Related papers: SemanticMIM: Marring Masked Image Modeling with Se…

Multi-modal semantic understanding requires integrating information from different modalities to extract users' real intention behind words. Most previous work applies a dual-encoder structure to separately encode image and text, but fails…

Conventional deep learning models deal with images one-by-one, requiring costly and time-consuming expert labeling in the field of medical imaging, and domain-specific restriction limits model generalizability. Visual in-context learning…

Masked image modeling has demonstrated great potential to eliminate the label-hungry problem of training large-scale vision Transformers, achieving impressive performance on various downstream tasks. In this work, we propose a unified view…

Large unimodal foundation models for vision and language encode rich semantic structures, yet aligning them typically requires computationally intensive multimodal fine-tuning. Such approaches depend on large-scale parameter updates, are…

Masked video modeling, such as VideoMAE, is an effective paradigm for video self-supervised learning (SSL). However, they are primarily based on reconstructing pixel-level details on natural videos which have substantial temporal…

Masked Image Modeling (MIM) is a new self-supervised vision pre-training paradigm using a Vision Transformer (ViT). Previous works can be pixel-based or token-based, using original pixels or discrete visual tokens from parametric tokenizer…

Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency. We believe the insufficient utilization of training signals should be responsible. To alleviate this…

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank.…

Unified models (UMs) hold promise for their ability to understand and generate content across heterogeneous modalities. Compared to merely generating visual content, the use of UMs for interleaved cross-modal reasoning is more promising and…

The landscape of publicly available vision foundation models (VFMs), such as CLIP and Segment Anything Model (SAM), is expanding rapidly. VFMs are endowed with distinct capabilities stemming from their pre-training objectives. For instance,…

This paper studies co-segmenting the common semantic object in a set of images. Existing works either rely on carefully engineered networks to mine the implicit semantic information in visual features or require extra data (i.e.,…

Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder…

Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic modalities. Due to noises in web-harvested text-image pairs, however, scaling up…

Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. However, subsequent works have complicated the framework with new auxiliary tasks or extra pre-trained models, inevitably…

Multimodal models, such as the Contrastive Language-Image Pre-training (CLIP) model, have demonstrated remarkable success in aligning visual and linguistic representations. However, these models exhibit limitations when applied to…

Recently, learned image compression has achieved remarkable performance. The entropy model, which estimates the distribution of the latent representation, plays a crucial role in boosting rate-distortion performance. However, most entropy…

While mainstream machine learning methods are known to have limited ability to compositionally generalize, new architectures and techniques continue to be proposed to address this limitation. We investigate state-of-the-art techniques and…

Large-scale natural image-text datasets, especially those automatically collected from the web, often suffer from loose semantic alignment due to weak supervision, while medical datasets tend to have high cross-modal correlation but low…

The success of language Transformers is primarily attributed to the pretext task of masked language modeling (MLM), where texts are first tokenized into semantically meaningful pieces. In this work, we study masked image modeling (MIM) and…

We introduce a novel representation learning method to disentangle pose-dependent as well as view-dependent factors from 2D human poses. The method trains a network using cross-view mutual information maximization (CV-MIM) which maximizes…