Tiny-ImageNet
PulseAugur coverage of Tiny-ImageNet — every cluster mentioning Tiny-ImageNet across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
New deep learning model adheres to biological neuron constraints
Researchers have developed a new biologically plausible learning model for deep neural networks that adheres to Dale's constraint, meaning neurons are either excitatory or inhibitory, not both, and synapses maintain a f…
-
New DFCS method boosts backdoor attack efficiency by 4.60% · 2 sources tracked
Researchers have developed a new method called Distributional Feature Coverage Sample Selection (DFCS) to improve the efficiency of backdoor attacks on machine learning models. This training-free, trigger-agnostic appro…
-
New Influence Matching method advances dataset distillation accuracy
Researchers have developed a new method called Influence Matching (Inf-Match) for dataset distillation, which focuses on aligning the final outcomes of model training rather than intermediate processes. This approach us…
-
New antidistillation sampling protects classification models from knowledge distillation
Researchers have developed ADS-C, a novel antidistillation sampling technique designed to protect classification models from knowledge distillation attacks. Unlike previous methods, ADS-C perturbs the model's output dis…
-
Influence Matching advances dataset distillation by aligning training outcomes
Researchers have introduced Influence Matching (Inf-Match), a novel approach to dataset distillation that focuses on aligning the final training outcomes rather than intermediate processes. This method utilizes a differ…
-
Withdrawn paper links Vision Transformer sparsity to data complexity
A recently withdrawn arXiv paper explored the phenomenon of "representational sparsity" in Vision Transformers (ViTs). The research, led by Kanishk Awadhiya, proposed that the observed "U-shaped" entropy profile in ViTs…
-
New Weight Feedback Method Enhances Local Updates in Deep Networks
Researchers have developed a new method called Weight Feedback with Activation-based Predictive Coding (WF-Act-PC) that allows for more localized weight updates in deep neural networks. This approach aims to overcome th…
-
New method RepTran repairs Transformer models with 74.7% success rate
Researchers have developed RepTran, a novel search-based method specifically designed to repair Transformer models, a critical component in modern AI-enabled software. This method focuses on optimizing the feed-forward …
-
New ETBQ method boosts low-bit neural network quantization accuracy
Researchers have developed a new method called Efficient Tuning Before Quantization (ETBQ) to improve the accuracy of low-bit post-training quantization (PTQ) for deep neural networks. This technique involves a pre-cond…
-
New LiST method enhances neural network accuracy, robustness, and calibration
Researchers have introduced Lipschitz Scaling Training (LiST), a new method designed to simultaneously improve the accuracy, robustness, and calibration of neural networks. LiST establishes a theoretical and empirical l…
-
New C-GCD Method Uses Virtual Categories for Improved Unlabeled Data Learning · 2 sources tracked
Researchers have developed a new method for Continual Generalized Category Discovery (C-GCD) called Virtual Category-Guided Continual Generalized Category Discovery. This approach adapts Virtual Category Learning (VCL) …
-
New FLAT method reveals hidden backdoor failures in federated learning
Researchers have developed a new method called FLAT to better detect hidden backdoor failures in horizontal federated learning (HFL) models. Traditional audits often use simplified metrics that can mask a critical vulne…
-
Lightweight CNNs benchmarked for accuracy and efficiency
A new study published on arXiv provides a reproducible benchmark for lightweight Convolutional Neural Networks (CNNs), comparing seven established architectures across CIFAR-10, CIFAR-100, and Tiny ImageNet datasets. Th…
-
New AEGIS Framework Enhances Adversarial Detection in Vision Sensors
Researchers have developed AEGIS, a novel framework designed to enhance the robustness of adversarial detection in vision sensor networks. This system integrates a SemantiGAN module for semantic discrimination of incons…
-
New TaFD Framework Boosts Adversarial Robustness in Deep Learning
Researchers have developed a novel defense framework called Threat-Aware Frequency Decoupling (TaFD) to improve adversarial robustness in deep learning models. TaFD addresses the challenge of heterogeneous attacks, such…
-
New methods advance personalized federated learning and unlearning
Researchers have developed several new methods to enhance personalized federated learning (PFL), a technique that allows AI models to learn from distributed data while maintaining client-specific adaptations. CLoVE, for…
-
Forward-only CNNs achieve new state-of-the-art with learnable channel assignment
Researchers have developed a new forward-only learning algorithm for convolutional neural networks (CNNs) that improves upon existing methods. This approach introduces a learnable mechanism for assigning channels to cla…
-
New defense system shields neural networks from parameter attacks
Researchers have developed ParDef, a novel defense mechanism designed to protect deep neural networks from persistent parameter attacks. This system integrates keyed channel reparameterization, QC-LDPC quantization for …
-
New local learning methods match self-supervised backpropagation
Researchers have developed new local self-supervised learning (SSL) algorithms that can approximate the performance of global backpropagation-based SSL in deep neural networks. These novel algorithms, particularly varia…
-
New RRISE method drastically cuts cost for certified AI robustness
Researchers have developed RRISE, a novel framework for robust radius inference that significantly speeds up the process of certifying $\ell_2$ classification robustness. By training a learned surrogate model, RRISE rep…