Related papers: Enhancing Test Time Adaptation with Few-shot Guida…
Deep neural networks (DNNs) trained on one set of medical images often experience severe performance drop on unseen test images, due to various domain discrepancy between the training images (source domain) and the test images (target…
Most of the recent few-shot learning (FSL) algorithms are based on transfer learning, where a model is pre-trained using a large amount of source data, and the pre-trained model is fine-tuned using a small amount of target data. In transfer…
This paper proposes a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation. TTA methods leverage unlabeled data at test time to adapt to…
In this paper, we tackle the new Cross-Domain Few-Shot Learning benchmark proposed by the CVPR 2020 Challenge. To this end, we build upon state-of-the-art methods in domain adaptation and few-shot learning to create a system that can be…
Test-time adaptation (TTA) has emerged as a promising paradigm to handle the domain shifts at test time for medical images from different institutions without using extra training data. However, existing TTA solutions for segmentation tasks…
Deep neural networks demonstrate strong performance under aligned training-test distributions. However, real-world test data often exhibit domain shifts. Test-Time Adaptation (TTA) addresses this challenge by adapting the model to test data…
To recognize the unseen classes with only few samples, few-shot learning (FSL) uses prior knowledge learned from the seen classes. A major challenge for FSL is that the distribution of the unseen classes is different from that of those…
Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot recognition by comparing image embeddings to text-derived class prototypes. However, under domain shift, they suffer from feature drift, class-prior mismatch, and severe…
Test-time adaptation (TTA) of Vision-Language Models (VLMs) has emerged as a technique for tackling distribution shifts during the test time. Recent research indicates that the test-time adaptation is intrinsically linked to the model's…
Few-shot unsupervised domain adaptation (FS-UDA) leverages a limited amount of labeled data from a source domain to enable accurate classification in an unlabeled target domain. Despite recent advancements, current approaches of FS-UDA…
Few-shot learning aims to generalize to novel classes with only a few samples with class labels. Research in few-shot learning has borrowed techniques from transfer learning, metric learning, meta-learning, and Bayesian methods. These…
Effectively classifying remote sensing scenes is still a challenge due to the increasing spatial resolution of remote imaging and large variances between remote sensing images. Existing research has greatly improved the performance of…
Cross-domain few-shot learning (CD-FSL) has drawn increasing attention for handling large differences between the source and target domains--an important concern in real-world scenarios. To overcome these large differences, recent works…
Node classification is of great importance among various graph mining tasks. In practice, real-world graphs generally follow the long-tail distribution, where a large number of classes only consist of limited labeled nodes. Although Graph…
Test-time adaptation (TTA) has increasingly been an important topic to efficiently tackle the cross-domain distribution shift at test time for medical images from different institutions. Previous TTA methods have a common limitation of…
Domain adaptation is essential for activity recognition to ensure accurate and robust performance across diverse environments, sensor types, and data sources. Unsupervised domain adaptation methods have been extensively studied, yet, they…
Solving the domain shift problem during inference is essential in medical imaging, as most deep-learning based solutions suffer from it. In practice, domain shifts are tackled by performing Unsupervised Domain Adaptation (UDA), where a…
Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference. Despite notable advances, several challenges still limit its broader applicability. First, most…
Deep Learning-based end-to-end Automatic Speech Recognition (ASR) has made significant strides but still struggles with performance on out-of-domain samples due to domain shifts in real-world scenarios. Test-Time Adaptation (TTA) methods…
Test-Time Adaptation (TTA) adjusts models using unlabeled test data to handle dynamic distribution shifts. However, existing methods rely on frequent adaptation and high computational cost, making them unsuitable for resource-constrained…