Papers › ACC-UNet: A Completely Convolutional UNet model for the 2020s

ACC-UNet: A Completely Convolutional UNet model for the 2020s

25 Aug 2023arXiv:2308.13680archive 2025-07-28

Nabil Ibtehaz, Daisuke Kihara

This decade is marked by the introduction of Vision Transformer, a radical paradigm shift in broad computer vision. A similar trend is followed in medical imaging, UNet, one of the most influential architectures, has been redesigned with transformers. Recently, the efficacy of convolutional models in vision is being reinvestigated by seminal works such as ConvNext, which elevates a ResNet to Swin Transformer level. Deriving inspiration from this, we aim to improve a purely convolutional UNet model so that it can be on par with the transformer-based models, e.g, Swin-Unet or UCTransNet. We examined several advantages of the transformer-based UNet models, primarily long-range dependencies and cross-level skip connections. We attempted to emulate them through convolution operations and thus propose, ACC-UNet, a completely convolutional UNet model that brings the best of both worlds, the inherent inductive biases of convnets with the design decisions of transformers. ACC-UNet was evaluated on 5 different medical image segmentation benchmarks and consistently outperformed convnets, transformers, and their hybrids. Notably, ACC-UNet outperforms state-of-the-art models Swin-Unet and UCTransNet by 2.64 ±2.54% and 0.45 ±1.61% in terms of dice score, respectively, while using a fraction of their parameters (59.26% and 24.24%). Our codes are available at https://github.com/kiharalab/ACC-UNet.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

kiharalab/acc-unet officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image SegmentationMedical Image SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAbsolute Position EncodingsAdamAttentionAverage PoolingBPEBatch NormalizationBottleneck Residual BlockChannel-wise Cross AttentionChannel-wise Cross Fusion TransformerConvolutionDense ConnectionsDropoutGlobal Average PoolingInstance NormalizationKaiming InitializationLabel SmoothingLayer NormalizationLinear LayerMax PoolingMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual BlockResidual ConnectionSigmoid ActivationSoftmaxStochastic DepthSwin TransformerTransformerUCTransNetVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections