On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “DeiT”

Realism in Action: Anomaly-Aware Diagnosis of Brain Tumors from Medical Images Using YOLOv8 and DeiTeess.IV

Framework detects brain tumors robustly from MRI images.

problem Low clinical incidence of brain tumor cases makes diagnosis challenging.

method YOLOv8n for detection, DeiT for classification, PTP metric for evaluation.

result F1-score of 0.92 achieved with reduced computational resources.

brain tumors medical images YOLOv8 DeiT anomaly detection

2024-01-06abs ↗pdf ↗

Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategycs.CV

Paper compresses ViTs models by 60% with minimal accuracy loss.

problem Memory constraints in ViTs models.

method Activation-aware low-rank tensor approximations.

result 60% reduction in model size with <1% accuracy loss.

Vision Transformers compression low-rank approximation memory efficiency computer vision

2024-02-08abs ↗pdf ↗

Hyperflux: Pruning Reveals Importancestat.ML

Hyperflux models pruning as a system to reveal weight importance.

problem Pruning large neural networks to reduce latency and power consumption.

method Introduces Hyperflux, a novel

L_0

method that models pruning as flux and pressure.

result Achieves competitive results with ResNet-50, VGG-19, and DeiT-T/S on various datasets.

network pruning neural networks inference latency power consumption ResNet-50

2025-04-06abs ↗pdf ↗

On Measuring Localization of Shortcuts in Deep Networkscs.LG

Study on shortcuts in deep networks, revealing their layer-wise distribution and impact.

problem Understudied impact of shortcuts on feature representations in deep networks.

method Layer-wise localization through counterfactual training on clean and skewed datasets.

result Shortcuts are distributed throughout the network, not localized in specific layers.

shortcuts deep networks feature representations counterfactual training CIFAR-10

2025-10-30abs ↗pdf ↗

ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescs.CV

ConViT combines CNN and ViT strengths, improving image classification.

problem Combining the strengths of CNNs and ViTs while avoiding their limitations.

method Introducing GPSA, a form of positional self-attention with a soft convolutional inductive bias.

result ConViT outperforms DeiT on ImageNet while offering improved sample efficiency.

Vision Transformers Convolutional Neural Networks Self-Attention Soft Convolutional Biases Image Classification

2021-03-19abs ↗pdf ↗

Engineering flexible machine learning systems by traversing functionally-invariant pathscs.LG

New method adapts neural networks without losing prior knowledge.

problem Understanding and enabling flexible adaptation of neural networks.

method Differential geometry framework, functionally invariant paths (FIP).

result Achieves comparable state-of-the-art performance on continual learning and sparsification tasks.

neural networks transformers fine-tuning differential geometry functionally invariant paths

2022-04-30abs ↗pdf ↗

Deep learning-based identification of precipitation clouds from all-sky camera data for observatory safetyastro-ph.IM

Deep learning identifies precipitation clouds from all-sky camera data.

problem Automating cloud warning systems for observatories.

method Deep learning using EfficientNet network.

result Average accuracy of 99% in identifying rainfall potential and 96% in cloud coverage.

deep learning precipitation clouds all-sky cameras observatory safety cloud warning system

2025-03-24abs ↗pdf ↗