Related papers: From fat droplets to floating forests: cross-domai…

Multi-task learning for dense prediction is limited by the need for extensive annotation for every task, though recent works have explored training with partial task labels. Leveraging the generalization power of diffusion models, we extend…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

Many medical datasets have recently been created for medical image segmentation tasks, and it is natural to question whether we can use them to sequentially train a single model that (1) performs better on all these datasets, and (2)…

Continual learning (CL) has been a critical topic in contemporary deep neural network applications, where higher levels of both forward and backward transfer are desirable for an effective CL performance. Existing CL strategies primarily…

The pre-training paradigm fine-tunes the models trained on large-scale datasets to downstream tasks with enhanced performance. It transfers all knowledge to downstream tasks without discriminating which part is necessary or unnecessary,…

In this paper, we propose a transfer learning (TL)-enabled edge-CNN framework for 5G industrial edge networks with privacy-preserving characteristic. In particular, the edge server can use the existing image dataset to train the CNN in…

There is substantial interest in developing artificial intelligence systems to support radiologists across tasks ranging from segmentation to report generation. Existing computed tomography (CT) foundation models have largely focused on…

Crop mapping involves identifying and classifying crop types using spatial data, primarily derived from remote sensing imagery. This study presents the first comprehensive review of large-scale, pixel-wise crop mapping workflows,…

Practical learning-based autonomous driving models must be capable of generalizing learned behaviors from simulated to real domains, and from training data to unseen domains with unusual image properties. In this paper, we investigate…

The shapes of functions provide highly interpretable summaries of their trajectories. This article develops a novel transfer learning methodology to tackle the challenge of data scarcity in functional linear models. The methodology…

We consider Heterogeneous Transfer Learning (HTL) from a source to a new target domain for high-dimensional regression with differing feature sets. Most homogeneous TL methods assume that target and source domains share the same feature…

Machine learning relies on the availability of a vast amount of data for training. However, in reality, most data are scattered across different organizations and cannot be easily integrated under many legal and practical constraints. In…

In activity recognition, it is often expensive and time-consuming to acquire sufficient activity labels. To solve this problem, transfer learning leverages the labeled samples from the source domain to annotate the target domain which has…

Quantum Transfer Learning (QTL) offers a promising approach for visual quantum machine learning under near-term constraints, where limited qubit counts, shallow circuit depths, and costly hybrid optimization restrict end-to-end quantum…

Deep Learning (DL) requires a large amount of training data to provide quality outcomes. However, the field of medical imaging suffers from the lack of sufficient data for properly training DL models because medical images require manual…

Deep Convolutional Neural Networks (CNN) have evolved as popular machine learning models for image classification during the past few years, due to their ability to learn the problem-specific features directly from the input images. The…

Lattice thermal conductivity (TC) of semiconductors is crucial for various applications, ranging from microelectronics to thermoelectrics. Data-driven approach can potentially establish the critical composition-property relationship needed…

Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Recently, an…

We provide in this paper a comprehensive comparison of various transfer learning strategies and deep learning architectures for computer-aided classification of adult-type diffuse gliomas. We evaluate the generalizability of out-of-domain…

Multi-Task Learning (MTL) has shown its importance at user products for fast training, data efficiency, reduced overfitting etc. MTL achieves it by sharing the network parameters and training a network for multiple tasks simultaneously.…