Related papers: AdPE: Adversarial Positional Embeddings for Pretra…

Word embeddings are fundamental to natural language processing, yet traditional approaches represent each word with a single vector, creating representational bottlenecks for polysemous words and limiting semantic expressiveness. While…

Self-supervised pre-training has proven highly effective for many computer vision tasks, particularly when labelled data are scarce. In the context of Earth Observation (EO), foundation models and various other Vision Transformer…

Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to imperceptible adversarial perturbations, raising serious safety concerns for open-world…

Recently, various studies have been directed towards exploring dense passage retrieval techniques employing pre-trained language models, among which the masked auto-encoder (MAE) pre-training architecture has emerged as the most promising.…

We propose an AE-based transceiver for a WDM system impaired by hardware imperfections. We design our AE following the architecture of conventional communication systems. This enables to initialize the AE-based transceiver to have similar…

We propose Masked Capsule Autoencoders (MCAE), the first Capsule Network that utilises pretraining in a modern self-supervised paradigm, specifically the masked image modelling framework. Capsule Networks have emerged as a powerful…

We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image…

Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally…

In this paper, we review adversarial pretraining of self-supervised deep networks including both convolutional neural networks and vision transformers. Unlike the adversarial training with access to labeled examples, adversarial pretraining…

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.…

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

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…

Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of the sequence. In this paper, we first investigate various…

Deep neural networks have achieved remarkable progress in enhancing low-light images by improving their brightness and eliminating noise. However, most existing methods construct end-to-end mapping networks heuristically, neglecting the…

So far, expensive finetuning beyond the pretraining sequence length has been a requirement for effectively extending the context of language models (LM). In this work, we break this key bottleneck by Dropping the Positional Embeddings of…

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…

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…

This paper proposes a GeneraLIst encoder-Decoder (GLID) pre-training method for better handling various downstream computer vision tasks. While self-supervised pre-training approaches, e.g., Masked Autoencoder, have shown success in…

Masked image modeling, an emerging self-supervised pre-training method, has shown impressive success across numerous downstream vision tasks with Vision transformers. Its underlying idea is simple: a portion of the input image is masked out…

Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks, especially the physical ones, pose a great threat to the security of such…