# Look Around and Learn: Self-Training Object Detection by Exploration

arXiv: https://arxiv.org/abs/2302.03566 · HTML: https://mlsanity.com/paper/2302.03566/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 7 Feb 2023.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera](https://mlsanity.com/paper/1910.02527/) (2019)
- [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019)
- [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022)
- [Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations](https://mlsanity.com/paper/2012.09988/) (2020)
- [Revisiting Active Perception](https://mlsanity.com/paper/1603.02729/) (2016)
- [An Exploration of Embodied Visual Exploration](https://mlsanity.com/paper/2001.02192/) (2020)
- [SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency](https://mlsanity.com/paper/2112.01001/) (2021)
- [Semantic Curiosity for Active Visual Learning](https://mlsanity.com/paper/2006.09367/) (2020)
- [Interactron: Embodied Adaptive Object Detection](https://mlsanity.com/paper/2202.00660/) (2022)
- [Batch Exploration with Examples for Scalable Robotic Reinforcement Learning](https://mlsanity.com/paper/2010.11917/) (2020)

## Built on by (most cited first, 2 of 2)

- [Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description](https://mlsanity.com/paper/2412.01398/) (2024)
- [See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent](https://mlsanity.com/paper/2602.23806/) (2026)

## Abstract (arXiv)

When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a new environment without relying on human intervention, i.e., a fully self-supervised approach. In our setting, an agent initially learns to explore the environment using a pre-trained off-the-shelf detector to locate objects and associate pseudo-labels. By assuming that pseudo-labels for the same object must be consistent across different views, we learn the exploration policy Look Around to mine hard samples, and we devise a novel mechanism called Disagreement Reconciliation for producing refined pseudo-labels from the consensus among observations. We implement a unified benchmark of the current state-of-the-art and compare our approach with pre-existing exploration policies and perception mechanisms. Our method is shown to outperform existing approaches, improving the object detector by 6.2% in a simulated scenario, a 3.59% advancement over other state-of-the-art methods, and by 9.97% in the real robotic test without relying on ground-truth. Code for the proposed approach and baselines are available at https://iit-pavis.github.io/Look_Around_And_Learn/.