ResNet50
PulseAugur coverage of ResNet50 — every cluster mentioning ResNet50 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Diffusion augmentation boosts Bangla character recognition accuracy
Researchers have developed a confidence-guided diffusion augmentation method to improve the recognition of handwritten Bangla compound characters. This approach uses diffusion models to generate high-quality synthetic c…
-
New OUIDecay method adapts CNN regularization layer-by-layer
Researchers have introduced OUIDecay, a novel adaptive weight decay method for convolutional neural networks. This technique dynamically adjusts regularization strength for each layer based on online activation patterns…
-
LC4-DViT uses generative AI and transformers for accurate land-cover mapping
Researchers have developed LC4-DViT, a novel framework for land-cover classification using a deformable Vision Transformer. This approach combines generative data creation with a deformation-aware backbone to improve ac…
-
New DEEP-GAP study compares NVIDIA T4 and L4 GPU inference performance
A new research paper introduces DEEP-GAP, a methodology for evaluating GPU inference performance. The study systematically compares the NVIDIA T4 and L4 GPUs using various deep learning models and precision modes. Resul…
-
AI models show strong breast density prediction from ultrasounds, generalize well
Researchers externally validated three deep learning models—DenseNet121, ViT-B/32, and ResNet50—for predicting breast density from ultrasound images. The models demonstrated strong performance, particularly in extremely…
-
Researchers develop new unsupervised domain adaptation frameworks for image classification and segmentation
Researchers have developed new unsupervised domain adaptation (UDA) frameworks to address the challenge of applying AI models trained on one dataset to different, unlabeled datasets. One approach utilizes dual foundatio…
-
From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models
Researchers have introduced a new framework for interpreting vision models, unifying local, global, and mechanistic analysis around instance-specific Effective Receptive Fields (iERFs). This approach uses pointwise feat…
-
New architecture tackles rare animal image classification with adaptive DCT and hybrid backbones
A research paper introduces a novel deep-learning architecture designed to improve image classification accuracy for rare animal species, where data is inherently scarce. The proposed hybrid framework combines an adapti…
-
Researchers combine DPUs and GPUs for faster neural network inference
Researchers have developed a novel method for accelerating neural network inference by splitting Convolutional Neural Network (CNN) computations between Deep Learning Processing Units (DPUs) and Graphics Processing Unit…
-
HFS-TriNet network improves prostate cancer classification from TRUS videos
Researchers have developed HFS-TriNet, a novel network designed to improve prostate cancer classification from transrectal ultrasound (TRUS) videos. This method addresses challenges in TRUS video analysis, such as redun…