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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

11 results for “VGG-19”

Plant Species Classification Using Transfer Learning by Pretrained Classifier VGG-19cs.CV

The paper uses VGG-19 for plant species classification from leaf images.

problem Manual inspection of plant species by botanists is time-consuming.

method Transfer learning with VGG-19 for feature extraction and classification.

result The model achieves 99.70% accuracy in predicting plant species.

plant species classification transfer learning VGG-19 image classification leaf images

2022-09-07abs ↗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 ↗

Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environmentscs.LG

Origami uses SGX enclaves and blinding to protect deep neural network inference privacy.

problem Protecting deep neural network inference privacy in machine learning services.

method Combines enclave execution, cryptographic blinding, and accelerator-based computation.

result Demonstrates improved privacy-preserving inference performance compared to prior work.

SGX cryptographic blinding deep neural networks privacy-preserving inference machine learning

2019-12-07abs ↗pdf ↗

Inspect Transfer Learning Architecture with Dilated Convolutioncs.LG

There are many award-winning pre-trained Convolutional Neural Network (CNN), which have a common phenomenon of increasing depth in convolutional layers. However, I inspect on VGG network, which is one of the famous model submitted to ILSVRC-2014, to show that slight modification in the basic architecture can enhance th…

2019-11-20abs ↗pdf ↗

Gradient Amplification: An efficient way to train deep neural networkscs.LG

Gradient amplification boosts deep learning model performance without increasing training time.

problem Vanishing gradients in deep neural networks.

method Gradient amplification approach to prevent vanishing gradients and training strategy to enable/disable across epochs.

result Improves performance of deep learning models with reduced training time.

gradient amplification deep learning vanishing gradients neural networks training time

2020-06-16abs ↗pdf ↗

Generalisation in humans and deep neural networkscs.CV

We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object recognition under twelve different types of image degradations. First, using three well known DNNs (ResNet-152, VGG-19, GoogLeNet) we find the human visual system to be more robust to nearly all of the tested image manip…

2018-08-27abs ↗pdf ↗

Coverage Testing of Deep Learning Models using Dataset Characterizationcs.LG

Deep Neural Networks (DNNs), with its promising performance, are being increasingly used in safety critical applications such as autonomous driving, cancer detection, and secure authentication. With growing importance in deep learning, there is a requirement for a more standardized framework to evaluate and test deep l…

2019-11-17abs ↗pdf ↗

Efficient Hybrid Network Architectures for Extremely Quantized Neural Networks Enabling Intelligence at the Edgecs.LG

The recent advent of `Internet of Things' (IOT) has increased the demand for enabling AI-based edge computing. This has necessitated the search for efficient implementations of neural networks in terms of both computations and storage. Although extreme quantization has proven to be a powerful tool to achieve significan…

2019-02-01abs ↗pdf ↗

Activation Density driven Energy-Efficient Pruning in Trainingcs.LG

Real-time pruning during training reduces network size and training time.

problem Efficiently reducing neural network size without sacrificing accuracy.

method Activation density-based pruning during training.

result Up to 200x reduction in parameters and 60x reduction in inference compute operations.

neural network pruning energy efficiency training time activation density sparse networks

2020-02-07abs ↗pdf ↗

FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusterscs.LG

Deep Neural Networks (DNNs) have revolutionized numerous applications, but the demand for ever more performance remains unabated. Scaling DNN computations to larger clusters is generally done by distributing tasks in batch mode using methods such as distributed synchronous SGD. Among the issues with this approach is th…

2019-01-04abs ↗pdf ↗

Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarksstat.ML

Study reveals pervasive label errors in test sets, affecting machine learning benchmarks.

problem Label errors in test sets destabilize machine learning benchmarks.

method Identified label errors in 10 common datasets using confident learning algorithms and human validation.

result Lower capacity models may be more useful in real-world datasets with high proportions of erroneously labeled data.

label errors test sets machine learning benchmarks confidence learning human validation

2021-03-26abs ↗pdf ↗