Papers › All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
Jia Ning, Chen Li, Zheng Zhang, Zigang Geng, Qi Dai, Kun He, Han Hu
Unlike language tasks, where the output space is usually limited to a set of tokens, the output space of visual tasks is more complicated, making it difficult to build a unified visual model for various visual tasks. In this paper, we seek to unify the output space of visual tasks, so that we can also build a unified model for visual tasks. To this end, we demonstrate a single unified model that simultaneously handles two typical visual tasks of instance segmentation and depth estimation, which have discrete/fixed-length and continuous/varied-length outputs, respectively. We propose several new techniques that take into account the particularity of visual tasks: 1) Soft token. We employ soft token to represent the task output. Unlike hard tokens in the common VQ-VAE which are assigned one-hot to discrete codebooks/vocabularies, the soft token is assigned softly to the codebook embeddings. Soft token can improve the accuracy of both the next token inference and decoding of the task output; 2) Mask augmentation. Many visual tasks have corruption, undefined or invalid values in label annotations, i.e., occluded area of depth maps. We show that a mask augmentation technique can greatly benefit these tasks. With these new techniques and other designs, we show that the proposed general-purpose task-solver can perform both instance segmentation and depth estimation well. Particularly, we achieve 0.279 RMSE on the specific task of NYUv2 depth estimation, setting a new record on this benchmark. The general-purpose task-solver, dubbed AiT, is available at \url{https://github.com/SwinTransformer/AiT}.
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
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 |
|---|---|---|---|---|---|---|---|
| Monocular Depth Estimation | NYU-Depth V2 | AiT-P(SwinV2-L) | Delta < 1.25 | 0.954 | #27 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | AiT-P(SwinV2-L) | Delta < 1.25^2 | 0.994 | #27 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | AiT-P(SwinV2-L) | Delta < 1.25^3 | 0.999 | #27 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | AiT-P(SwinV2-L) | RMSE | 0.275 | #27 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | AiT-P(SwinV2-L) | absolute relative error | 0.076 | #27 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | AiT-P(SwinV2-L) | log 10 | 0.033 | #27 of 85 | 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.
Methods
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