Related papers: A simple, efficient and scalable contrastive maske…
Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance…
Learning robust representations for physiological time-series signals continues to pose a substantial challenge in developing efficient few-shot learning applications. This difficulty is largely due to the complex pathological variations in…
Tokenizing images into compact visual representations is a key step in learning efficient and high-quality image generative models. We present a simple diffusion tokenizer (DiTo) that learns compact visual representations for image…
Contrastive self-supervised learning has attracted significant research attention recently. It learns effective visual representations from unlabeled data by embedding augmented views of the same image close to each other while pushing away…
Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long…
We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on instance-discriminative contrastive learning are not as…
Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations. A promising technique for unsupervised learning is the framework of Variational Auto-encoders (VAEs).…
Learning robust representations to discriminate cell phenotypes based on microscopy images is important for drug discovery. Drug development efforts typically analyse thousands of cell images to screen for potential treatments. Early works…
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the…
Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in leveraging high-quality pre-trained visual…
Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…
Can a lightweight Vision Transformer (ViT) match or exceed the performance of Convolutional Neural Networks (CNNs) like ResNet on small datasets with small image resolutions? This report demonstrates that a pure ViT can indeed achieve…
For learned image representations, basic autoencoders often produce blurry results. Reconstruction quality can be improved by incorporating additional penalties such as adversarial (GAN) and perceptual losses. Arguably, these approaches…
Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for…
This paper presents SimMIM, a simple framework for masked image modeling. We simplify recently proposed related approaches without special designs such as block-wise masking and tokenization via discrete VAE or clustering. To study what let…
Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variation of information density between them. The question is: Is…
Deep Convolutional Neural Networks (CNN) have exhibited superior performance in many visual recognition tasks including image classification, object detection, and scene label- ing, due to their large learning capacity and resistance to…
Unsupervised learning methods based on contrastive learning have drawn increasing attention and achieved promising results. Most of them aim to learn representations invariant to instance-level variations, which are provided by different…
The use of self-supervised pre-training has emerged as a promising approach to enhance the performance of many different visual tasks. In this context, recent approaches have employed the Masked Image Modeling paradigm, which pre-trains a…
Computational models that predict cellular phenotypic responses to chemical and genetic perturbations can accelerate drug discovery by prioritizing therapeutic hypotheses and reducing costly wet-lab iteration. However, extracting…