CNNS
PulseAugur coverage of CNNS — every cluster mentioning CNNS across labs, papers, and developer communities, ranked by signal.
- instance of convolutional neural network 90%
- instance of Vision Transformers 90%
- used by deep learning 90%
- instance of Vits 90%
- used by alphaXiv 70%
- uses Vision Transformers 70%
- instance of alphaXiv 70%
- instance of ScienceCast 70%
- instance of DagsHub 70%
- instance of Manchester Literary and Philosophical Society 70%
- competes with Vits 70%
- competes with Manchester Literary and Philosophical Society 70%
18 day(s) with sentiment data
-
Vision Transformers' data efficiency linked to pretraining coherence, not inherent bias
A new research paper challenges the common belief that Vision Transformers (ViTs) inherently require more labeled data than Convolutional Neural Networks (CNNs) for industrial dense prediction tasks. The study suggests …
-
New UniDFKD framework enhances data-free knowledge distillation for Vision Transformers
Researchers have introduced UniDFKD, a novel framework for data-free knowledge distillation that addresses limitations in modern neural network architectures like Vision Transformers. Unlike previous methods that relied…
-
New tropical convolution methods boost CNN efficiency and accuracy
Researchers have introduced novel extensions to tropical convolutional neural networks (TCNNs) called compound tropical convolution (cTCNN) and parallel tropical convolution (pTCNN). These new operators aim to enhance t…
-
Explainability methods show architecture-dependent performance across AI vision models
A new benchmark study published on arXiv investigates the effectiveness of explainable AI (XAI) attribution methods, particularly their transferability between Convolutional Neural Networks (CNNs) and Vision Transformer…
-
New framework predicts hyperparameter transfer laws for neural networks
Researchers have developed a new framework called Hyperparameter Transfer Laws to better understand and predict how hyperparameters should be adjusted when scaling neural network architectures. This framework introduces…
-
Specialized design data training challenges reliance on massive pretraining
A new research paper explores the effectiveness of pretraining strategies for machine learning models when applied to specialized design data. The study, using the JONES-19 dataset derived from "The Grammar of Ornament,…
-
New CENDRe method extracts concepts from CNN time-series models
Researchers have developed CENDRe, a novel concept extraction method designed for convolutional neural networks (CNNs) used in time-series classification. This method addresses limitations of existing techniques by anal…
-
New Benchmark Compares Deep Learning Models for Brain Tumor Segmentation
Researchers have developed a unified benchmark to compare deep learning models for 3D brain tumor segmentation from MRI scans. The study evaluates five state-of-the-art models, including CNNs, Transformer-based models, …
-
AI and ML advance cognitive impairment detection in older adults
A new arXiv paper reviews technological advancements in detecting and managing cognitive impairment in older adults, focusing on AI and machine learning applications. The paper synthesizes findings from neurophysiologic…
-
Real-time facial keypoint detection project uses CNNs and OpenCV
This article details a project focused on real-time facial keypoint detection using Convolutional Neural Networks (CNNs) and the OpenCV library. The author, new to computer vision, aimed to gain hands-on experience with…
-
PatchDenoiser offers parameter-efficient denoising for low-dose CT scans
Researchers have developed PatchDenoiser, a novel, parameter-efficient framework for denoising low-dose CT images. This method utilizes multi-scale patch learning and a fusion strategy to effectively suppress noise whil…
-
New lightweight detection transformer enables integer-only inference
Researchers have developed I-LW-DETR, a novel lightweight detection transformer that enables fully integer-only inference. This is a significant advancement for deploying such models on NPUs and microcontrollers, which …
-
CNNs rely on pixel intensity over texture for vascular imaging
A new research paper explores how Convolutional Neural Networks (CNNs) interpret visual information for vascular segmentation in microscopy and fundus imaging. The study found that pixel intensity is more crucial than t…
-
New Directional Influence Function improves data attribution in constrained learning
Researchers have developed a new method called the Directional Influence Function (DIF) to accurately estimate the impact of individual training data points on machine learning models, particularly in constrained learni…
-
New framework uses causal reasoning to detect adversarial AI examples
Researchers have introduced CausAdv, a novel framework designed to detect adversarial examples in deep learning models, particularly Convolutional Neural Networks (CNNs) used in computer vision. This approach leverages …
-
AI in Eye Care: Data, Preprocessing, and Models Evolve Together
A recent review paper details the co-evolution of data, preprocessing, and modeling techniques in the field of AI for color fundus photography (CFP) analysis. The paper highlights the progression of CFP datasets from sm…
-
New research probes CNNs' visual cues for vascular segmentation
A new paper explores how Convolutional Neural Networks (CNNs) identify blood vessels in medical images, specifically in fluorescence microscopy and retinal fundus photography. Researchers found that pixel intensity is m…
-
First benchmark for machine unlearning in Vision Transformers released
A new research paper introduces the first benchmark for machine unlearning (MU) specifically designed for Vision Transformers (VTs). The study addresses the gap in MU research, which has largely focused on Convolutional…
-
Vision Transformer and FFT-ReLU integrated for enhanced image deblurring
Researchers have developed a novel dual-domain architecture for image deblurring that integrates Vision Transformers (ViTs) with a frequency-domain FFT-ReLU module. This approach aims to enhance the recovery of sharp im…
-
New UEP codec slashes AI inference memory costs by up to 62.5%
Researchers have developed a new method for protecting memory in AI inference by analyzing bit-position fault sensitivity in various models and floating-point formats. They found that certain lower-order bits have minim…