Related papers: Unlocking Masked Autoencoders as Loss Function for…

Image fusion aims to combine information from multiple source images into a single one with more comprehensive informational content. Deep learning-based image fusion algorithms face significant challenges, including the lack of a…

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

Wearable accelerometers are widely used for continuous monitoring of physical activity. Supervised machine learning and deep learning algorithms have long been used to extract meaningful activity information from raw accelerometry data, but…

Overparameterized autoencoder models often memorize their training data. For image data, memorization is often examined by using the trained autoencoder to recover missing regions in its training images (that were used only in their…

Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process,…

Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for…

Deep neural networks have increased the accuracy of automatic segmentation, however, their accuracy depends on the availability of a large number of fully segmented images. Methods to train deep neural networks using images for which some,…

Diffusion Probabilistic Models (DPMs) have shown a powerful capacity of generating high-quality image samples. Recently, diffusion autoencoders (Diff-AE) have been proposed to explore DPMs for representation learning via autoencoding. Their…

Deep learning based image compression has recently witnessed exciting progress and in some cases even managed to surpass transform coding based approaches that have been established and refined over many decades. However, state-of-the-art…

Autoencoders have achieved great success in various computer vision applications. The autoencoder learns appropriate low dimensional image representations through the self-supervised paradigm, i.e., reconstruction. Existing studies mainly…

Tremendous efforts have been made on document image rectification, but how to learn effective representation of such distorted images is still under-explored. In this paper, we present DocMAE, a novel self-supervised framework for document…

Deep neural networks are capable of learning powerful representations to tackle complex vision tasks but expose undesirable properties like the over-fitting issue. To this end, regularization techniques like image augmentation are necessary…

This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures…

The accurate segmentation of lesions in whole-body PET/CT imaging is es-sential for tumor characterization, treatment planning, and response assess-ment, yet current manual workflows are labor-intensive and prone to inter-observer…

Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…

Learned image reconstruction techniques using deep neural networks have recently gained popularity, and have delivered promising empirical results. However, most approaches focus on one single recovery for each observation, and thus neglect…

Masked autoencoder (MAE) shows that severe augmentation during training produces robust representations for high-level tasks. This paper brings the MAE-like framework to nighttime image enhancement, demonstrating that severe augmentation…

Audio classification and restoration are among major downstream tasks in audio signal processing. However, restoration derives less of a benefit from pretrained models compared to the overwhelming success of pretrained models in…

The Masked autoencoder (MAE) has drawn attention as a representative self-supervised approach for masked image modeling with vision transformers. However, even though MAE shows better generalization capability than fully supervised training…

While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…