paper-with-me

Papers

Invariance is Key to Generalization: Examining the Role of Representation in Sim-to-Real Transfer for Visual Navigation

2023-10-23 · Bo Ai, Zhanxin Wu, David Hsu

The data-driven approach to robot control has been gathering pace rapidly, yet generalization to unseen task domains remains a critical challenge. We argue that the key to generalization is representations that are (i) rich enough to capture all task-relevant information and (ii) invariant to superfluous variability between the training and the test domains. We experimentally study such a representation -- containing both depth and semantic information -- for visual navigation and show that it enables a control policy trained entirely in simulated indoor scenes to generalize to diverse real-world environments, both indoors and outdoors. Further, we show that our representation reduces the A-distance between the training and test domains, improving the generalization error bound as a result. Our proposed approach is scalable: the learned policy improves continuously, as the foundation models that it exploits absorb more diverse data during pre-training.

📄 PDF Abstract BibTeX arXiv:2310.15020

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Navigation

Similar Papers 제목 키워드 기반

On Invariance Penalties for Risk Minimization

2021-06-17 · Kia Khezeli, Arno Blaas, Frank Soboczenski, Nicholas Chia 외

The Invariant Risk Minimization (IRM) principle was first proposed by Arjovsky et al. [2019] to address the domain generalization problem by leveraging data heterogeneity from differing experimental conditions. Specifica…

Domain Generalization

What Does CNN Shift Invariance Look Like? A Visualization Study

2020-11-09 · Jake Lee, Junfeng Yang, Zhangyang Wang

Feature extraction with convolutional neural networks (CNNs) is a popular method to represent images for machine learning tasks. These representations seek to capture global image content, and ideally should be independe…

Generalization Gap in Data Augmentation: Insights from Illumination

2024-04-11 · Jianqiang Xiao, Weiwen Guo, Junfeng Liu, Mengze Li

In the field of computer vision, data augmentation is widely used to enrich the feature complexity of training datasets with deep learning techniques. However, regarding the generalization capabilities of models, the dif…

Data AugmentationDiversity

Domain Generalization through the Lens of Angular Invariance

2022-10-28 · Yujie Jin, Xu Chu, Yasha Wang, Wenwu Zhu

Domain generalization (DG) aims at generalizing a classifier trained on multiple source domains to an unseen target domain with domain shift. A common pervasive theme in existing DG literature is domain-invariant represe…

Domain GeneralizationRepresentation Learning

"One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviors

2023-10-23 · Li Lucy, Su Lin Blodgett, Milad Shokouhi, Hanna Wallach 외

Fairness-related assumptions about what constitute appropriate NLG system behaviors range from invariance, where systems are expected to behave identically for social groups, to adaptation, where behaviors should instead…

AllFairness