CIFAR-10
PulseAugur coverage of CIFAR-10 — every cluster mentioning CIFAR-10 across labs, papers, and developer communities, ranked by signal.
- instance of ResNet-20 90%
- instance of CIFAR10-DVS: An Event-Stream Dataset for Object Classification 90%
- instance of CIFAR-100 70%
- instance of Fashion-MNIST 70%
- used by ResNet-18 70%
- instance of DagsHub 70%
- instance of The Street View House Numbers Dataset 70%
- used by Tiny-ImageNet 70%
- instance of Tiny-ImageNet 70%
- instance of ResNet-18 70%
- used by The Street View House Numbers Dataset 70%
- used by residual neural network 70%
16 day(s) with sentiment data
-
New Fusion Method Merges Dissimilar Vision Models
Researchers have developed a novel method called Riemannian--Lorentz Parameter Fusion (RLPF) to merge independently trained vision models, even when their architectures differ. This technique addresses the challenges of…
-
New watermarking scheme TwinMark protects AI models from distillation attacks
Researchers have developed TwinMark, a novel watermarking technique designed to protect AI models against distillation attacks. This method uses two complementary linear functionals, one based on feature covariance and …
-
New method enhances deep neural network interpolation robustness
Researchers have introduced Sharp Mode Connectivity (SMC), a new method for optimizing parametric curves in the weight space of deep neural networks. Unlike standard mode connectivity, which only ensures low loss along …
-
Temperon training method achieves SAM quality with reduced cost
Researchers have introduced Temperon, a novel training method designed to achieve the quality of Sharpness-Aware Minimization (SAM) while significantly reducing computational costs. Temperon utilizes a two-phase approac…
-
LePoKet framework enhances robotic vision with learnable knowledge transfer
Researchers have developed LePoKet, a novel framework for knowledge transfer in robotic vision systems. This method optimizes interaction parameters within a block-wise interface, enabling learnable parameter optimizati…
-
Dual Randomized Smoothing enhances neural network robustness
Researchers have introduced Dual Randomized Smoothing (Dual RS), a novel framework designed to enhance the robustness of neural networks against adversarial perturbations. Unlike traditional Randomized Smoothing which u…
-
New pruning method uses Fisher information distances for neural networks
Researchers have introduced a novel parameter pruning technique for neural networks, grounded in differential-geometric distances within model space. This method quantures the minimal distance to a hypersurface where a …
-
New BARGE method tackles imbalanced learning with noisy labels
Researchers have developed a new method called BARGE (Bounded Adjustment with Reliability-Guided Embeddings) to address challenges in imbalanced learning with noisy labels. This single-stage objective combines a bounded…
-
New framework offers tighter confidence regions for importance weights in label shift
Researchers have developed a new framework for estimating importance weights in domain adaptation under label shift, moving away from traditional inversion-based inference to a direct matrix constraint approach. This ne…
-
New method fuses AI detection techniques for healthcare imaging models
Researchers have developed a new method for detecting backdoors in healthcare imaging AI models by fusing spectral signature analysis and activation clustering techniques. This combined approach aims to improve detectio…
-
ZAPS pipeline enhances Neural Architecture Search by combining proxy signals and topology
Researchers have developed ZAPS, a novel four-stage pipeline designed to improve Neural Architecture Search (NAS) by efficiently combining proxy signals with architectural topology. This method addresses the limitations…
-
Sakana AI proposes layer-local training method for 1000-layer networks
Researchers at Sakana AI have developed a novel training method called Augmented Lagrangian Predictive Coding (PC-ALM), which offers a layer-local alternative to traditional backpropagation. This new approach allows for…
-
SakanaAI proposes PC-ALM as backpropagation alternative for deep networks
SakanaAI has introduced Augmented Lagrangian Predictive Coding (PC-ALM), a novel method for training deep neural networks that offers an alternative to traditional backpropagation. PC-ALM utilizes layer-local dynamical …
-
New SDE Splitting Method Boosts Generative AI Efficiency
Researchers have developed a new splitting method for estimating terminal laws in stochastic differential equations (SDEs), particularly relevant for diffusion-based generative AI. This method involves generating a tree…
-
New Model-Aware Schedules Enhance Diffusion and Flow-Matching Generation
Researchers have developed a novel method for constructing diffusion and flow-matching schedules, which are crucial for controlling the mixing of data and noise in generative models. This new approach, termed "model-awa…
-
ZK-Trace paper details certified collusion tracing for GNSS monitoring
A new research paper introduces ZK-Trace, a system designed to trace the source of leaked proprietary classifiers in federated global navigation satellite system (GNSS) monitoring. ZK-Trace combines public identity mark…
-
New Non-Coherent AirFL Protocol Enhances Federated Learning Efficiency
Researchers have developed a novel Non-Coherent Over-the-Air Federated Learning (NCAirFL) protocol designed to overcome the scalability limitations in federated edge learning. This new protocol waives the need for insta…
-
New method enhances decentralized federated distillation with multi-modality knowledge collaboration
This paper introduces a novel decentralized federated distillation method designed for clients with heterogeneous models. The approach leverages shared unlabeled public data for collaboration, where each client evaluate…
-
New framework learns kernels by alignment for multiclass Bayes classification
Researchers have developed a new framework for multiclass Bayes classification that learns kernels through alignment, moving beyond the traditional approach of pre-selecting kernels. This method, termed Collaborative Le…
-
FANS framework optimizes model architectures for heterogeneous federated learning
Researchers have developed FANS (Federated Adaptive Network Search), a new framework designed to optimize model architectures in heterogeneous federated learning environments. This approach utilizes a hypernetwork to le…