Papers › UniNet: Unified Architecture Search with Convolution, Transformer, and MLP

UniNet: Unified Architecture Search with Convolution, Transformer, and MLP

12 Jul 2022arXiv:2207.05420archive 2025-07-28

Jihao Liu, Xin Huang, Guanglu Song, Hongsheng Li, Yu Liu

Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. However, how to effectively combine those operators to form high-performance hybrid visual architectures still remains a challenge. In this work, we study the learnable combination of convolution, transformer, and MLP by proposing a novel unified architecture search approach. Our approach contains two key designs to achieve the search for high-performance networks. First, we model the very different searchable operators in a unified form, and thus enable the operators to be characterized with the same set of configuration parameters. In this way, the overall search space size is significantly reduced, and the total search cost becomes affordable. Second, we propose context-aware downsampling modules (DSMs) to mitigate the gap between the different types of operators. Our proposed DSMs are able to better adapt features from different types of operators, which is important for identifying high-performance hybrid architectures. Finally, we integrate configurable operators and DSMs into a unified search space and search with a Reinforcement Learning-based search algorithm to fully explore the optimal combination of the operators. To this end, we search a baseline network and scale it up to obtain a family of models, named UniNets, which achieve much better accuracy and efficiency than previous ConvNets and Transformers. In particular, our UniNet-B5 achieves 84.9% top-1 accuracy on ImageNet, outperforming EfficientNet-B7 and BoTNet-T7 with 44% and 55% fewer FLOPs respectively. By pretraining on the ImageNet-21K, our UniNet-B6 achieves 87.4%, outperforming Swin-L with 51% fewer FLOPs and 41% fewer parameters. Code is available at https://github.com/Sense-X/UniNet.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

sense-x/uninet officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to id 136810034 (not an arXiv id) (that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
sense-x/tokenmix mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers (arXiv:2207.08409; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Image ClassificationNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet UniNet-B6 GFLOPs 51 #94 of 1060 Archive leaderboard report
Image Classification ImageNet UniNet-B6 Number of params 117M #94 of 1060 Archive leaderboard report
Image Classification ImageNet UniNet-B6 Top 1 Accuracy 87.4% #94 of 1060 Archive leaderboard report
Image Classification ImageNet UniNet-B5 GFLOPs 20.4 #112 of 1060 Archive leaderboard report
Image Classification ImageNet UniNet-B5 Number of params 72.9M #112 of 1060 Archive leaderboard report
Image Classification ImageNet UniNet-B5 Top 1 Accuracy 87% #112 of 1060 Archive leaderboard report
Image Classification ImageNet UniNet-B0 GFLOPs 0.555 #680 of 1060 Archive leaderboard report
Image Classification ImageNet UniNet-B0 Number of params 11.5M #680 of 1060 Archive leaderboard report
Image Classification ImageNet UniNet-B0 Top 1 Accuracy 80.8% #680 of 1060 Archive leaderboard report
Neural Architecture Search ImageNet UniNet-B0 FLOPs 555M #13 of 135 Archive leaderboard report
Neural Architecture Search ImageNet UniNet-B0 Params 11.5M #13 of 135 Archive leaderboard report
Neural Architecture Search ImageNet UniNet-B0 Top-1 Error Rate 19.2 #13 of 135 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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