# Move to See Better: Self-Improving Embodied Object Detection

arXiv: https://arxiv.org/abs/2012.00057 · HTML: https://mlsanity.com/paper/2012.00057/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 7 of 7)

- [SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency](https://mlsanity.com/paper/2112.01001/) (2021)
- [O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning](https://mlsanity.com/paper/2106.15087/) (2021)
- [Interactron: Embodied Adaptive Object Detection](https://mlsanity.com/paper/2202.00660/) (2022)
- [An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs](https://mlsanity.com/paper/2105.01342/) (2021)
- [IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes](https://mlsanity.com/paper/2112.05298/) (2021)
- [Interactive Semantic Map Representation for Skill-based Visual Object Navigation](https://mlsanity.com/paper/2311.04107/) (2023)
- [SegmATRon: Embodied Adaptive Semantic Segmentation for Indoor Environment](https://mlsanity.com/paper/2310.12031/) (2023)

## Abstract (arXiv)

Passive methods for object detection and segmentation treat images of the same scene as individual samples and do not exploit object permanence across multiple views. Generalization to novel or difficult viewpoints thus requires additional training with lots of annotations. In contrast, humans often recognize objects by simply moving around, to get more informative viewpoints. In this paper, we propose a method for improving object detection in testing environments, assuming nothing but an embodied agent with a pre-trained 2D object detector. Our agent collects multi-view data, generates 2D and 3D pseudo-labels, and fine-tunes its detector in a self-supervised manner. Experiments on both indoor and outdoor datasets show that (1) our method obtains high-quality 2D and 3D pseudo-labels from multi-view RGB-D data; (2) fine-tuning with these pseudo-labels improves the 2D detector significantly in the test environment; (3) training a 3D detector with our pseudo-labels outperforms a prior self-supervised method by a large margin; (4) given weak supervision, our method can generate better pseudo-labels for novel objects.