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
-
New dataset and models advance sign language handshape recognition
Researchers have developed a new dataset and baseline models for fine-grained isolated handshape recognition in sign language, utilizing the HamNoSys notation system. The dataset comprises 144,000 RGB images from 15 par…
-
New MAGIC-SSCIL framework improves semi-supervised incremental learning
Researchers have introduced MAGIC-SSCIL, a novel framework designed to address the significant challenge of Semi-supervised Class Incremental Learning (SSCIL) in neural networks, particularly in scenarios where past dat…
-
Perforated AI enhances ResNet-18 to match ResNet-34 performance
Perforated AI has developed a technique to enhance the performance of the ResNet-18 model, bringing its accuracy on par with the larger ResNet-34. This method, inspired by biological processes, achieves improved results…
-
New research explores advanced federated learning techniques · 10 sources tracked
Multiple research papers published on arXiv in August 2026 introduce novel approaches to enhance federated learning (FL) and decentralized FL. These methods address challenges such as modality missingness in multimodal …
-
New analysis quantifies SAM's bias toward flat minima
Researchers have analyzed the implicit bias of Sharpness-Aware Minimization (SAM) in improving model generalization. Their linear stability analysis reveals a quantitative relationship between SAM's perturbation radius …
-
Shape-based AI improves glioma grading accuracy
Researchers have developed a novel shape-based approach for glioma grading using tumor contours, outperforming traditional pixel-based methods. This method, which aligns closed contours and separates global deformation …
-
New DECAF method enhances machine unlearning by disrupting data clusters
Researchers have introduced DECAF, a novel post-hoc machine unlearning method designed to enhance privacy and adaptive deployment by specifically targeting and disrupting residual feature-space structures associated wit…
-
New DECAF method enhances machine unlearning against clustering attacks
Researchers have developed DECAF (DE-Clustering for Adaptive Forgetting), a novel post-hoc machine unlearning method designed to prevent data recovery through clustering attacks. This method operates solely on the "forg…
-
Machine unlearning effectiveness questioned by new research
A new research paper challenges the effectiveness of saliency-based weight selection in machine unlearning. The study found that gradient concentration in the final network layers, rather than the specific weights chose…
-
New research tackles federated fine-tuning with spectral control and low-rank methods · 2 sources tracked
Two new research papers propose novel methods for federated parameter-efficient fine-tuning (PEFT) to address communication bottlenecks and improve model performance on decentralized data. The first paper introduces TRI…
-
TinyGLASS enables real-time in-sensor anomaly detection on edge devices
Researchers have developed TinyGLASS, a lightweight adaptation of the GLASS framework for real-time, self-supervised anomaly detection on resource-constrained edge devices. This new architecture utilizes a compact ResNe…
-
New Orthogonal Gradient Method Explores Noisy-Label Memorization in Neural Networks
A new research paper introduces OrthoGrad, a method that modifies the optimizer's update by removing the component of each weight gradient parallel to the current weight vector. This geometric intervention was tested on…
-
New method enhances deep neural network fault tolerance using Center of Gravity
Researchers have developed a novel Center of Gravity (CoG) guided weight correction method to enhance the fault tolerance of deep neural networks (DNNs) used in safety-critical applications. This technique restores corr…
-
A*-Inspired Batch Selection speeds up CNN training
Researchers have developed a new method called A*-Inspired Batch Selection (A*-BS) to improve the efficiency of training convolutional neural networks (CNNs). This model-agnostic strategy treats mini-batch scheduling as…
-
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 SGD momentum schedule accelerates training, debunks layer selection claims
A new research paper proposes a momentum schedule for SGD that mimics critical damping, achieving a 2.34x speedup in reaching 90% test accuracy on ResNet-18/CIFAR-10 compared to a constant momentum of 0.9. While this me…
-
Synthetic data improves canola branch counting, study finds · arXiv research
Researchers have investigated the impact of synthetic data and label distribution on canola branch counting using a ResNet-18 model. Their findings indicate that incorporating synthetic data can improve performance, wit…
-
New SLORR framework enhances neural network compressibility with minimal overhead
Researchers have introduced SLORR, a novel framework designed to improve the compressibility of neural networks without sacrificing accuracy. This method offers a simple, stateless, and architecture-preserving approach …
-
ML approach classifies and generates structured light in turbulence · arXiv research
Researchers have developed a machine learning approach to classify and generate structured light beams that have propagated through turbulent media. The study utilizes numerical simulations to create speckle patterns an…
-
New framework enhances fault tolerance in FPGA-based CNN accelerators
Researchers have developed ProWAFT, a novel fault-tolerance framework designed for CNN accelerators implemented on SRAM-based FPGAs. This system addresses the challenge of transient faults that can compromise reliabilit…