CNNS
PulseAugur coverage of CNNS — every cluster mentioning CNNS across labs, papers, and developer communities, ranked by signal.
- instance of alphaXiv 90%
- instance of convolutional neural network 90%
- instance of ScienceCast 90%
- used by Vits 90%
- used by convolutional neural network 80%
- used by Vision Transformers 70%
- uses Vision Transformers 70%
- used by DagsHub 70%
- used by alphaXiv 70%
- used by Gotit.pub 70%
- instance of DagsHub 70%
- instance of Recurrent Neural Networks 70%
8 day(s) with sentiment data
-
Color's role in object recognition under occlusion studied
A new research paper explores how color impacts object recognition in both humans and computer vision systems when objects are partially obscured. The study found that while camouflage occlusions negatively affect human…
-
TrustMix method enhances pretrained models against distribution shifts
Researchers have introduced TrustMix, a novel post-hoc method designed to improve the robustness of pretrained models when faced with distribution shifts. This technique makes a model's extrapolative behavior explicit a…
-
Saliency maps in mammography classifiers show bias against dense breasts
A new research paper published on arXiv investigates the fairness of saliency maps in mammography classifiers, specifically focusing on dense breasts where cancers can be more difficult to detect. The study found that s…
-
Rectified flows show promise for CT denoising without clean targets
Researchers have explored the use of unconditional rectified flows as a method for denoising low-dose CT scans without requiring clean training targets. Their findings suggest that a single step of the flow is optimal f…
-
ConvNeXt Explained: CNNs Adopt Vision Transformer Techniques
This article delves into the ConvNeXt architecture, explaining how Convolutional Neural Networks (CNNs) have incorporated elements from Vision Transformers. It explores the design choices made in ConvNeXt and contrasts …
-
Survey details Vision Transformer compression for edge devices
A new survey paper published on arXiv details strategies for compressing and accelerating Vision Transformers (ViTs) for deployment on edge devices. The paper systematically reviews various model compression techniques …
-
Rotation-equivariant deep learning improves brain age prediction
Researchers have developed a novel framework for predicting brain age using diffusion MRI data, which captures white matter fiber orientation distributions. This approach utilizes a rotation-equivariant Convolutional Ne…
-
New QUAN framework enhances image classification and object detection
Researchers have developed Quaternion Approximate Networks (QUAN), a novel deep learning framework that uses quaternion algebra for rotation-equivariant image classification and object detection. QUAN approximates quate…
-
New method aligns neural network weights, reducing barriers in NeRF models
Researchers have developed a new method called Progressive Permutation Alignment with Temperature-Controlled Spectral Sharpening to address the challenge of permutation symmetry in implicit neural representations (INRs)…
-
New spatio-temporal attack enhances adversarial threats to cognitive radars
Researchers have developed a new method called Segmented Spatio-Temporal Attack (SSTA) to improve the effectiveness of adversarial attacks against cognitive radars. SSTA addresses limitations in existing attacks by enha…
-
VeilNN framework enhances edge neural network security against adversarial attacks
Researchers have developed VeilNN, a new defense framework designed to protect neural networks deployed on edge devices from cross-node adversarial attacks. This framework introduces controlled diversity in models throu…
-
Deep learning system detects cow labor contractions with 95% accuracy
Researchers have developed a computer vision system using deep learning to automatically detect labor contractions in dairy cattle. The system, which utilizes Convolutional Neural Networks (CNNs) and Vision Transformers…
-
New methods enhance adversarial attack transferability against MLLMs and vision models
Researchers have developed new methods to improve the transferability of adversarial attacks against multimodal large language models (MLLMs) and vision-language models. The first approach, IAU-FOA, aligns adversarial a…
-
New Graph Metanetworks Enable Cross-Architecture Model Transformations
Researchers have developed Graph Metanetworks (GMNs) to operate directly on the parameters of neural networks, enabling tasks like predicting model properties and transforming trained models. The CrossGMN model specific…
-
New framework unifies 55 hyperspectral image models across six paradigms
A new technical report introduces "Hyperspectral Image Models," a framework designed to standardize and unify the development of deep learning models for hyperspectral remote sensing. The framework integrates 55 models …
-
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…