相关论文: LEEP: A New Measure to Evaluate Transferability of…

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…

Transfer learning has become the de facto standard in computer vision and natural language processing, especially where labeled data is scarce. Accuracy can be significantly improved by using pre-trained models and subsequent fine-tuning.…

Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a…

Modern federated networks, such as those comprised of wearable devices, mobile phones, or autonomous vehicles, generate massive amounts of data each day. This wealth of data can help to learn models that can improve the user experience on…

In this article we present a methodology to estimate the Transfer Entropy Rate between two systems through the Lempel-Ziv complexity. This methodology carries a set of practical advantages: it can be estimated from two single discrete…

Contrastive vision-language models like CLIP have shown great progress in transfer learning. In the inference stage, the proper text description, also known as prompt, needs to be carefully designed to correctly classify the given images.…

Learning efficient representations for decision-making policies is a challenge in imitation learning (IL). Current IL methods require expert demonstrations, which are expensive to collect. Additionally, they are not explicitly trained to…

Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time…

While transferring a pretrained language model, common approaches conventionally attach their task-specific classifiers to the top layer and adapt all the pretrained layers. We investigate whether one could make a task-specific selection on…

Task embeddings are low-dimensional representations that are trained to capture task properties. In this paper, we propose MetaEval, a collection of $101$ NLP tasks. We fit a single transformer to all MetaEval tasks jointly while…

Referring Expression Comprehension (REC), which aims to ground a local visual region via natural language, is a task that heavily relies on multimodal alignment. Most existing methods utilize powerful pre-trained models to transfer…

Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a…

The use of deep learning techniques for automatic facial expression recognition has recently attracted great interest but developed models are still unable to generalize well due to the lack of large emotion datasets for deep learning. To…

This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic Inference for Prediction. ML-PIP extends existing…

This paper presents an automatic network adaptation method that finds a ConvNet structure well-suited to a given target task, e.g., image classification, for efficiency as well as accuracy in transfer learning. We call the concept…

Layer-aligned distillation and convergence-based early exit represent two predominant computational efficiency paradigms for transformer inference; yet we establish that they exhibit systematic incompatibility under standard deployment…

Existing work on understanding deep learning often employs measures that compress all data-dependent information into a few numbers. In this work, we adopt a perspective based on the role of individual examples. We introduce a measure of…

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…

Representation learning is a key technique in modern machine learning that enables models to identify meaningful patterns in complex data. However, different methods tend to extract distinct aspects of the data, and relying on a single…

Current methods in training and benchmarking vision models exhibit an over-reliance on passive, curated datasets. Although models trained on these datasets have shown strong performance in a wide variety of tasks such as classification,…