Related papers: RevColV2: Exploring Disentangled Representations i…

Point cloud segmentation is central to autonomous driving and 3D scene understanding. While voxel- and point-based methods dominate recent research due to their compatibility with deep architectures and ability to capture fine-grained…

Masked image modeling (MIM) has achieved promising results on various vision tasks. However, the limited discriminability of learned representation manifests there is still plenty to go for making a stronger vision learner. Towards this…

There is substantial interest in developing artificial intelligence systems to support radiologists across tasks ranging from segmentation to report generation. Existing computed tomography (CT) foundation models have largely focused on…

In this paper, we study how to use masked signal modeling in vision and language (V+L) representation learning. Instead of developing masked language modeling (MLM) and masked image modeling (MIM) independently, we propose to build joint…

We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder…

The rapid advancement of generative models has introduced serious risks, including deepfake techniques for facial synthesis and editing. Traditional approaches rely on training classifiers and enhancing generalizability through various…

This paper studies the potential of distilling knowledge from pre-trained models, especially Masked Autoencoders. Our approach is simple: in addition to optimizing the pixel reconstruction loss on masked inputs, we minimize the distance…

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…

This study explores the ability of Image Captioning (IC) models to decode masked visual content sourced from diverse datasets. Our findings reveal the IC model's capability to generate captions from masked images, closely resembling the…

Finetuning a pretrained vision model (PVM) is a common technique for learning downstream vision tasks. However, the conventional finetuning process with randomly sampled data points results in diminished training efficiency. To address this…

The evolution of semantic segmentation has long been dominated by learning more discriminative image representations for classifying each pixel. Despite the prominent advancements, the priors of segmentation masks themselves, e.g.,…

Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation. However, such representations tend to…

We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL. By incorporating a comprehensive suite of architectural innovations,…

We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene-level features. We do this by: (i) the introduction of a perceptual…

Exploring large-scale pretrained foundation models is of significant interest in computer vision because these models can be quickly transferred to many downstream tasks. This paper presents Contrastive Captioner (CoCa), a minimalist design…

Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained autoencoders. However, standard pixel-space diffusion models receive relatively weak semantic…

This work presents Robust Representation Learning via Adaptive Mask (RAM++), a two-stage framework for all-in-one image restoration. RAM++ integrates high-level semantic understanding with low-level texture generation to achieve…

We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue. Our core design is a progressive training approach that…

We introduce CogVLM, a powerful open-source visual language foundation model. Different from the popular shallow alignment method which maps image features into the input space of language model, CogVLM bridges the gap between the frozen…

Multi-modal MRIs are widely used in neuroimaging applications since different MR sequences provide complementary information about brain structures. Recent works have suggested that multi-modal deep learning analysis can benefit from…