Related papers: SelfSwapper: Self-Supervised Face Swapping via Sha…

Medical imaging tasks are very challenging due to the lack of publicly available labeled datasets. Hence, it is difficult to achieve high performance with existing deep-learning models as they require a massive labeled dataset to be trained…

We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is…

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multidimensional features.…

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

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…

Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations,…

Self-Supervised Learning (SSL) has emerged as a key technique in machine learning, tackling challenges such as limited labeled data, high annotation costs, and variable wireless channel conditions. It is essential for developing Channel…

Transformer-based audio self-supervised learning (SSL) models commonly use spectrograms, vision-style Transformers, and masked modeling objectives. However, convolutional patchification with temporal downsampling lowers the effective…

In contrast to fully-supervised models, self-supervised representation learning only needs a fraction of data to be labeled and often achieves the same or even higher downstream performance. The goal is to pre-train deep neural networks on…

Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios. Recently, contrastive learning and Transformer-based models have achieved good performance in many long-term series…

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…

Most deep learning based image inpainting approaches adopt autoencoder or its variants to fill missing regions in images. Encoders are usually utilized to learn powerful representational spaces, which are important for dealing with…

In this paper, we design and evaluate a convolutional autoencoder that perturbs an input face image to impart privacy to a subject. Specifically, the proposed autoencoder transforms an input face image such that the transformed image can be…

Masked autoencoder (MAE) is a promising self-supervised pre-training technique that can improve the representation learning of a neural network without human intervention. However, applying MAE directly to volumetric medical images poses…

Vision Transformer (ViT) suffers from data scarcity in semi-supervised learning (SSL). To alleviate this issue, inspired by masked autoencoder (MAE), which is a data-efficient self-supervised learner, we propose Semi-MAE, a pure ViT-based…

Recent methods for self-supervised learning can be grouped into two paradigms: contrastive and non-contrastive approaches. Their success can largely be attributed to data augmentation pipelines which generate multiple views of a single…

Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for language and 2D image transformers. However, it still remains an open question on how to exploit masked autoencoding for learning 3D representations…

Unsupervised multivariate time series (MTS) representation learning aims to extract compact and informative representations from raw sequences without relying on labels, enabling efficient transfer to diverse downstream tasks. In this…

Test-time adaption (TTA) has witnessed important progress in recent years, the prevailing methods typically first encode the image and the text and design strategies to model the association between them. Meanwhile, the image encoder is…

Self-supervised learning with masked autoencoders has recently gained popularity for its ability to produce effective image or textual representations, which can be applied to various downstream tasks without retraining. However, we observe…