# Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation

arXiv: https://arxiv.org/abs/2211.11116 · HTML: https://mlsanity.com/paper/2211.11116/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 57 references that are in the map.
- First posted on arXiv 20 Nov 2022.

## Builds on (most cited first, 30 of 54)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [Speaker-Follower Models for Vision-and-Language Navigation](https://mlsanity.com/paper/1806.02724/) (2018)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [Learning Representations for Automatic Colorization](https://mlsanity.com/paper/1603.06668/) (2016)
- [Vision-and-Dialog Navigation](https://mlsanity.com/paper/1907.04957/) (2019)
- [Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout](https://mlsanity.com/paper/1904.04195/) (2019)

## Built on by (most cited first, 9 of 9)

- [Learning Vision-and-Language Navigation from YouTube Videos](https://mlsanity.com/paper/2307.11984/) (2023)
- [Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation](https://mlsanity.com/paper/2309.08138/) (2023)
- [Vision-Language Navigation with Embodied Intelligence: A Survey](https://mlsanity.com/paper/2402.14304/) (2024)
- [VISTAv2: World Imagination for Indoor Vision-and-Language Navigation](https://mlsanity.com/paper/2512.00041/) (2025)
- [Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation](https://mlsanity.com/paper/2403.11541/) (2024)
- [Reinforcement Learning via Auxiliary Task Distillation](https://mlsanity.com/paper/2406.17168/) (2024)
- [NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired People](https://mlsanity.com/paper/2410.18109/) (2024)
- [A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigation](https://mlsanity.com/paper/2607.09792/) (2026)
- [Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining](https://mlsanity.com/paper/2504.20800/) (2025)

## Abstract (arXiv)

In Vision-and-Language Navigation (VLN), researchers typically take an image encoder pre-trained on ImageNet without fine-tuning on the environments that the agent will be trained or tested on. However, the distribution shift between the training images from ImageNet and the views in the navigation environments may render the ImageNet pre-trained image encoder suboptimal. Therefore, in this paper, we design a set of structure-encoding auxiliary tasks (SEA) that leverage the data in the navigation environments to pre-train and improve the image encoder. Specifically, we design and customize (1) 3D jigsaw, (2) traversability prediction, and (3) instance classification to pre-train the image encoder. Through rigorous ablations, our SEA pre-trained features are shown to better encode structural information of the scenes, which ImageNet pre-trained features fail to properly encode but is crucial for the target navigation task. The SEA pre-trained features can be easily plugged into existing VLN agents without any tuning. For example, on Test-Unseen environments, the VLN agents combined with our SEA pre-trained features achieve absolute success rate improvement of 12% for Speaker-Follower, 5% for Env-Dropout, and 4% for AuxRN.