Related papers: Concatenated Masked Autoencoders as Spatial-Tempor…

Building scalable models to learn from diverse, multimodal data remains an open challenge. For vision-language data, the dominant approaches are based on contrastive learning objectives that train a separate encoder for each modality. While…

Whole-slide images are central to digital pathology, yet their extreme size and scarce annotations make self-supervised learning essential. Masked Autoencoders (MAEs) with Vision Transformer backbones have recently shown strong potential…

We introduce SyncLipMAE, a self-supervised pretraining framework for talking-face video that learns synchronization-aware and transferable facial dynamics from unlabeled audio-visual streams. Our approach couples masked visual modeling with…

The hematology analytics used for detection and classification of small blood components is a significant challenge. In particular, when objects exists as small pixel-sized entities in a large context of similar objects. Deep learning…

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…

Recently, learned video compression has achieved exciting performance. Following the traditional hybrid prediction coding framework, most learned methods generally adopt the motion estimation motion compensation (MEMC) method to remove…

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…

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,…

Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder…

Image-based Joint-Embedding Predictive Architecture (IJEPA) offers an attractive alternative to Masked Autoencoder (MAE) for representation learning using the Masked Image Modeling framework. IJEPA drives representations to capture useful…

Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. However, in 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling…

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.…

Pre-training by numerous image data has become de-facto for robust 2D representations. In contrast, due to the expensive data acquisition and annotation, a paucity of large-scale 3D datasets severely hinders the learning for high-quality 3D…

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…

Broadcast and media organizations increasingly rely on artificial intelligence to automate the labor-intensive processes of content indexing, tagging, and metadata generation. However, existing AI systems typically operate on a single…

This study explores the application of self-supervised learning (SSL) to the task of motion forecasting, an area that has not yet been extensively investigated despite the widespread success of SSL in computer vision and natural language…

Self-supervised learning methods like masked autoencoders (MAE) have shown significant promise in learning robust feature representations, particularly in image reconstruction-based pretraining task. However, their performance is often…

In this work, we explore self-supervised visual pre-training on images from diverse, in-the-wild videos for real-world robotic tasks. Like prior work, our visual representations are pre-trained via a masked autoencoder (MAE), frozen, and…

Dynamic vision sensors (DVS) are bio-inspired devices that capture visual information in the form of asynchronous events, which encode changes in pixel intensity with high temporal resolution and low latency. These events provide rich…

We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image…