CIFAR-100
PulseAugur coverage of CIFAR-100 — every cluster mentioning CIFAR-100 across labs, papers, and developer communities, ranked by signal.
- instance of CIFAR10-DVS: An Event-Stream Dataset for Object Classification 90%
- instance of Tiny-ImageNet 70%
- used by residual neural network 70%
- instance of Imagenet 1k 70%
- instance of ResNet-34 70%
- instance of ImageNet-100 70%
- used by CNNS 70%
- used by Deep Neural Networks 70%
- used by VGG-11 70%
- competes with Imagenet 1k 60%
- instance of ResNet-50 60%
- used by Vision Transformers 60%
16 day(s) with sentiment data
-
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 regression method enhances foundation model safety and accuracy
Researchers have developed a new method for black-box assisted regression that aims to improve the reliability of foundation models when used for downstream tasks with limited data. The approach, called the Safe Residua…
-
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…
-
Mamba-FSCIL: Selective State Space Models for Few-Shot Class-Incremental Learning
Researchers have developed Mamba-FSCIL, a novel approach to few-shot class-incremental learning that utilizes Selective State Space Models (SSMs). This method addresses the challenge of balancing static and dynamic arch…
-
New framework improves exemplar-free class-incremental learning
Researchers have introduced the Geometry-Anchored Transport Framework, a novel approach to exemplar-free class-incremental learning (EFCIL). This framework integrates feature transport as an intrinsic training constrain…
-
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 framework probes AI agents' grounded word learning
Researchers have introduced "Lexical Consensus," a new experimental framework designed to study how artificial agents learn and stabilize lexical meanings from grounded experiences. Using frozen DINOv2 visual embeddings…
-
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…
-
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 ToaSt framework boosts Vision Transformer efficiency
Researchers have developed a new framework called ToaSt designed to make Vision Transformers (ViTs) more computationally efficient. ToaSt decouples strategies for different parts of the ViT architecture, applying head-w…
-
Ultra-tiny Vision Transformer designed for mobile deployment
Researchers have developed UtVAA, an ultra-tiny Vision Transformer architecture optimized for mobile and edge devices. This new model incorporates Affix Attention, which combines local feature extraction with linear sel…
-
New IGLU activation function offers improved gradient flow
Researchers have introduced IGLU, a novel parametric activation function for deep neural networks designed to improve gradient flow and optimization stability. Derived from a mixture of GELU gates under a half-normal di…
-
New HiRo Model Achieves High Accuracy with Under 1M Parameters
Researchers have introduced HiRo, a novel image classification model designed for efficiency and performance. HiRo utilizes a combination of shifted-window partitioning and multi-directional hierarchical reservoir compu…
-
VIOLIN enhances Vision Transformers with spatial priors for limited data
Researchers have developed VIOLIN, a novel masked attention mechanism for Vision Transformers (ViTs) that enhances their ability to process images with limited data or smaller model capacities. By encoding spatial struc…
-
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…
-
New Spiking Transformer Achieves State-of-the-Art Efficiency
Researchers have introduced SAFformer, a novel Spiking Transformer architecture designed to improve energy efficiency and performance in visual data processing. By adopting an active predictive filtering paradigm inspir…
-
AI Models Shift Focus to Stability and Adaptability in Real-World Deployments
Recent research presented at CVPR 2026 highlights a shift in AI model development from pure capability expansion to "capability management." This involves ensuring models retain old knowledge while adapting to new data …
-
Emotional Regulation Framework Boosts Deep Learning Image Classification
Researchers have introduced a novel framework called Emotional Regulation to enhance deep learning models for image classification. This approach models artificial subjective experience by pre-training models on affecti…
-
HydraCIL offers efficient class-incremental learning for edge devices
Researchers have introduced HydraCIL, a novel approach to class-incremental learning designed for resource-constrained environments like embedded systems. This method decouples feature extraction from classifier trainin…