DeiT-Tiny
PulseAugur coverage of DeiT-Tiny — every cluster mentioning DeiT-Tiny across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
UC Berkeley researchers develop bandit-based pruning for transformers
Researchers from the University of California, Berkeley have developed a novel method for pruning large transformer models, including those used in vision and language tasks. This technique, framed as a damage-aware mul…
-
Deep learning models for breast cancer detection benchmarked for performance and emissions
A new paper benchmarks seven deep learning models for breast cancer detection, evaluating their performance and environmental impact. The study found that while EfficientNet and ResNet offer strong accuracy, they also p…
-
MDTransformer: Novel photonic accelerator design boosts efficiency
Researchers have developed MDTransformer, a novel hardware-software co-design for photonic transformer accelerators. This system utilizes mode-division optical dataflow and inverse-designed photonic components to perfor…
-
New BMFA method improves Vision Transformer accuracy by addressing underestimation
Researchers have developed a new method called Boundary-Minority Free-Energy Adaptive Screening (BMFA) to address an underestimation failure in Vision Transformers. This failure occurs when spatially small, high-respons…
-
CLEAR-MoE converts frozen Vision Transformers to sparse MoE models
Researchers have developed CLEAR-MoE, a novel post-training method to transform frozen Vision Transformers (ViTs) into sparse Mixture-of-Experts (MoE) models without altering the original backbone weights. This techniqu…
-
New Finetuning Method Adapts DNNs for ReRAM In-Memory Computing
Researchers have developed a new finetuning method to adapt deep neural networks for deployment on ReRAM-based in-memory computing hardware. This approach addresses the challenges of I-V non-linearity and retention erro…
-
New framework evaluates AI driver models on more than just accuracy
Researchers have introduced a new framework for evaluating driver monitoring models, moving beyond simple accuracy metrics. The Human-Centered Benchmarking Framework (HCBF) assesses models on accuracy, explainability, e…
-
New research tackles feature distillation challenges in Vision Transformers
Researchers have identified a key issue in feature distillation for Vision Transformers (ViTs), particularly when compressing models. They discovered that while individual images are compressible, the overall dataset ex…