Related papers: Intensity-Spatial Dual Masked Autoencoder for Mult…

This paper explores Masked Autoencoders (MAE) with Gaussian Splatting. While reconstructive self-supervised learning frameworks such as MAE learns good semantic abstractions, it is not trained for explicit spatial awareness. Our approach,…

Medical image segmentation faces challenges due to variations in anatomical structures. While convolutional neural networks (CNNs) effectively capture local features, they struggle with modeling long-range dependencies. Transformers…

This paper explores improvements to the masked image modeling (MIM) paradigm. The MIM paradigm enables the model to learn the main object features of the image by masking the input image and predicting the masked part by the unmasked part.…

Integrating high-level semantically correlated contents and low-level anatomical features is of central importance in medical image segmentation. Towards this end, recent deep learning-based medical segmentation methods have shown great…

In this paper, we first extend the recent Masked Auto-Encoder (MAE) model from a single modality to audio-visual multi-modalities. Subsequently, we propose the Contrastive Audio-Visual Masked Auto-Encoder (CAV-MAE) by combining contrastive…

The scarcity of labeled data often limits the application of supervised deep learning techniques for medical image segmentation. This has motivated the development of semi-supervised techniques that learn from a mixture of labeled and…

Accurate imputation of missing laboratory values in electronic health records (EHRs) is critical to enable robust clinical predictions and reduce biases in AI systems in healthcare. Existing methods, such as XGBoost, softimpute, GAIN,…

Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or…

Masked autoencoders (MAE) have become a dominant paradigm in 3D representation learning, setting new performance benchmarks across various downstream tasks. Existing methods with fixed mask ratio neglect multi-level representational…

Accurate atmospheric profiles from remote sensing instruments such as Doppler Lidar, Radar, and radiometers are frequently corrupted by low-SNR (Signal to Noise Ratio) gates, range folding, and spurious discontinuities. Traditional gap…

To enhance the performance of affective models and reduce the cost of acquiring physiological signals for real-world applications, we adopt multimodal deep learning approach to construct affective models from multiple physiological signals.…

Domain shift is a problem commonly encountered when developing automated histopathology pipelines. The performance of machine learning models such as convolutional neural networks within automated histopathology pipelines is often…

We propose a novel 3D fully convolutional deep network for automated pancreas segmentation from both MRI and CT scans. More specifically, the proposed model consists of a 3D encoder that learns to extract volume features at different…

Gastrointestinal (GI) imaging via Wireless Capsule Endoscopy (WCE) generates a large number of images requiring manual screening. Deep learning-based Clinical Decision Support (CDS) systems can assist screening, yet their performance relies…

Based on digital pathology slice scanning technology, artificial intelligence algorithms represented by deep learning have achieved remarkable results in the field of computational pathology. Compared to other medical images, pathology…

Medical image segmentation has significantly benefitted thanks to deep learning architectures. Furthermore, semi-supervised learning (SSL) has recently been a growing trend for improving a model's overall performance by leveraging abundant…

Human social behaviors are inherently multimodal necessitating the development of powerful audiovisual models for their perception. In this paper, we present Social-MAE, our pre-trained audiovisual Masked Autoencoder based on an extended…

Vehicle re-identification is a cross-view search task by matching the same target vehicle from different perspectives. It serves an important role in road-vehicle collaboration and intelligent road control. With the large-scale and dynamic…

Unsupervised segmentation approaches have increasingly leveraged foundation models (FM) to improve salient object discovery. However, these methods often falter in scenes with complex, multi-component morphologies, where fine-grained…

We present a variation of the Autoencoder (AE) that explicitly maximizes the mutual information between the input data and the hidden representation. The proposed model, the InfoMax Autoencoder (IMAE), by construction is able to learn a…