Related papers: A Data-Based Perspective on Transfer Learning
Evidence is mounting that Convolutional Networks (ConvNets) are the most effective representation learning method for visual recognition tasks. In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the…
It has been demonstrated that deep neural networks outperform traditional machine learning. However, deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution…
This paper examines the effectiveness of combining active learning and transfer learning for anomaly detection in cross-domain time-series data. Our results indicate that there is an interaction between clustering and active learning and in…
In this work, we study the transfer learning problem under high-dimensional generalized linear models (GLMs), which aim to improve the fit on target data by borrowing information from useful source data. Given which sources to transfer, we…
Transfer learning has become a central paradigm in modern machine learning, yet it suffers from the long-standing problem of negative transfer, where leveraging source representations can harm rather than help performance on the target…
While the majority of today's object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate. However, models trained to provide richer…
Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target). Unsupervised methods that can adapt to domain shift are highly…
The successful application of deep learning to many visual recognition tasks relies heavily on the availability of a large amount of labeled data which is usually expensive to obtain. The few-shot learning problem has attracted increasing…
Lesion segmentation of ultrasound medical images based on deep learning techniques is a widely used method for diagnosing diseases. Although there is a large amount of ultrasound image data in medical centers and other places, labeled…
In this work, we propose ModelPred, a framework that helps to understand the impact of changes in training data on a trained model. This is critical for building trust in various stages of a machine learning pipeline: from cleaning…
Transfer learning and ensembling are two popular techniques for improving the performance and robustness of neural networks. Due to the high cost of pre-training, ensembles of models fine-tuned from a single pre-trained checkpoint are often…
This paper presents a framework for deep transfer learning, which aims to leverage information from multi-domain upstream data with a large number of samples $n$ to a single-domain downstream task with a considerably smaller number of…
Transfer learning aims to transfer knowledge or information from a source domain to a relevant target domain. In this paper, we understand transfer learning from the perspectives of knowledge transferability and trustworthiness. This…
Data unlearning aims to remove the influence of specific training samples from a trained model without requiring full retraining. Unlike concept unlearning, data unlearning in diffusion models remains underexplored and often suffers from…
This paper presents a new approach of transfer learning-based medical image classification to mitigate insufficient labeled data problem in medical domain. Instead of direct transfer learning from source to small number of labeled target…
Retrosynthesis is a problem to infer reactant compounds to synthesize a given product compound through chemical reactions. Recent studies on retrosynthesis focus on proposing more sophisticated prediction models, but the dataset to feed the…
Transfer learning from huge natural image datasets, fine-tuning of deep neural networks and the use of the corresponding pre-trained networks have become de facto the core of art analysis applications. Nevertheless, the effects of transfer…
In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…
Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…
Supervised learning techniques typically assume training data originates from the target population. Yet, in reality, dataset shift frequently arises, which, if not adequately taken into account, may decrease the performance of their…