Related papers: CAE v2: Context Autoencoder with CLIP Target

SimMIM is a widely used method for pretraining vision transformers using masked image modeling. However, despite its success in fine-tuning performance, it has been shown to perform sub-optimally when used for linear probing. We propose an…

Open-vocabulary semantic segmentation aims to segment an image into semantic regions according to text descriptions, which may not have been seen during training. Recent two-stage methods first generate class-agnostic mask proposals and…

We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample…

CLIP has become a cornerstone of multimodal representation learning, yet improving its performance typically requires a prohibitively costly process of training from scratch on billions of samples. We ask a different question: Can we…

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt,…

Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT,…

Prior work using Masked Autoencoders (MAEs) typically relies on random patch masking based on the assumption that images have significant redundancies across different channels, allowing for the reconstruction of masked content using…

In this work, we examine the impact of inter-patch dependencies in the decoder of masked autoencoders (MAE) on representation learning. We decompose the decoding mechanism for masked reconstruction into self-attention between mask tokens…

Learned image compression (LIC) methods have experienced significant progress during recent years. However, these methods are primarily dedicated to optimizing the rate-distortion (R-D) performance at medium and high bitrates (> 0.1 bits…

Large, pretrained models are commonly finetuned with imagery that is heavily augmented to mimic different conditions and scales, with the resulting models used for various tasks with imagery from a range of spatial scales. Such models…

Featurizing microscopy images for use in biological research remains a significant challenge, especially for large-scale experiments spanning millions of images. This work explores the scaling properties of weakly supervised classifiers and…

Dense pixel-specific representation learning at scale has been bottlenecked due to the unavailability of large-scale multi-view datasets. Current methods for building effective pretraining datasets heavily rely on annotated 3D meshes, point…

Masked Image Modeling (MIM) is a self-supervised learning technique that involves masking portions of an image, such as pixels, patches, or latent representations, and training models to predict the missing information using the visible…

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…

In unsupervised domain adaptation (UDA), a model trained on source data (e.g. synthetic) is adapted to target data (e.g. real-world) without access to target annotation. Most previous UDA methods struggle with classes that have a similar…

In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and…

Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-training efficiency and fine-tuning accuracy. Notably, the…

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…

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…

Due to the prevalence of scale variance in nature images, we propose to use image scale as a self-supervised signal for Masked Image Modeling (MIM). Our method involves selecting random patches from the input image and downsampling them to…