# InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding

arXiv: https://arxiv.org/abs/2203.07997 · HTML: https://mlsanity.com/paper/2203.07997/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 55 references that are in the map.
- First posted on arXiv 15 Mar 2022.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [Bottleneck Transformers for Visual Recognition](https://mlsanity.com/paper/2101.11605/) (2021)
- [Attention Augmented Convolutional Networks](https://mlsanity.com/paper/1904.09925/) (2019)
- [Pix2seq: A Language Modeling Framework for Object Detection](https://mlsanity.com/paper/2109.10852/) (2021)
- [Focal Self-attention for Local-Global Interactions in Vision Transformers](https://mlsanity.com/paper/2107.00641/) (2021)
- [Understanding Robustness of Transformers for Image Classification](https://mlsanity.com/paper/2103.14586/) (2021)

## Built on by (most cited first, 30 of 89)

- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation](https://mlsanity.com/paper/2404.04256/) (2024)
- [Multi-Task Dense Prediction via Mixture of Low-Rank Experts](https://mlsanity.com/paper/2403.17749/) (2024)
- [All in Tokens: Unifying Output Space of Visual Tasks via Soft Token](https://mlsanity.com/paper/2301.02229/) (2023)
- [TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts](https://mlsanity.com/paper/2307.15324/) (2023)
- [MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning](https://mlsanity.com/paper/2403.20320/) (2024)
- [Multi-Task Learning with Multi-Query Transformer for Dense Prediction](https://mlsanity.com/paper/2205.14354/) (2022)
- [PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions](https://mlsanity.com/paper/2409.15278/) (2024)
- [Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching](https://mlsanity.com/paper/2303.14969/) (2023)
- [Dual-Balancing for Multi-Task Learning](https://mlsanity.com/paper/2308.12029/) (2023)
- [InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding](https://mlsanity.com/paper/2306.04842/) (2023)
- [MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders](https://mlsanity.com/paper/2407.02228/) (2024)
- [PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation](https://mlsanity.com/paper/2301.00954/) (2023)
- [DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data](https://mlsanity.com/paper/2403.15389/) (2024)
- [Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond](https://mlsanity.com/paper/2501.10945/) (2025)
- [FedHCA2: Towards Hetero-Client Federated Multi-Task Learning](https://mlsanity.com/paper/2311.13250/) (2023)
- [Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection](https://mlsanity.com/paper/2406.00830/) (2024)
- [Selective Task Group Updates for Multi-Task Optimization](https://mlsanity.com/paper/2502.11986/) (2025)
- [Vision Transformer Adapters for Generalizable Multitask Learning](https://mlsanity.com/paper/2308.12372/) (2023)
- [PolyMaX: General Dense Prediction with Mask Transformer](https://mlsanity.com/paper/2311.05770/) (2023)
- [Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision](https://mlsanity.com/paper/2504.04903/) (2025)
- [Pixel Difference Convolutional Network for RGB-D Semantic Segmentation](https://mlsanity.com/paper/2302.11951/) (2023)
- [Prompt Guided Transformer for Multi-Task Dense Prediction](https://mlsanity.com/paper/2307.15362/) (2023)
- [Supervised Fine-tuning in turn Improves Visual Foundation Models](https://mlsanity.com/paper/2401.10222/) (2024)
- [SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images](https://mlsanity.com/paper/2403.10662/) (2024)
- [TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding](https://mlsanity.com/paper/2311.03427/) (2023)
- [A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision](https://mlsanity.com/paper/2303.17376/) (2023)
- [MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders](https://mlsanity.com/paper/2408.15101/) (2024)
- [DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation](https://mlsanity.com/paper/2210.06747/) (2022)
- [Efficient Computation Sharing for Multi-Task Visual Scene Understanding](https://mlsanity.com/paper/2303.09663/) (2023)

## Abstract (arXiv)

Multi-task dense scene understanding is a thriving research domain that requires simultaneous perception and reasoning on a series of correlated tasks with pixel-wise prediction. Most existing works encounter a severe limitation of modeling in the locality due to heavy utilization of convolution operations, while learning interactions and inference in a global spatial-position and multi-task context is critical for this problem. In this paper, we propose a novel end-to-end Inverted Pyramid multi-task Transformer (InvPT) to perform simultaneous modeling of spatial positions and multiple tasks in a unified framework. To the best of our knowledge, this is the first work that explores designing a transformer structure for multi-task dense prediction for scene understanding. Besides, it is widely demonstrated that a higher spatial resolution is remarkably beneficial for dense predictions, while it is very challenging for existing transformers to go deeper with higher resolutions due to huge complexity to large spatial size. InvPT presents an efficient UP-Transformer block to learn multi-task feature interaction at gradually increased resolutions, which also incorporates effective self-attention message passing and multi-scale feature aggregation to produce task-specific prediction at a high resolution. Our method achieves superior multi-task performance on NYUD-v2 and PASCAL-Context datasets respectively, and significantly outperforms previous state-of-the-arts. The code is available at https://github.com/prismformore/InvPT