相关论文: ETran: Energy-Based Transferability Estimation

With the increasing abundance of pretrained models in recent years, the problem of selecting the best pretrained checkpoint for a particular downstream classification task has been gaining increased attention. Although several methods have…

Large-scale pre-training followed by downstream fine-tuning is an effective solution for transferring deep-learning-based models. Since finetuning all possible pre-trained models is computational costly, we aim to predict the…

Transfer learning has become crucial in computer vision tasks due to the vast availability of pre-trained deep learning models. However, selecting the optimal pre-trained model from a diverse pool for a specific downstream task remains a…

Text ranking has witnessed significant advancements, attributed to the utilization of dual-encoder enhanced by Pre-trained Language Models (PLMs). Given the proliferation of available PLMs, selecting the most effective one for a given…

Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages…

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…

Transferability estimation has been an essential tool in selecting a pre-trained model and the layers in it for transfer learning, to transfer, so as to maximize the performance on a target task and prevent negative transfer. Existing…

Estimating the transferability of publicly available pretrained models to a target task has assumed an important place for transfer learning tasks in recent years. Existing efforts propose metrics that allow a user to choose one model from…

As transfer learning techniques are increasingly used to transfer knowledge from the source model to the target task, it becomes important to quantify which source models are suitable for a given target task without performing…

We consider transferability estimation, the problem of estimating how well deep learning models transfer from a source to a target task. We focus on regression tasks, which received little previous attention, and propose two simple and…

Transferability estimation is a fundamental problem in transfer learning to predict how good the performance is when transferring a source model (or source task) to a target task. With the guidance of transferability score, we can…

Transfer learning across heterogeneous data distributions (a.k.a. domains) and distinct tasks is a more general and challenging problem than conventional transfer learning, where either domains or tasks are assumed to be the same. While…

Most existing approaches to training object detectors rely on fully supervised learning, which requires the tedious manual annotation of object location in a training set. Recently there has been an increasing interest in developing weakly…

Transfer learning methods endeavor to leverage relevant knowledge from existing source pre-trained models or datasets to solve downstream target tasks. With the increase in the scale and quantity of available pre-trained models nowadays, it…

Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific…

Quantifying prediction uncertainty when applying object detection models to new, unlabeled datasets is critical in applied machine learning. This study introduces an approach to estimate the performance of deep learning-based object…

Data association is a crucial component for any multiple object tracking (MOT) method that follows the tracking-by-detection paradigm. To generate complete trajectories such methods employ a data association process to establish assignments…

Deep learning based object detectors are commonly deployed on mobile devices to solve a variety of tasks. For maximum accuracy, each detector is usually trained to solve one single specific task, and comes with a completely independent set…

Transfer learning is a widely used method to build high performing computer vision models. In this paper, we study the efficacy of transfer learning by examining how the choice of data impacts performance. We find that more pre-training…

Given a set of pre-trained models, how can we quickly and accurately find the most useful pre-trained model for a downstream task? Transferability measurement is to quantify how transferable is a pre-trained model learned on a source task…