Papers › Active Token Mixer
Active Token Mixer
Guoqiang Wei, Zhizheng Zhang, Cuiling Lan, Yan Lu, Zhibo Chen
The three existing dominant network families, i.e., CNNs, Transformers, and MLPs, differ from each other mainly in the ways of fusing spatial contextual information, leaving designing more effective token-mixing mechanisms at the core of backbone architecture development. In this work, we propose an innovative token-mixer, dubbed Active Token Mixer (ATM), to actively incorporate flexible contextual information distributed across different channels from other tokens into the given query token. This fundamental operator actively predicts where to capture useful contexts and learns how to fuse the captured contexts with the query token at channel level. In this way, the spatial range of token-mixing can be expanded to a global scope with limited computational complexity, where the way of token-mixing is reformed. We take ATM as the primary operator and assemble ATMs into a cascade architecture, dubbed ATMNet. Extensive experiments demonstrate that ATMNet is generally applicable and comprehensively surpasses different families of SOTA vision backbones by a clear margin on a broad range of vision tasks, including visual recognition and dense prediction tasks. Code is available at https://github.com/microsoft/ActiveMLP.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | ImageNet | ActiveMLP-L | GFLOPs | 36.4 | #288 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ActiveMLP-L | Number of params | 76.4M | #288 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ActiveMLP-L | Top 1 Accuracy | 84.8% | #288 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ActiveMLP-T | GFLOPs | 4 | #586 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ActiveMLP-T | Number of params | 27.2M | #586 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ActiveMLP-T | Top 1 Accuracy | 82% | #586 of 1060 | Archive leaderboard | report |
| Object Detection | COCO minival | ActiveMLP-B (Cascade Mask R-CNN) | box AP | 52.3 | #66 of 220 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ActiveMLP-L(UperNet) | Params (M) | 108 | #100 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ActiveMLP-L(UperNet) | Validation mIoU | 51.1 | #100 of 235 | 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