MogaNet a new family of efficient ConvNets with preferable parameter-performance trade-offs, which is trained on ImageNet-1k (1 million images, 1,000 classes). It was first introduced in the paper MogaNet and released in Westlake/MogaNet and Westlake/openmixup.

Since the recent success of Vision Transformers (ViTs), explorations toward ViT-style architectures have triggered the resurgence of ConvNets. In this work, we explore the representation ability of modern ConvNets from a novel view of multi-order game-theoretic interaction, which reflects inter-variable interaction effects w.r.t. contexts of different scales based on game theory. Within the modern ConvNet framework, we tailor the two feature mixers with conceptually simple yet effective depthwise convolutions to facilitate middle-order information across spatial and channel spaces respectively. In this light, a new family of pure ConvNet architecture, dubbed MogaNet, is proposed, which shows excellent scalability and attains competitive results among state-of-the-art models with more efficient use of parameters on ImageNet and multifarious typical vision benchmarks, including COCO object detection, ADE20K semantic segmentation, 2D&3D human pose estimation and video prediction.Typically, MogaNet hits 80.0% and 87.8% top-1 accuracy with 5.2M and 181M parameters on ImageNet, outperforming ParC-Net-S and ConvNeXt-L while saving 59% FLOPs and 17M parameters.

Setup before using the model.