CIFAR-10
PulseAugur coverage of CIFAR-10 — every cluster mentioning CIFAR-10 across labs, papers, and developer communities, ranked by signal.
- instance of CIFAR10-DVS: An Event-Stream Dataset for Object Classification 90%
- instance of CIFAR-100 70%
- instance of ResNet-18 70%
- used by residual neural network 70%
- used by federated learning 70%
- instance of Imagenet 1k 70%
- instance of residual neural network 70%
- used by Deep Neural Networks 70%
- instance of Fashion-MNIST 70%
- used by ImageNet-100 70%
- used by SGD 70%
- instance of ImageNet-100 70%
22 day(s) with sentiment data
-
New GAN model advances solvable high-dimensional training dynamics · 2 sources tracked
Researchers have developed a solvable high-dimensional model for generative adversarial network (GAN) training, extending prior analyses to include structured latent covariance. This new model accounts for class-depende…
-
New research explores privacy techniques for computer vision systems
Two new research papers explore methods for enhancing privacy in computer vision systems. The first paper, "PrivacyBench," introduces a framework to evaluate combinations of privacy techniques, revealing that combining …
-
PERTINENCE method optimizes DNN efficiency by dynamically selecting models
Researchers have developed PERTINENCE, a novel runtime method designed to optimize the computational efficiency of deep neural networks (DNNs). This technique dynamically selects the most appropriate model from a pre-tr…
-
New TL++ framework enhances accuracy and privacy in distributed AI training
Researchers have developed TL++, a novel framework for distributed intelligent systems that enhances both accuracy and privacy in training across data silos. This system addresses limitations of traditional federated an…
-
New IF-Beta framework streamlines knowledge distillation with data pruning
Researchers have developed IF-Beta, a novel framework for efficient knowledge distillation that utilizes learnable data pruning. This method combines influence functions with a Beta distribution-parameterized sampling p…
-
New 'Pre-Warm' method improves CNN initialization accuracy
Researchers have developed a novel method called Pre-Warm for initializing convolutional neural networks. This technique conditions the initialization of the first convolutional layer using data from a single training b…
-
New SKANs offer parameter-efficient alternative to KANs
Researchers have introduced Structural Kolmogorov-Arnold Convolutions (SKANs) as a more parameter-efficient alternative to existing Convolutional Kolmogorov-Arnold Networks (KANs). The new approach repositions learnable…
-
New TooBad framework enables stealthy backdoor attacks on diffusion models
Researchers have developed a new backdoor attack framework called TooBad, specifically designed for diffusion models. This framework significantly enhances the performance of backdoor attacks by employing a novel trigge…
-
New framework PeLAP-A prunes latent diffusion models, revealing 'sparsity collapse'
Researchers have introduced PeLAP-A, a framework designed to make latent diffusion models more lightweight by adaptively pruning unimportant channels in the latent space. This method uses a multilayer perceptron to pred…
-
New training method boosts diffusion model robustness against data contamination
Researchers have developed a new training method for diffusion models that enhances their robustness against data contamination. By replacing the standard Mean Squared Error (MSE) denoising loss with a transformation de…
-
AI Transfer Attacks: "Scissors Effect" Reveals Diversity Hinders Robust Models
Researchers have identified a phenomenon called the "Scissors Effect" in transfer attacks against AI models. This effect demonstrates that while random resizing and padding (Input Diversity or DI) generally improve atta…
-
New concolic testing method enhances Transformer robustness analysis
Researchers have developed a new concolic testing method for Transformer classifiers that uses SHAP estimates to prioritize path predicates based on their influence on the model's predictions. This approach, implemented…
-
New theory grounds deep learning flatness in Riemannian geometry
Researchers have developed a new theoretical framework for understanding the generalization capabilities of deep learning models by grounding the concept of flatness in Riemannian geometry. This approach utilizes the Fi…
-
New Veriphi System Integrates Attacks and Certification for Neural Network Verification
Researchers have developed Veriphi, a new system for verifying neural networks that integrates fast adversarial attacks with formal bound certification. Experiments on MNIST and CIFAR-10 datasets revealed that the effec…
-
New PAC-Bayes Derandomization Method for Smooth Loss Functions
Researchers have developed a new method for derandomizing PAC-Bayes generalization bounds, specifically for smooth loss functions. This approach aims to create high-probability bounds for deterministic predictors by lev…
-
GrapNet introduces programmable neural graphs, enhancing model editability
Researchers have introduced GrapNet, a novel neural graph substrate designed to bring programmability to fixed-tensor neural networks. This system treats the graph itself as the executable program, allowing for operatio…
-
New HeteRo-Select framework optimizes federated learning by prioritizing data informativeness
Researchers have developed a new framework called HeteRo-Select for federated learning systems that prioritizes data informativeness over link speed for gradient compression. This approach aims to address the issue wher…
-
TrustErase enables auditable, instant machine unlearning without original data
Researchers have developed TrustErase, a novel machine unlearning framework that allows for instant and auditable data removal without needing access to the original training data. This method embeds data representation…
-
Researchers analyze neural network image classification on CIFAR-10 dataset
A research paper details an experimental analysis of neural network-based image classification using the CIFAR-10 dataset. The study covers the entire learning pipeline, from data preprocessing to model training and val…
-
Volterra Generative Models Introduce Path-Dependent Noise for Enhanced AI Generation
Researchers have introduced Volterra generative models, a new framework for continuous-time score-based generative models. Unlike traditional models that use memoryless Brownian perturbations, Volterra models incorporat…