Related papers: Code and Pixels: Multi-Modal Contrastive Pre-train…

Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other. They can only utilize single-modal data (i.e. text or image) or limited multi-modal data (i.e. image-text…

Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture…

Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such representations fail to capture the 3D spatial information…

Tabular anomaly detection, which aims at identifying deviant samples, has been crucial in a variety of real-world applications, such as medical disease identification, financial fraud detection, intrusion monitoring, etc. Although recent…

Cross-modal contrastive distillation has recently been explored for learning effective 3D representations. However, existing methods focus primarily on modality-shared features, neglecting the modality-specific features during the…

Handling heterogeneous data in tabular datasets poses a significant challenge for deep learning models. While attention-based architectures and self-supervised learning have achieved notable success, their application to tabular data…

Multimodal representation learning is a challenging task in which previous work mostly focus on either uni-modality pre-training or cross-modality fusion. In fact, we regard modeling multimodal representation as building a skyscraper, where…

Tabular data have been extensively used in different knowledge domains. Convolutional neural networks (CNNs) have been successfully used in many applications where important information about data is embedded in the order of features…

A restricted Boltzmann machine (RBM) is a two-layer neural network with shared weights and has been extensively studied for dimensionality reduction, data representation and recommendation systems in the literature. The traditional RBM…

Multi-task learning (MTL) aims to improve the generalization of several related tasks by learning them jointly. As a comparison, in addition to the joint training scheme, modern meta-learning allows unseen tasks with limited labels during…

Deep learning has potential to automate screening, monitoring and grading of disease in medical images. Pretraining with contrastive learning enables models to extract robust and generalisable features from natural image datasets,…

Real-world data often have a long-tailed distribution, where the number of samples per class is not equal over training classes. The imbalanced data form a biased feature space, which deteriorates the performance of the recognition model.…

This paper explores multi-task learning (MTL) for face recognition. We answer the questions of how and why MTL can improve the face recognition performance. First, we propose a multi-task Convolutional Neural Network (CNN) for face…

Obtaining annotations for 3D medical images is expensive and time-consuming, despite its importance for automating segmentation tasks. Although multi-task learning is considered an effective method for training segmentation models using…

Humans exhibit a remarkable ability to learn quickly from a limited number of labeled samples, a capability that starkly contrasts with that of current machine learning systems. Unsupervised Few-Shot Learning (U-FSL) seeks to bridge this…

Unsupervised Multi-View Stereo (MVS) methods have achieved promising progress recently. However, previous methods primarily depend on the photometric consistency assumption, which may suffer from two limitations: indistinguishable regions…

Table pretrain-then-finetune paradigm has been proposed and employed at a rapid pace after the success of pre-training in the natural language domain. Despite the promising findings in tabular pre-trained language models (TPLMs), there is…

We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations within MIM models generally reside in intermediate layers.…

Deep learning architectures for supervised learning on tabular data range from simple multilayer perceptrons (MLP) to sophisticated Transformers and retrieval-augmented methods. This study highlights a major, yet so far overlooked…

Representation learning stands as one of the critical machine learning techniques across various domains. Through the acquisition of high-quality features, pre-trained embeddings significantly reduce input space redundancy, benefiting…