Related papers: RI-MAE: Rotation-Invariant Masked AutoEncoders for…
Network traffic classification using self-supervised pre-training models based on Masked Autoencoders (MAE) has demonstrated a huge potential. However, existing methods are confined to isolated byte-level reconstruction of individual flows,…
The Masked Autoencoder (MAE) has recently demonstrated effectiveness in pre-training Vision Transformers (ViT) for analyzing natural images. By reconstructing complete images from partially masked inputs, the ViT encoder gathers contextual…
Unsupervised visual anomaly detection conveys practical significance in many scenarios and is a challenging task due to the unbounded definition of anomalies. Moreover, most previous methods are application-specific, and establishing a…
The latent space of generative modeling is long dominated by the VAE encoder. The latents from the pretrained representation encoders (e.g., DINO, SigLIP, MAE) are previously considered inappropriate for generative modeling. Recently, RAE…
Masked point modeling has become a promising scheme of self-supervised pre-training for point clouds. Existing methods reconstruct either the original points or related features as the objective of pre-training. However, considering the…
Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks for very large fully-annotated datasets. Different classes of self-supervised learning offer representations with either good contextual…
We present LBS-AE; a self-supervised autoencoding algorithm for fitting articulated mesh models to point clouds. As input, we take a sequence of point clouds to be registered as well as an artist-rigged mesh, i.e. a template mesh equipped…
Masked Autoencoders is a simple yet powerful self-supervised learning method. However, it learns representations indirectly by reconstructing masked input patches. Several methods learn representations directly by predicting representations…
Many real-world physics and engineering problems arise in geometrically complex domains discretized by meshes for numerical simulations. The nodes of these potentially irregular meshes naturally form point clouds whose limited tractability…
A major challenge in quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional…
We investigated the adaptation and performance of Masked Autoencoders (MAEs) with Vision Transformer (ViT) architectures for self-supervised representation learning on one-dimensional (1D) ultrasound signals. Although MAEs have demonstrated…
We introduce CAN, a simple, efficient and scalable method for self-supervised learning of visual representations. Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the…
Pre-training strategies based on self-supervised learning (SSL) have proven to be effective pretext tasks for many downstream tasks in computer vision. Due to the significant disparity between medical and natural images, the application of…
Dynamic facial expression recognition (DFER) is essential to the development of intelligent and empathetic machines. Prior efforts in this field mainly fall into supervised learning paradigm, which is severely restricted by the limited…
We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…
Referring Image Segmentation (RIS) aims to segment target objects expressed in natural language within a scene at the pixel level. Various recent RIS models have achieved state-of-the-art performance by generating contextual tokens to model…
Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale unlabeled medical datasets presents a promising solution,…
Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data. Like existing TTT methods from the 2D image…
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…
Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either fully implicit neural fields or fully explicit geometric primitives. Implicit…