Related papers: Simulation-Based Pretraining and Domain Adaptation…
We propose a task-agnostic framework for multimodal fusion of time series and single timestamp images, enabling cross-modal generation and robust downstream performance. Our approach explores deterministic and learned strategies for time…
While neural networks have shown impressive performance on large datasets, applying these models to tasks where little data is available remains a challenging problem. In this paper we propose to use feature transfer in a zero-shot…
In this paper, we look at cross-domain few-shot classification which presents the challenging task of learning new classes in previously unseen domains with few labelled examples. Existing methods, though somewhat effective, encounter…
Autonomous driving relies on a huge volume of real-world data to be labeled to high precision. Alternative solutions seek to exploit driving simulators that can generate large amounts of labeled data with a plethora of content variations.…
Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…
A sufficient amount of annotated data is usually required to fine-tune pre-trained language models for downstream tasks. Unfortunately, attaining labeled data can be costly, especially for multiple language varieties and dialects. We…
Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data. To address this issue, Test Time Adaptation (TTA) methods have been proposed to adapt…
Time series analysis is a fundamental data mining task that supervised training methods based on empirical risk minimization have proven their effectiveness on specific tasks and datasets. However, the acquisition of well-annotated data is…
Few-shot learning is often motivated by the ability of humans to learn new tasks from few examples. However, standard few-shot classification benchmarks assume that the representation is learned on a limited amount of base class data,…
Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…
Few-shot learners aim to recognize new categories given only a small number of training samples. The core challenge is to avoid overfitting to the limited data while ensuring good generalization to novel classes. Existing literature makes…
Large photometric surveys will image billions of galaxies, but we currently lack quick, reliable automated ways to infer their physical properties like morphology, stellar mass, and star formation rates. Simulations provide galaxy images…
In computer vision applications, such as domain adaptation (DA), few shot learning (FSL) and zero-shot learning (ZSL), we encounter new objects and environments, for which insufficient examples exist to allow for training "models from…
A basic assumption of statistical learning theory is that train and test data are drawn from the same underlying distribution. Unfortunately, this assumption doesn't hold in many applications. Instead, ample labeled data might exist in a…
Existing deep learning methods for remote sensing image fusion often suffer from poor generalization when applied to unseen datasets due to the limited availability of real training data and the domain gap between different satellite…
Few-shot segmentation (FSS) expects models trained on base classes to work on novel classes with the help of a few support images. However, when there exists a domain gap between the base and novel classes, the state-of-the-art FSS methods…
Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing. However, in practice domain shift often exists, where real-world factors such as lighting and sensor type change between…
Domain Generalization aims to develop models that can generalize to novel and unseen data distributions. In this work, we study how model architectures and pre-training objectives impact feature richness and propose a method to effectively…
The need to address the scarcity of task-specific annotated data has resulted in concerted efforts in recent years for specific settings such as zero-shot learning (ZSL) and domain generalization (DG), to separately address the issues of…
The exponential growth of astronomical data from large-scale surveys has created both opportunities and challenges for the astrophysics community. This paper explores the possibilities offered by transfer learning techniques in addressing…