Related papers: Efficient Image Pre-Training with Siamese Cropped …

Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners…

Current video-based Masked Autoencoders (MAEs) primarily focus on learning effective spatiotemporal representations from a visual perspective, which may lead the model to prioritize general spatial-temporal patterns but often overlook…

This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS),…

Self-supervised pretraining has transformed computer vision by enabling data-efficient fine-tuning, yet high-resolution training typically requires server-scale infrastructure, limiting in-domain foundation model development for many…

Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can…

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input…

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual…

Masked image modeling has been demonstrated as a powerful pretext task for generating robust representations that can be effectively generalized across multiple downstream tasks. Typically, this approach involves randomly masking patches…

Self-supervised learning for computer vision has achieved tremendous progress and improved many downstream vision tasks such as image classification, semantic segmentation, and object detection. Among these, generative self-supervised…

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…

Transformers have shown significant effectiveness for various vision tasks including both high-level vision and low-level vision. Recently, masked autoencoders (MAE) for feature pre-training have further unleashed the potential of…

This paper studies a conceptually simple extension of Masked Autoencoders (MAE) to spatiotemporal representation learning from videos. We randomly mask out spacetime patches in videos and learn an autoencoder to reconstruct them in pixels.…

Recently, significant progress has been made in masked image modeling to catch up to masked language modeling. However, unlike words in NLP, the lack of semantic decomposition of images still makes masked autoencoding (MAE) different…

Masked autoencoders (MAEs) have displayed significant potential in the classification and semantic segmentation of medical images in the last year. Due to the high similarity of human tissues, even slight changes in medical images may…

Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data augmentation strategies for MAE still remain open questions, different…

In the domain of computer vision, the restoration of missing information in video frames is a critical challenge, particularly in applications such as autonomous driving and surveillance systems. This paper introduces the Siamese Masked…

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…

In this work, we introduce long-video masked-embedding autoencoders (LV-MAE), a self-supervised learning framework for long video representation. Our approach treats short- and long-span dependencies as two separate tasks. Such decoupling…

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…

We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the representation of an image view containing randomly masked patches to the representation of the…