E-ConvNeXt combines CSPNet, batch-normalized ConvNeXt blocks, a stepped stem, and ESE attention to reach 78.3-81.9% ImageNet top-1 at 0.9-3.1 GFLOPs.
Original approach for the localisation of objects in images.IEE Proceedings- Vision, Image and Signal Processing, 141(4):245–250, 1994
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections
E-ConvNeXt combines CSPNet, batch-normalized ConvNeXt blocks, a stepped stem, and ESE attention to reach 78.3-81.9% ImageNet top-1 at 0.9-3.1 GFLOPs.