CNNS
PulseAugur coverage of CNNS — every cluster mentioning CNNS across labs, papers, and developer communities, ranked by signal.
- instance of convolutional neural network 95%
- used by deep learning 90%
- instance of Vits 90%
- used by Vision Transformers 70%
- competes with Vision Transformers 70%
- used by convolutional neural network 70%
- instance of alphaXiv 70%
- instance of DagsHub 70%
- instance of Recurrent Neural Networks 70%
- uses Vision Transformers 70%
- used by alphaXiv 70%
- used by DagsHub 70%
9 day(s) with sentiment data
-
evMLP: New event-driven MLP architecture for efficient vision processing
Researchers have introduced evMLP, a novel all-MLP architecture designed for vision tasks, particularly video processing. This architecture leverages an event-driven mechanism that processes only changed regions between…
-
New checksum method enhances CNN fault detection on edge devices
Researchers have developed a new lightweight fault-detection technique called Carry-Through Checksum for convolutional neural networks (CNNs) used in edge applications. This method embeds filters into convolutional laye…
-
Vision backbones compared for robotic tree segmentation and depth estimation
A new research paper explores the impact of different vision backbone architectures on joint tree segmentation and stereo depth estimation for robotic applications. The study found that convolutional and hybrid models o…
-
New framework optimizes mobile AI inference latency
Researchers have developed a new scheduling framework for mobile heterogeneous inference, combining inter-operator and intra-operator parallelism. This approach aims to reduce inference latency for tasks represented by …
-
New SPICE framework simplifies polysemanticity analysis in vision models
Researchers have developed SPICE, a novel framework designed to simplify the analysis of polysemanticity in deep vision architectures. This new method offers a generalizable approach that is not tied to specific model a…
-
Few-shot learning for NIDS dominated by meta-learning and CNNs, study finds
A recent arXiv preprint reviewed 21 studies from 2022 to 2026 on few-shot learning approaches for Network Intrusion Detection Systems (NIDS). The survey found that meta-learning and Convolutional Neural Networks (CNNs) …
-
Elastoformer framework enables dynamic adaptation in neural networks
Researchers have introduced Elastoformer, a novel framework designed to make deep neural networks more adaptable to dynamic conditions on edge devices. Unlike existing methods that require multiple models for varying co…
-
AI models for brain MRI match anatomical feature performance
Researchers have conducted a comprehensive evaluation of feature extraction methods for AI models used in structural brain MRI analysis. Their study, which utilized 18 public datasets and approximately 80,000 participan…
-
AI's next frontier: Mamba, JEPA, and Diffusion Models poised to replace transformers
The AI landscape is experiencing a cyclical shift, with transformers, dominant since 2017, potentially being replaced by newer architectures like state space models (Mamba) and Joint Embedding Predictive Architectures (…
-
AI research reveals distillation bottleneck, label-aware methods improve performance
Researchers have identified a significant geometric bottleneck in knowledge distillation between Vision Transformers and smaller CNNs. Standard cosine distillation causes the learned representations to collapse to a low…
-
Foundation models show no consistent advantage over CNNs for eye disease detection
A new research paper evaluates the effectiveness of foundation models (FMs) for detecting diabetic macular edema (DME) from fundus images. The study found that while FMs like RETFound and FLAIR were tested, they did not…
-
New TRACE framework enhances robot decision auditability
A new decision framework called TRACE has been proposed to enhance the auditability of autonomous robots powered by deep learning. This framework ensures that every decision made by a robot can be traced back to the sen…
-
New framework models real-world image noise using normalizing flows
Researchers have developed a new normalizing flows (NF) framework to model real-world image noise more effectively. Unlike previous methods that rely on camera metadata even during the sampling phase, this new framework…
-
New benchmark evaluates AI for Earth observation change detection
A new benchmark has been developed to evaluate AI methods for change detection in Earth observation, addressing inconsistencies in current research. This benchmark standardizes evaluation protocols and considers both pr…
-
Ampere system boosts split federated learning efficiency and accuracy
Researchers have introduced Ampere, a novel system designed to enhance the efficiency and accuracy of split federated learning (SFL). Ampere addresses the limitations of traditional SFL, which often suffers from high co…
-
New Graph-Based AI Learns ECG Patterns for Disease Diagnosis
Researchers have developed a novel graph-based pseudo-multimodal contrastive learning framework, named Graph-CMMC, to improve the analysis of 12-lead electrocardiogram (ECG) data. This method addresses limitations in ex…
-
New No-Code Tool Simplifies AI for Structural Defect Detection
Researchers have developed YOLOEZ, an open-source, GUI-based tool designed to simplify the application of YOLO models for automated structural defect detection. This no-code workflow integrates data labeling, model trai…
-
New M-Fibration Theory Offers Framework for Neural Network Compression
A new theoretical framework called M-Fibration Theory has been introduced, extending the concept of graph fibrations to handle weighted graphs and algebraic structures. This theory provides a robust mathematical foundat…
-
GradAttn enhances CNNs with attention-modulated gradient flow
Researchers have introduced GradAttn, a novel approach to enhance deep convolutional neural networks (CNNs) by replacing fixed residual connections with attention-controlled pathways. This method dynamically weights fea…
-
New Corpus and Transformer Model Detect Metaphors in Hindi Legal Texts
Researchers have developed a new method for detecting metaphors in Hindi legal documents, a task previously unaddressed due to a lack of annotated data for low-resource languages. They created the Hindi Legal Metaphor C…