Related papers: Variance-Covariance Regularization Improves Repres…

Training a fine-grained image recognition model with limited data presents a significant challenge, as the subtle differences between categories may not be easily discernible amidst distracting noise patterns. One commonly employed strategy…

Multimodality Representation Learning, as a technique of learning to embed information from different modalities and their correlations, has achieved remarkable success on a variety of applications, such as Visual Question Answering (VQA),…

We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in continual learning scenarios, storing network parameters at each…

Optimization-based regularization methods have been effective in addressing the challenges posed by data heterogeneity in medical federated learning, particularly in improving the performance of underrepresented clients. However, these…

There are many time series in the literature with high dimension yet limited sample sizes, such as macroeconomic variables, and it is almost impossible to obtain efficient estimation and accurate prediction by using the corresponding…

The substantial modality-induced variations in radiometric, texture, and structural characteristics pose significant challenges for the accurate registration of multimodal images. While supervised deep learning methods have demonstrated…

Visual question answering (VQA) models have been shown to over-rely on linguistic biases in VQA datasets, answering questions "blindly" without considering visual context. Adversarial regularization (AdvReg) aims to address this issue via…

Training a deep neural network with a small amount of data is a challenging problem as it is vulnerable to overfitting. However, one of the practical difficulties that we often face is to collect many samples. Transfer learning is a…

In this paper, we argue that viewing VICReg-a popular self-supervised learning (SSL) method--through the lens of spectral embedding reveals a potential source of sub-optimality: it may struggle to generalize robustly to unseen data due to…

Transferring the weights of a pre-trained model to assist another task has become a crucial part of modern deep learning, particularly in data-scarce scenarios. Pre-training refers to the initial step of training models outside the current…

To successfully apply trained neural network models to new domains, powerful transfer learning solutions are essential. We propose to introduce a novel cross-domain latent modulation mechanism to a variational autoencoder framework so as to…

Scarcity of labeled data has motivated the development of semi-supervised learning methods, which learn from large portions of unlabeled data alongside a few labeled samples. Consistency Regularization between model's predictions under…

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…

This paper is about regularizing deep convolutional networks (CNNs) based on an adaptive framework for transfer learning with limited training data in the target domain. Recent advances of CNN regularization in this context are commonly due…

Medical image segmentation models are typically optimised with voxel-wise losses that constrain predictions only in the output space. This leaves latent feature representations largely unconstrained, potentially limiting generalisation. We…

While sequential recommendation achieves significant progress on capturing user-item transition patterns, transferring such large-scale recommender systems remains challenging due to the disjoint user and item groups across domains. In this…

We propose ROI regularization (ROIreg) as a semi-supervised learning method for image classification. ROIreg focuses on the maximum probability of a posterior probability distribution g(x) obtained when inputting an unlabeled data sample x…

Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. This problem usually arises due to the overfitting problem, which is characterized by learning everything presented in the…

Agents trained with deep reinforcement learning algorithms are capable of performing highly complex tasks including locomotion in continuous environments. We investigate transferring the learning acquired in one task to a set of previously…

Transfer learning is a powerful technique for knowledge-sharing between different tasks. Recent work has found that the representations of models with certain invariances, such as to adversarial input perturbations, achieve higher…