# Robust Learning Through Cross-Task Consistency

arXiv: https://arxiv.org/abs/2006.04096 · HTML: https://mlsanity.com/paper/2006.04096/

## Key facts

- Cited by 105 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2020.

## Built on by (most cited first, 30 of 105)

- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [UniT: Multimodal Multitask Learning with a Unified Transformer](https://mlsanity.com/paper/2102.10772/) (2021)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13774/) (2021)
- [Rethinking Inductive Biases for Surface Normal Estimation](https://mlsanity.com/paper/2403.00712/) (2024)
- [4M: Massively Multimodal Masked Modeling](https://mlsanity.com/paper/2312.06647/) (2023)
- [3D Common Corruptions and Data Augmentation](https://mlsanity.com/paper/2203.01441/) (2022)
- [Auto-Lambda: Disentangling Dynamic Task Relationships](https://mlsanity.com/paper/2202.03091/) (2022)
- [Weakly Supervised Learning of Rigid 3D Scene Flow](https://mlsanity.com/paper/2102.08945/) (2021)
- [Shape from Polarization for Complex Scenes in the Wild](https://mlsanity.com/paper/2112.11377/) (2021)
- [Hierarchical Normalization for Robust Monocular Depth Estimation](https://mlsanity.com/paper/2210.09670/) (2022)
- [MulT: An End-to-End Multitask Learning Transformer](https://mlsanity.com/paper/2205.08303/) (2022)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts](https://mlsanity.com/paper/2307.15324/) (2023)
- [StyleGAN knows Normal, Depth, Albedo, and More](https://mlsanity.com/paper/2306.00987/) (2023)
- [Learning Multiple Dense Prediction Tasks from Partially Annotated Data](https://mlsanity.com/paper/2111.14893/) (2021)
- [Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture](https://mlsanity.com/paper/2311.00457/) (2023)
- [Discrete Representations Strengthen Vision Transformer Robustness](https://mlsanity.com/paper/2111.10493/) (2021)
- [CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data](https://mlsanity.com/paper/2112.09081/) (2021)
- [Learning to Ground Instructional Articles in Videos through Narrations](https://mlsanity.com/paper/2306.03802/) (2023)
- [Towards a Collective Agenda on AI for Earth Science Data Analysis](https://mlsanity.com/paper/2104.05107/) (2021)
- [MGNet: Monocular Geometric Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2206.13199/) (2022)
- [Robustness via Cross-Domain Ensembles](https://mlsanity.com/paper/2103.10919/) (2021)
- [Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing](https://mlsanity.com/paper/2111.12608/) (2021)
- [Egocentric Video Task Translation](https://mlsanity.com/paper/2212.06301/) (2022)
- [XVO: Generalized Visual Odometry via Cross-Modal Self-Training](https://mlsanity.com/paper/2309.16772/) (2023)
- [DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data](https://mlsanity.com/paper/2403.15389/) (2024)
- [Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance](https://mlsanity.com/paper/2407.14032/) (2024)
- [Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection](https://mlsanity.com/paper/2204.04836/) (2022)
- [Relational Multi-Task Learning: Modeling Relations between Data and Tasks](https://mlsanity.com/paper/2303.07666/) (2023)

## Abstract (arXiv)

Visual perception entails solving a wide set of tasks, e.g., object detection, depth estimation, etc. The predictions made for multiple tasks from the same image are not independent, and therefore, are expected to be consistent. We propose a broadly applicable and fully computational method for augmenting learning with Cross-Task Consistency. The proposed formulation is based on inference-path invariance over a graph of arbitrary tasks. We observe that learning with cross-task consistency leads to more accurate predictions and better generalization to out-of-distribution inputs. This framework also leads to an informative unsupervised quantity, called Consistency Energy, based on measuring the intrinsic consistency of the system. Consistency Energy correlates well with the supervised error (r=0.67), thus it can be employed as an unsupervised confidence metric as well as for detection of out-of-distribution inputs (ROC-AUC=0.95). The evaluations are performed on multiple datasets, including Taskonomy, Replica, CocoDoom, and ApolloScape, and they benchmark cross-task consistency versus various baselines including conventional multi-task learning, cycle consistency, and analytical consistency.