ViT-Small
PulseAugur coverage of ViT-Small — every cluster mentioning ViT-Small across labs, papers, and developer communities, ranked by signal.
-
DINOv3 Features Refined for Efficient Anterior Eye Segmentation
Researchers have developed a novel method for segmenting anterior eye segments (AES) using a distilled DINOv3 ViT-Small backbone. This approach incorporates a step-attention feature refinement module to adapt multi-leve…
-
Lightweight AI model identifies raptor species for wind turbine safety
Researchers have developed a lightweight image classification system for identifying raptor species on edge devices, specifically for wind turbine collision mitigation. The system utilizes knowledge distillation to trai…
-
Deep learning framework estimates coastal wave parameters from video
Researchers have developed a novel deep learning framework for estimating five key coastal wave parameters from monocular video. This system utilizes a V-JEPA backbone for feature extraction in challenging visual condit…
-
AnomExpert framework improves prenatal ultrasound anomaly diagnosis accuracy
Researchers have developed AnomExpert, a novel framework designed to improve the accuracy of prenatal ultrasound anomaly diagnosis. This system utilizes case-level supervision and learnable plane prototypes to organize …
-
New adaptive checkpointing slashes GPU memory for vision model fine-tuning
Researchers have developed an adaptive checkpointing algorithm to reduce the GPU memory required for fine-tuning vision models and vision-language models (VLMs). This method, tested on consumer-grade GPUs with limited V…
-
CLEAR-MoE converts frozen Vision Transformers to sparse MoE models
Researchers have developed CLEAR-MoE, a novel post-training method to transform frozen Vision Transformers (ViTs) into sparse Mixture-of-Experts (MoE) models without altering the original backbone weights. This techniqu…
-
Adaptive Hebbian Routing enhances few-shot Vision Transformer performance
Researchers have developed an Adaptive Hebbian Routing method for few-shot Vision Transformers to improve image recognition from limited data. This approach uses a lightweight MLP router to dynamically control Hebbian m…
-
New framework statistically analyzes Vision Transformer reliability
Researchers have developed SENTRY, a statistical framework to analyze the reliability of Vision Transformers (ViTs) against soft errors. This method uses finite-population sampling theory to provide formal reliability g…
-
Hebbian Fast Weights enhance Vision Transformers for few-shot character recognition
Researchers have developed a new approach to few-shot character recognition by integrating Hebbian Fast-Weight (HFW) modules into Vision Transformer architectures. This method aims to mimic biological neural systems' ab…