when monitoring image feeds from social media: only a pretrained source model is available and every target image uploaded by the users belongs to a different domain not foreseen during training. We address this challenging setting by presenting an object detection algorithm able to exploit a pre-trained source model and perform unsupervised adaptation by using only one target sample seen at test time. Our multi-task architecture includes a self-supervised branch that we exploit to meta-train the whole model with single-sample cross-domain episodes, and prepare to the test condition. At deployment time the self-supervised task is iteratively solved on any incoming sample to one-shot adapt on it. We introduce a new dataset of social media image feeds and present a thorough benchmark with the most recent cross-domain detection methods showing the advantages of our approach.

📄 PDF Abstract BibTeX arXiv:2106.03496

Code (1)

francescocappio/oshot-meta-learning 공식 구현 pytorch

Tasks

Domain Adaptation Meta-Learning object-detection Object Detection

Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning

2023-03-02 · 6th Workshop on Meta-Learning at NeurIPS 2022 2022 11 · Huiwon Jang, Hankook Lee, Jinwoo Shin

Unsupervised meta-learning aims to learn generalizable knowledge across a distribution of tasks constructed from unlabeled data. Here, the main challenge is how to construct diverse tasks for meta-learning without label …

Contrastive Learning Cross-Domain Few-Shot Meta-Learning Self-Supervised Learning

Few-Shot Image Classification via Contrastive Self-Supervised Learning

2020-08-23 · Jianyi Li, Guizhong Liu

Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. I…

Classification Few-Shot Image Classification Few-Shot Learning General Classification+5

Few-Shot Unsupervised Continual Learning through Meta-Examples

2020-09-17 · Alessia Bertugli, Stefano Vincenzi, Simone Calderara, Andrea Passerini

In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream. Hence many existing deep learning solutions suf…

Clustering Continual Learning Few-Shot Learning Meta-Learning

MSDA: Combining Pseudo-labeling and Self-Supervision for Unsupervised Domain Adaptation in ASR

2025-05-30 · Dimitrios Damianos, Georgios Paraskevopoulos, Alexandros Potamianos

In this work, we investigate the Meta PL unsupervised domain adaptation framework for Automatic Speech Recognition (ASR). We introduce a Multi-Stage Domain Adaptation pipeline (MSDA), a sample-efficient, two-stage adapta…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Domain Adaptation Self-Supervised Learning+3

MetaGAN: An Adversarial Approach to Few-Shot Learning

2018-12-01 · NeurIPS 2018 12 · Ruixiang Zhang, Tong Che, Zoubin Ghahramani, Yoshua Bengio 외

In this paper, we propose a conceptually simple and general framework called MetaGAN for few-shot learning problems. Most state-of-the-art few-shot classification models can be integrated with MetaGAN in a principled and…

Classification Few-Shot Image Classification Few-Shot Learning General Classification+2