相关论文: Masked strategies for images with small objects

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Recently, the advancement of self-supervised learning techniques, like masked autoencoders (MAE), has greatly influenced visual representation learning for images and videos. Nevertheless, it is worth noting that the predominant approaches…

There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our…

Current deep learning-based manifold learning algorithms such as the variational autoencoder (VAE) require fully sampled data to learn the probability density of real-world datasets. Once learned, the density can be used for a variety of…

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…

Subtle hand differences make sign language recognition challenging, yet many existing methods rely on encoders pretrained on generic action datasets that poorly capture such fine-grained cues. We propose a self-supervised pretraining method…

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…

Learning object segmentation in image and video datasets without human supervision is a challenging problem. Humans easily identify moving salient objects in videos using the gestalt principle of common fate, which suggests that what moves…

In digital pathology, whole slide images (WSIs) are widely used for applications such as cancer diagnosis and prognosis prediction. Visual transformer models have recently emerged as a promising method for encoding large regions of WSIs…

Autoencoding, which aims to reconstruct the input images through a bottleneck latent representation, is one of the classic feature representation learning strategies. It has been shown effective as an auxiliary task for semi-supervised…

Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing pretraining…

Mask-based pretraining has become a cornerstone of modern large-scale models across language, vision, and recently biology. Despite its empirical success, its role and limits in learning data representations have been unclear. In this work,…

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…

We propose an efficient approach to train large diffusion models with masked transformers. While masked transformers have been extensively explored for representation learning, their application to generative learning is less explored in…

Self-supervised auto-encoders have emerged as a successful framework for representation learning in computer vision and natural language processing in recent years, However, their application to graph data has been met with limited…

Ultrasound imaging is challenging to interpret due to non-uniform intensities, low contrast, and inherent artifacts, necessitating extensive training for non-specialists. Advanced representation with clear tissue structure separation could…

Autoencoding is a popular method in representation learning. Conventional autoencoders employ symmetric encoding-decoding procedures and a simple Euclidean latent space to detect hidden low-dimensional structures in an unsupervised way.…

Semi-supervised learning relaxes the need of large pixel-wise labeled datasets for image segmentation by leveraging unlabeled data. A prominent way to exploit unlabeled data is to regularize model predictions. Since the predictions of…

Masked Image Modeling (MIM) has emerged as a promising method for deriving visual representations from unlabeled image data by predicting missing pixels from masked portions of images. It excels in region-aware learning and provides strong…

Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain…