Related papers: Deep ViT Features as Dense Visual Descriptors

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…

Vision foundation models have shown great promise for open-set 3D object retrieval (3DOR) through efficient adaptation to multi-view images. Leveraging semantically aligned latent space, previous work typically adapts the CLIP encoder to…

Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision…

Unsupervised semantic segmentation aims to categorize each pixel in an image into a corresponding class without the use of annotated data. It is a widely researched area as obtaining labeled datasets is expensive. While previous works in…

This paper presents a new Vision Transformer (ViT) architecture Multi-Scale Vision Longformer, which significantly enhances the ViT of \cite{dosovitskiy2020image} for encoding high-resolution images using two techniques. The first is the…

The vision transformer-based foundation models, such as ViT or Dino-V2, are aimed at solving problems with little or no finetuning of features. Using a setting of prototypical networks, we analyse to what extent such foundation models can…

This paper explores the potential of abstracting complex visual information into discrete, structured symbolic sequences using self-supervised learning (SSL). Inspired by how language abstracts and organizes information to enable better…

This paper investigates two techniques for developing efficient self-supervised vision transformers (EsViT) for visual representation learning. First, we show through a comprehensive empirical study that multi-stage architectures with…

Vision foundation models (VFMs) have demonstrated remarkable performance across a wide range of downstream tasks. While several VFM adapters have shown promising results by leveraging the prior knowledge of VFMs, we identify two…

Object-centric understanding is fundamental to human vision and required for complex reasoning. Traditional methods define slot-based bottlenecks to learn object properties explicitly, while recent self-supervised vision models like DINO…

Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not…

Vision Transformers (ViTs) have demonstrated remarkable performance across a wide range of vision tasks. In particular, self-distillation frameworks such as DINO have contributed significantly to these advances. Within such frameworks,…

Casting semantic segmentation of outdoor LiDAR point clouds as a 2D problem, e.g., via range projection, is an effective and popular approach. These projection-based methods usually benefit from fast computations and, when combined with…

In recent years, weakly supervised semantic segmentation using image-level labels as supervision has received significant attention in the field of computer vision. Most existing methods have addressed the challenges arising from the lack…

A deep clustering model conceptually consists of a feature extractor that maps data points to a latent space, and a clustering head that groups data points into clusters in the latent space. Although the two components used to be trained…

Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real…

Real-world image denoising is a practical image restoration problem that aims to obtain clean images from in-the-wild noisy inputs. Recently, the Vision Transformer (ViT) has exhibited a strong ability to capture long-range dependencies,…

Self-supervised pretrain techniques have been widely used to improve the downstream tasks' performance. However, real-world magnetic resonance (MR) studies usually consist of different sets of contrasts due to different acquisition…

We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local…

Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks. Current approaches to VLP heavily rely on image feature extraction processes, most of which involve region supervision…