ResNet-18
PulseAugur coverage of ResNet-18 — every cluster mentioning ResNet-18 across labs, papers, and developer communities, ranked by signal.
13 day(s) with sentiment data
-
CLIP-based model shows limited gains in context-aware emotion recognition
Researchers have conducted a study on using CLIP-based models for emotion recognition, focusing on how body posture and scene context contribute to understanding emotions in images. The study employed a two-stream model…
-
New optical prior boosts wireless capsule endoscopy classification accuracy
Researchers have developed a novel framework for wireless capsule endoscopy classification that incorporates a physics-informed hemoglobin prior during the training phase. This approach aims to improve the detection of …
-
New research explores feature extraction for acoustic gunshot classification
Researchers have conducted a systematic investigation into feature extraction techniques for acoustic gunshot classification, utilizing a dataset of 23,000 gunshot recordings from 85 firearms. The study benchmarked thre…
-
GrapNet introduces programmable neural graphs, enhancing model editability
Researchers have introduced GrapNet, a novel neural graph substrate designed to bring programmability to fixed-tensor neural networks. This system treats the graph itself as the executable program, allowing for operatio…
-
New HeteRo-Select framework optimizes federated learning by prioritizing data informativeness
Researchers have developed a new framework called HeteRo-Select for federated learning systems that prioritizes data informativeness over link speed for gradient compression. This approach aims to address the issue wher…
-
ANEForge enables direct Python programming of Apple Neural Engine
A new Python package called ANEForge allows developers to directly program the Apple Neural Engine (ANE) without relying on CoreML. This bypass enables more efficient use of the ANE, which is the dedicated neural accele…
-
New framework disentangles curriculum learning factors for data efficiency
Researchers have developed a new framework called Confusion-Aware Transfer Teacher Curriculum Learning to better understand the components of curriculum learning. By disentangling sample difficulty scoring from pacing, …
-
New InstantForget Method Unlearns AI Backdoors Without Retraining
Researchers have developed a new method called InstantForget for removing backdoor triggers from AI models without requiring model retraining. This technique operates at inference time by identifying and resetting anoma…
-
New GRAPE framework boosts neural network adversarial robustness
Researchers have introduced GRAPE, a novel training framework designed to enhance the adversarial robustness of neural networks while maintaining compact model sizes. GRAPE distinguishes itself by treating robust model …
-
New research identifies 'cheating trap' in AI pedestrian recognition
Researchers have identified a significant challenge in pedestrian attribute recognition (PAR) caused by extreme class imbalance in large datasets like PETA and PA-100K. This imbalance leads to a phenomenon termed the 'm…
-
Energy conservation improves modular neural network robustness
Researchers have developed a novel method to improve the robustness of modular neural networks by enforcing energy conservation at module boundaries. This approach ensures that the activation energy, defined as the squa…
-
New pruning method creates sparse neural networks in one training cycle
Researchers have developed a new method for creating sparse neural networks in a single training cycle, a significant improvement over existing techniques that require multiple cycles. This progressive magnitude-based p…
-
Feedback Alignment training method improved with new dimensionality techniques
Researchers have identified a key limitation in Feedback Alignment (FA), a method for training neural networks that bypasses the biological implausibility of backpropagation. They found that FA's error signals have a lo…
-
AI model detects Parkinson's disease using multi-modal speech analysis
Researchers have developed a novel multi-branch deep learning framework designed to improve the detection of Parkinson's disease through speech analysis. This approach utilizes three distinct speech representations: Log…
-
New backdoor attack exploits hardware faults in federated learning
Researchers have developed a new type of backdoor attack against federated learning systems by inducing hardware faults, specifically bit-flips, in model parameters during training. This novel approach, termed "Chain of…
-
New PAND framework enhances VLM knowledge distillation for visual classification
Researchers have developed a new framework called PAND (Prompt-Aware Neighborhood Distillation) to improve the process of transferring knowledge from large Vision-Language Models (VLMs) to smaller, more efficient networ…
-
New SDP framework cuts model training memory use by up to 60%
Researchers have developed a new distributed training framework called Subnetwork Data Parallelism (SDP) to address the high memory demands and communication costs associated with pre-training large neural networks. SDP…
-
Transformer model predicts seizure onset with 98.85% recall
Researchers have developed EEG-FuseFormer, a novel framework utilizing transformer architecture for predicting seizure onset in epilepsy patients. This model integrates features from CNN-LSTM and ResNet-18 networks, ach…
-
New $\ell_p$-norm scheme enhances deep learning optimization
Researchers have introduced a new optimization scheme for deep neural networks that utilizes a dynamic $\ell_p$-norm, moving beyond the limitations of fixed $\ell_2$ and $\ell_\infty$ norms. This novel approach, termed …
-
New research tackles AI's catastrophic forgetting problem
Multiple research papers explore advanced techniques for continual learning, aiming to prevent catastrophic forgetting in AI models. One approach, Experience Blending (EB), uses generated "support boundary data" to enri…