# All in Tokens: Unifying Output Space of Visual Tasks via Soft Token

arXiv: https://arxiv.org/abs/2301.02229 · HTML: https://mlsanity.com/paper/2301.02229/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 58 references that are in the map.
- First posted on arXiv 5 Jan 2023.

## Builds on (most cited first, 30 of 50)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)

## Built on by (most cited first, 30 of 52)

- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation](https://mlsanity.com/paper/2312.02145/) (2023)
- [Unleashing Text-to-Image Diffusion Models for Visual Perception](https://mlsanity.com/paper/2303.02153/) (2023)
- [Multimodal Foundation Models: From Specialists to General-Purpose Assistants](https://mlsanity.com/paper/2309.10020/) (2023)
- [PaLI-3 Vision Language Models: Smaller, Faster, Stronger](https://mlsanity.com/paper/2310.09199/) (2023)
- [The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation](https://mlsanity.com/paper/2306.01923/) (2023)
- [ImageFolder: Autoregressive Image Generation with Folded Tokens](https://mlsanity.com/paper/2410.01756/) (2024)
- [Monocular Depth Estimation using Diffusion Models](https://mlsanity.com/paper/2302.14816/) (2023)
- [Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis](https://mlsanity.com/paper/2505.09358/) (2025)
- [Perception Tokens Enhance Visual Reasoning in Multimodal Language Models](https://mlsanity.com/paper/2412.03548/) (2024)
- [MolmoAct2: Action Reasoning Models for Real-world Deployment](https://mlsanity.com/paper/2605.02881/) (2026)
- [ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation](https://mlsanity.com/paper/2403.18807/) (2024)
- [Text-image Alignment for Diffusion-based Perception](https://mlsanity.com/paper/2310.00031/) (2023)
- [PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation](https://mlsanity.com/paper/2312.02284/) (2023)
- [LocCa: Visual Pretraining with Location-aware Captioners](https://mlsanity.com/paper/2403.19596/) (2024)
- [Video Depth without Video Models](https://mlsanity.com/paper/2411.19189/) (2024)
- [GiT: Towards Generalist Vision Transformer through Universal Language Interface](https://mlsanity.com/paper/2403.09394/) (2024)
- [Unified Language Representation for Question Answering over Text, Tables, and Images](https://mlsanity.com/paper/2306.16762/) (2023)
- [Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling](https://mlsanity.com/paper/2403.10071/) (2024)
- [ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation](https://mlsanity.com/paper/2407.08187/) (2024)
- [PolyMaX: General Dense Prediction with Mask Transformer](https://mlsanity.com/paper/2311.05770/) (2023)
- [EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment](https://mlsanity.com/paper/2312.08548/) (2023)
- [The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation](https://mlsanity.com/paper/2307.15061/) (2023)
- [TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding](https://mlsanity.com/paper/2311.03427/) (2023)
- [XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generation](https://mlsanity.com/paper/2412.01762/) (2024)
- [Image Tokenizer Needs Post-Training](https://mlsanity.com/paper/2509.12474/) (2025)
- [Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis](https://mlsanity.com/paper/2503.08354/) (2025)
- [cVLA: Towards Efficient Camera-Space VLAs](https://mlsanity.com/paper/2507.02190/) (2025)
- [Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Image](https://mlsanity.com/paper/2504.12103/) (2025)

## Abstract (arXiv)

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 urlhttps://github.com/SwinTransformer/AiT.