相关论文: From Edges to Depth: Probing the Spatial Hierarchy…

The ultimate goal for foundation models is realizing task-agnostic, i.e., supporting out-of-the-box usage without task-specific fine-tuning. Although breakthroughs have been made in natural language processing and image representation…

We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch,…

Vision Transformer (ViT) has recently demonstrated promise in computer vision problems. However, unlike Convolutional Neural Networks (CNN), it is known that the performance of ViT saturates quickly with depth increasing, due to the…

Object detectors achieve strong performance under nominal imaging conditions but can fail silently when exposed to blur, noise, compression, adverse weather, or resolution changes. In safety-critical settings, it is therefore insufficient…

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of…

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Extensive work has demonstrated the effectiveness of Vision Transformers. The plain Vision Transformer tends to obtain multi-scale features by selecting fixed layers, or the last layer of features aiming to achieve higher performance in…

High-resolution images offer more information about scenes that can improve model accuracy. However, the dominant model architecture in computer vision, the vision transformer (ViT), cannot effectively leverage larger images without…

Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood. Existing interpretability work on VLMs uses Sparse Autoencoders (SAEs), which decompose…

Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models remains a challenge. To…

Enhancing the robustness of deep learning models, particularly in the realm of vision transformers (ViTs), is crucial for their real-world deployment. In this work, we provide a finetuning approach to enhance the robustness of vision…

Vision Transformers (ViT) have recently demonstrated the significant potential of transformer architectures for computer vision. To what extent can image-based deep reinforcement learning also benefit from ViT architectures, as compared to…

In recent computer vision research, the advent of the Vision Transformer (ViT) has rapidly revolutionized various architectural design efforts: ViT achieved state-of-the-art image classification performance using self-attention found in…

Wide-parameter-space searches for continuous gravitational waves using semi-coherent matched-filter methods require enormous computing power, which limits their achievable sensitivity. Here we explore an alternative search method based on…

We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an…

Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale unlabeled medical datasets presents a promising solution,…

Vision transformers have shown great success on numerous computer vision tasks. However, its central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational…

In deep learning, it is usually assumed that the optimization process is conducted on a shape-fixed loss surface. Differently, we first propose a novel concept of deformation mapping in this paper to affect the behaviour of the optimizer.…

Vision transformers have achieved remarkable progress in vision tasks such as image classification and detection. However, in instance-level image retrieval, transformers have not yet shown good performance compared to convolutional…

In computer vision, Single Image Super-Resolution (SISR) is still a difficult problem. We present ViT-SR, a new technique to improve the performance of a Vision Transformer (ViT) employing a two-stage training strategy. In our method, the…