ImageNet
PulseAugur coverage of ImageNet — every cluster mentioning ImageNet across labs, papers, and developer communities, ranked by signal.
- used by Normalizing Flows 80%
- used by CIFAR-10 70%
- instance of arXiv 70%
- used by arXiv 70%
- used by Diffusion Models 70%
- instance of CIFAR-100 70%
- instance of Diffusion Models 70%
- used by CIFAR-100 70%
- instance of Cifar 70%
- used by MNIST database 70%
- used by vision transformer 70%
- instance of ViT-B/16 70%
24 day(s) with sentiment data
-
New quantum autoencoder framework learns compact data embeddings
Researchers have developed a variational autoencoder framework to create task-specific quantum embeddings for classical data, extending the utility of autoencoders to quantum machine learning. This method allows high-di…
-
New Geometric Gradient Rectification improves open-set learning
Researchers have introduced Geometric Gradient Rectification (GGR), a novel framework designed to improve open-set semi-supervised learning. GGR addresses the limitations of existing methods by focusing on gradient-leve…
-
New training method enhances visual model generalization and robustness
Researchers have developed a new training method called Subset-Selected Counterfactual Augmentation (SS-CA) to improve the causal reasoning of visual models. This technique uses attribution methods to identify critical …
-
AI data quality metrics misaligned with human perception and task performance
A new paper published on arXiv explores the disconnect between automated data quality metrics and their actual utility for deep learning models, particularly in Earth observation. The research highlights that common met…
-
MIMFlow integrates Masked Image Modeling with Normalizing Flows for advanced image generation
Researchers have introduced MIMFlow, a novel framework that integrates Masked Image Modeling (MIM) with Normalizing Flows (NFs) for enhanced end-to-end image generation. This approach uses a VAE encoder to extract seman…
-
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…
-
Transformer vs CNNs: Colorectal Histology Classification Benchmark
A new study published on arXiv compares the performance of convolutional neural networks (CNNs), transformer-based models, and hybrid architectures for classifying colorectal histology images. The research evaluated twe…
-
AI model segments food images to identify ingredients for nutrition awareness
Researchers have developed a novel approach to food image segmentation, focusing on identifying individual ingredients within dishes to enhance nutrition awareness. The study fine-tuned two SegFormer variants, SegFormer…
-
Research paper analyzes image transformation effects on latent space embeddings
A new research paper explores how image transformations affect the latent space representations used in histopathology classification. The study found that while embeddings of transformed images are closer to original e…
-
SeFi-Image model uses semantic-first diffusion to cut training compute by 80%
Researchers have introduced SeFi-Image, a novel text-to-image foundation model that utilizes a semantic-first diffusion approach to significantly reduce training compute requirements. The model, available in 1B, 2B, and…
-
DiffusionBench benchmark and NanoGen framework challenge image generation evaluation
Researchers have introduced DiffusionBench, a new benchmark designed to holistically evaluate diffusion transformers (DiTs) used in image generation. The benchmark highlights that current evaluation methods, primarily f…
-
New framework enables linear merging of billion-parameter transformers
Researchers have developed a new framework for merging large pretrained transformers, specifically those with billions of parameters. This method addresses limitations of previous approaches by optimizing interpolation …
-
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…
-
MonoSoup method achieves strong ID-OOD balance with single checkpoint
Researchers have developed MonoSoup, a novel post-hoc method that enhances the balance between in-distribution accuracy and out-of-distribution robustness in large pre-trained models using only a single checkpoint. This…
-
Meta Flow Maps framework streamlines generative model control
Researchers have introduced Meta Flow Maps (MFMs), a new framework designed to make controlling generative models more computationally efficient. MFMs extend consistency models and flow maps into the stochastic regime, …
-
Hybrid ANN-SNN Pipeline Achieves 99% Accuracy on ImageNet
Researchers have developed a novel hybrid pipeline that combines Artificial Neural Networks (ANNs) with Spiking Neural Networks (SNNs) to enhance performance. This approach utilizes embeddings from a pretrained Efficien…
-
Kaiming He's undergraduate team unveils MiniT2I text-to-image model with 258M parameters
Researchers, including a team led by Kaiming He and composed primarily of undergraduate students, have introduced MiniT2I, a novel text-to-image generation model. This model achieves competitive results with significant…
-
New research explores merging large transformers and improving looped model stability
Two new research papers explore novel techniques for enhancing the capabilities and stability of large transformer models. The first paper introduces a scalable framework for linear mode connectivity (LMC) that allows f…
-
New Generalized KL Divergence Loss Achieves State-of-the-Art Robustness
Researchers have introduced the Generalized Kullback-Leibler (GKL) Divergence loss, an enhancement to existing KL Divergence loss methods. This new loss function addresses limitations in scenarios like knowledge distill…
-
New methods enhance AI model adaptation robustness against adversarial attacks and data shifts · 6 sources tracked
Researchers have developed new methods to improve the robustness of test-time adaptation (TTA) for machine learning models, particularly in scenarios with adversarial attacks and evolving data distributions. One approac…