Swin-Tiny
PulseAugur coverage of Swin-Tiny — every cluster mentioning Swin-Tiny across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New calibration method boosts AI reliability in imbalanced medical datasets
Researchers have developed a new method for improving the reliability of classification models, particularly in scenarios with imbalanced data, such as cervical cytology. The study focused on the Mendeley LBC dataset, u…
-
Adaptive Hebbian Routing enhances few-shot Vision Transformer performance
Researchers have developed an Adaptive Hebbian Routing method for few-shot Vision Transformers to improve image recognition from limited data. This approach uses a lightweight MLP router to dynamically control Hebbian m…
-
New MoE framework integrates diverse architectures for improved plant disease classification
Researchers have developed a novel adaptive soft Mixture-of-Experts (MoE) framework designed to improve plant leaf disease classification. This framework integrates three distinct architectures—EfficientNet-B0, DenseNet…
-
New HumP-KD framework efficiently distills fire classification models
Researchers have developed HumP-KD, a novel framework for efficient fire classification using knowledge distillation. This method distills knowledge from larger transformer models like Swin-Tiny and ViT-Base into a smal…
-
AI distills multiplexed microscopy data for single-channel tissue segmentation
Researchers have developed a cross-modal knowledge distillation framework to improve single-channel tissue segmentation in microscopy. This method transfers knowledge from a foundation model trained on multiplexed image…
-
New audit protocol assesses AI explanation faithfulness in visual inspection
Researchers have developed a new method for auditing the explanations generated by deep learning models used in industrial visual inspection. This "architecture-aware" protocol assesses how faithfully an explanation met…
-
Hebbian Fast Weights enhance Vision Transformers for few-shot character recognition
Researchers have developed a new approach to few-shot character recognition by integrating Hebbian Fast-Weight (HFW) modules into Vision Transformer architectures. This method aims to mimic biological neural systems' ab…