Imagenette
PulseAugur coverage of Imagenette — every cluster mentioning Imagenette across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
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 method probes neural network loss sharpness for stable learning rates
Researchers have developed a novel method to estimate the local sharpness of a loss function in neural networks, a critical factor for stable gradient steps. By analyzing the step size accepted during Armijo backtrackin…
-
Fusion framework unifies Vision Transformer adaptation for efficiency
Researchers have developed Fusion, a novel framework designed to enhance the efficiency of Vision Transformers (ViTs) by unifying sequential token adaptation techniques. This framework coordinates token merging, early e…
-
LLMs guide neural network generation, improving accuracy via source-model guidance · 2 sources tracked
Researchers have developed a novel protocol for using large language models (LLMs) to improve existing neural networks by guiding the generation process with a stronger, same-family source model. This method aims to dis…
-
CLEAR-MoE converts frozen Vision Transformers to sparse MoE models
Researchers have developed CLEAR-MoE, a novel post-training method to transform frozen Vision Transformers (ViTs) into sparse Mixture-of-Experts (MoE) models without altering the original backbone weights. This techniqu…
-
Dataset Distillation Falls Short Against Coreset Selection in New Study
A new research paper critically evaluates dataset distillation (DD) methods, finding that they often do not outperform simpler coreset selection (CS) strategies, especially on large-scale datasets like ImageNet. The stu…
-
Spin-glass theory applied to AI latent spaces for improved generation and anomaly detection
Researchers have developed a new method to analyze the latent spaces of autoencoders and variational autoencoders by applying spin-glass theory. This approach formalizes a dictionary that allows for the detection of ord…
-
Anomaly detection benchmarks flawed by score-direction instability
A new research paper highlights a critical flaw in how anomaly detection models are evaluated. The study reveals that standard within-dataset class-split evaluation can be unreliable when the anomaly class overlaps with…
-
New FP-MGMs slash training costs and boost generation quality
Researchers have developed Fixed-Point Masked Generative Models (FP-MGMs) to improve the efficiency and quality of masked generative models. This new framework, named CoFRe, utilizes a fixed-point solver and adaptive de…
-
Research explores how sparsity allocation affects neural network recovery after pruning
A new research paper investigates how the allocation of sparsity in neural networks impacts their ability to recover accuracy after pruning, especially when labeled retraining data is unavailable. The study compares dif…
-
Learn&Drop method halves CNN training time by dropping layers
Researchers have developed a novel method called Learn&Drop to accelerate the training of Convolutional Neural Networks (CNNs). This technique dynamically assesses layer parameter changes during training and scales down…
-
RDCNet achieves state-of-the-art image classification with novel dilated convolution
Researchers have introduced RDCNet, a novel architecture designed to improve image classification accuracy. The network integrates a Multi-Branch Random Dilated Convolution module for capturing fine-grained features and…