CrisisViT is a robust Vision Transformer for crisis image classification. The paper argues that in emergency situations, images from social media can provide valuable, real-time information. However, the volume of…
Continue readingThis article presents the development of LT-ViT, a Vision Transformer (ViT) for multi-label Chest X-ray (CXR) classification. Unlike previous ViTs, LT-ViT aggregates information from multiple scales, improving vision-only training for…
Continue readingThe article presents AiluRus, a new method to speed up Vision Transformers (ViTs) for dense prediction tasks like object detection and semantic segmentation. The approach reduces the complexity of ViTs…
Continue readingThe paper focuses on the detection of heart disease through ECG images using advanced technologies, specifically vision transformer models. These models include Google-Vit, Microsoft-Beit, and Swin-Tiny. The study emphasizes the…
Continue readingThe article presents PlainSeg, a minimalist and efficient system for semantic segmentation utilizing plain Vision Transformer (ViT) models. The system aims to achieve high performance using a simple structure, consisting…
Continue readingThis research paper discusses the identification of artifacts in the feature maps of both supervised and self-supervised Vision Transformer (ViT) networks. These artifacts are high-norm tokens appearing primarily in low-informative…
Continue readingThe article presents BayesDLL, a new Bayesian neural network library for PyTorch. The library is designed for large-scale deep networks and implements various approximate Bayesian inference algorithms such as variational…
Continue readingThe paper “Hardwiring ViT Patch Selectivity into CNNs using Patch Mixing” investigates the unique property of Vision Transformers (ViTs) known as “patch selectivity”. This feature enables ViTs to effectively ignore…
Continue readingThe model presented in this paper is designed to address the challenges of multi-task learning in the field of computer vision. It is built upon a mixture-of-experts (MoE) vision transformer…
Continue readingThe paper presents two strategies for learning pose-aware representations in Vision Transformers (ViTs). The first strategy, called Pose-aware Attention Block (PAAB), is a plug-and-play ViT block that performs localized attention…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
