Related papers: Transferability-Guided Cross-Domain Cross-Task Tra…

On edge devices, data scarcity occurs as a common problem where transfer learning serves as a widely-suggested remedy. Nevertheless, transfer learning imposes a heavy computation burden to resource-constrained edge devices. Existing task…

Identifying beneficial tasks to transfer from is a critical step toward successful intermediate-task transfer learning. In this work, we experiment with 130 source-target task combinations and demonstrate that the transfer performance…

Transfer Learning (TL) offers the potential to accelerate learning by transferring knowledge across tasks. However, it faces critical challenges such as negative transfer, domain adaptation and inefficiency in selecting solid source…

Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naive formulations often degrade performance and in particular, identifying the tasks that would benefit from…

The design of new strategies that exploit methods from Machine Learning to facilitate the resolution of challenging and large-scale mathematical optimization problems has recently become an avenue of prolific and promising research. In this…

Few-Shot classification aims at solving problems that only a few samples are available in the training process. Due to the lack of samples, researchers generally employ a set of training tasks from other domains to assist the target task,…

Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address this by providing efficient proxy metrics to rank models…

Optimal Transport (OT) offers a powerful framework for finding correspondences between distributions and addressing matching and alignment problems in various areas of computer vision, including shape analysis, image generation, and…

Transfer learning has recently attracted significant research attention, as it simultaneously learns from different source domains, which have plenty of labeled data, and transfers the relevant knowledge to the target domain with limited…

Maximum Causal Entropy (MCE) Inverse Optimal Control (IOC) has become an effective tool for modelling human behaviour in many control tasks. Its advantage over classic techniques for estimating human policies is the transferability of the…

Current transferability estimation methods designed for natural image datasets are often suboptimal in medical image classification. These methods primarily focus on estimating the suitability of pre-trained source model features for a…

Recent advances in NLP demonstrate the effectiveness of training large-scale language models and transferring them to downstream tasks. Can fine-tuning these models on tasks other than language modeling further improve performance? In this…

Kernelized Correlation Filter (KCF) is one of the state-of-the-art object trackers. However, it does not reasonably model the distribution of correlation response during tracking process, which might cause the drifting problem, especially…

When a source-trained model $Q$ is replaced by a model $\tilde{Q}$ trained on shifted data, its performance on the source domain can change unpredictably. To address this, we study the two-model risk change, $\Delta R := R_P(\tilde{Q}) -…

Multi-source transfer learning has been proven effective when within-target labeled data is scarce. Previous work focuses primarily on exploiting domain similarities and assumes that source domains are richly or at least comparably labeled.…

In low-resource settings, model transfer can help to overcome a lack of labeled data for many tasks and domains. However, predicting useful transfer sources is a challenging problem, as even the most similar sources might lead to unexpected…

This paper addresses the practical challenge in Entropic Optimal Transport (EOT) where the underlying ground cost function is typically latent and unobserved. Rather than assuming a fixed geometric cost, we adopt a data-driven approach…

We study a fundamental transfer learning process from source to target linear regression tasks, including overparameterized settings where there are more learned parameters than data samples. The target task learning is addressed by using…

Transfer learning has become a popular method for leveraging pre-trained models in computer vision. However, without performing computationally expensive fine-tuning, it is difficult to quantify which pre-trained source models are suitable…

Transfer learning has been demonstrated to be successful and essential in diverse applications, which transfers knowledge from related but different source domains to the target domain. Online transfer learning(OTL) is a more challenging…