Related papers: Understanding Masked Autoencoders From a Local Con…

Masked autoencoders (MAE) have shown great promise in medical image classification. However, the random masking strategy employed by traditional MAEs may overlook critical areas in medical images, where even subtle changes can indicate…

Masked autoencoders (MAEs) have emerged as a powerful approach for pre-training on unlabelled data, capable of learning robust and informative feature representations. This is particularly advantageous in diffused lung disease research,…

Neural fields excel in computer vision and robotics due to their ability to understand the 3D visual world such as inferring semantics, geometry, and dynamics. Given the capabilities of neural fields in densely representing a 3D scene from…

Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing…

Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive…

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…

Missing input sequences are common in medical imaging data, posing a challenge for deep learning models reliant on complete input data. In this work, inspired by MultiMAE [2], we develop a masked autoencoder (MAE) paradigm for multi-modal,…

Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such visual cues depends…

Self-supervised frameworks for representation learning have recently stirred up interest among the remote sensing community, given their potential to mitigate the high labeling costs associated with curating large satellite image datasets.…

Recently, self-supervised pre-training has advanced Vision Transformers on various tasks w.r.t. different data modalities, e.g., image and 3D point cloud data. In this paper, we explore this learning paradigm for 3D mesh data analysis based…

Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition. This work shows that CMAE also trivially generalizes well on…

Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfully reproduce real-world scenarios, such as uneven…

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…

Self-supervised pre-training for images without labels has recently achieved promising performance in image classification. The success of transformer-based methods, ViT and MAE, draws the community's attention to the design of backbone…

Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to assist in the…

Self-supervised landmark estimation is a challenging task that demands the formation of locally distinct feature representations to identify sparse facial landmarks in the absence of annotated data. To tackle this task, existing…

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…

In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrained text encoder into contrastive audio-visual masked…

We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. The novelty of the proposed model is threefold. First, we introduce an approach to weight tokens based…

Learning transferable representations from unlabeled time series is crucial for improving performance in data-scarce classification. Existing self-supervised methods often operate at the point level and rely on unidirectional encoding,…