Facebook AI & UC Berkeley’s ConvNeXts Compete Favourably With SOTA Hierarchical ViTs on CV Benchmarks | Synced
A team from Facebook AI Research and UC Berkeley proposes ConvNeXts, a pure ConvNet model that achieves performance comparable with state-of-the-art hierarchical vision transformers on computer vis...
Source: Synced | AI Technology & Industry Review
A team from Facebook AI Research and UC Berkeley proposes ConvNeXts, a pure ConvNet model that achieves performance comparable with state-of-the-art hierarchical vision transformers on computer vision benchmarks while retaining the simplicity and efficiency of standard ConvNets.