Related papers: Large Vision Models Can Solve Mental Rotation Prob…

The human brain is adept at solving difficult high-level visual processing problems such as image interpretation and object recognition in natural scenes. Over the past few years neuroscientists have made remarkable progress in…

Vision transformers (ViTs) are top performing models on many computer vision benchmarks and can accurately predict human behavior on object recognition tasks. However, researchers question the value of using ViTs as models of biological…

This paper presents DINO-RotateMatch, a deep-learning framework designed to address the chal lenges of image matching in large-scale 3D reconstruction from unstructured Internet images. The method integrates a dataset-adaptive image pairing…

Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a…

Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly…

Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked image modeling (MIM) in self-supervised representation…

The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged. However, models such as the Vision Transformer (ViT)…

Transformers are state-of-the-art deep learning models that are composed of stacked attention and point-wise, fully connected layers designed for handling sequential data. Transformers are not only ubiquitous throughout Natural Language…

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…

Deep Neural Networks (DNNs) demonstrate remarkable capabilities in learning complex hierarchical data representations, but the nature of these representations remains largely unknown. Existing global explainability methods, such as Network…

The dual thinking framework considers fast, intuitive, and slower logical processing. The perception of dual thinking in vision requires images where inferences from intuitive and logical processing differ, and the latter is under-explored…

Multimodal Large Language Models (MLLMs) have recently achieved remarkable success in visual-language understanding, demonstrating superior high-level semantic alignment within their vision encoders. An important question thus arises: Can…

Visual reasoning may require models to interpret images and videos and respond to implicit text queries across diverse output formats, from pixel-level segmentation masks to natural language descriptions. Existing approaches rely on…

Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to dataset and model sizes which has led to state-of-the-art…

Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly designed for image classification that generate single-scale…

Human physical reasoning relies on internal "body" representations - coarse, volumetric approximations that capture an object's extent and support intuitive predictions about motion and physics. While psychophysical evidence suggests humans…

Recent self-supervised learning models simulate the development of semantic object representations by training on visual experience similar to that of toddlers. However, these models ignore the foveated nature of human vision with high/low…

Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to…

Vision Transformers (ViTs) have demonstrated strong capabilities in capturing global dependencies but often struggle to efficiently represent fine-grained local details. Existing multi-scale approaches alleviate this issue by integrating…

Vision Transformers (ViTs) and Swin Transformers (Swin) are currently state-of-the-art in computational pathology. However, domain experts are still reluctant to use these models due to their lack of interpretability. This is not…