GraphLeap decouples per-layer graph construction from feature updates in Vision GNNs by using previous-layer features for the current graph, enabling pipelined FPGA acceleration with up to 95.7× CPU speedup after fine-tuning.
Do vision transformers see like convolutional neural networks?
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3years
2026 3roles
background 1polarities
background 1representative citing papers
Vision encoders alter spectral accessibility non-monotonically across depth with architecture-specific effects from projections and pooling, quantified via a new residual loss against random baselines.
LEAP is an adaptive layer-skipping curriculum for ViT feature distillation that reports accuracy gains on ImageNet and retrieval tasks plus training compute savings.
citing papers explorer
-
GraphLeap: Decoupling Graph Construction and Convolution for Vision GNN Acceleration on FPGA
GraphLeap decouples per-layer graph construction from feature updates in Vision GNNs by using previous-layer features for the current graph, enabling pipelined FPGA acceleration with up to 95.7× CPU speedup after fine-tuning.
-
Beyond Compression: Quantifying Spectral Accessibility in Vision Representations
Vision encoders alter spectral accessibility non-monotonically across depth with architecture-specific effects from projections and pooling, quantified via a new residual loss against random baselines.
-
LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation
LEAP is an adaptive layer-skipping curriculum for ViT feature distillation that reports accuracy gains on ImageNet and retrieval tasks plus training compute savings.