No AI summary available for this article.
Why It Matters
Large-kernel Convolutional Neural Networks (CNNs) deliver remarkable performance in vision tasks by significantly expanding receptive fields, yet their quadratic parameter growth critically impedes storage-efficient edge deployment.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Large-kernel Convolutional Neural Networks (CNNs) deliver remarkable performance in vision tasks by significantly expanding receptive fields, yet their quadratic parameter growth critically impedes storage-efficient edge deployment. While existing efficient architectures adopt parameter-efficient depthwise separable convolution backbones that leverage techniques like low-rank approximation and weight sharing to compress depthwise convolutions, we identify a critical oversight: pointwise convolutions dominate parameter volume (>87% in models like RepLKNet-31B) and constitute the primary deploym...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2608.26069v1 · Indexed 4 days ago