# Are we done with object recognition? The iCub robot's perspective

arXiv: https://arxiv.org/abs/1709.09882 · HTML: https://mlsanity.com/paper/1709.09882/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2017.

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

- [Uncertainty for Identifying Open-Set Errors in Visual Object Detection](https://mlsanity.com/paper/2104.01328/) (2021)
- [What's in the Black Box? The False Negative Mechanisms Inside Object Detectors](https://mlsanity.com/paper/2203.07662/) (2022)
- [Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search](https://mlsanity.com/paper/2407.07541/) (2024)
- [Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition](https://mlsanity.com/paper/2404.01397/) (2024)
- [Detecting Morphing Attacks via Continual Incremental Training](https://mlsanity.com/paper/2307.15105/) (2023)
- [A wearable sensor vest for social humanoid robots with GPGPU, IoT, and modular software architecture](https://mlsanity.com/paper/2201.02192/) (2022)
- [Top-Tuning: a study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods](https://mlsanity.com/paper/2209.07932/) (2022)

## Abstract (arXiv)

We report on an extensive study of the benefits and limitations of current deep learning approaches to object recognition in robot vision scenarios, introducing a novel dataset used for our investigation. To avoid the biases in currently available datasets, we consider a natural human-robot interaction setting to design a data-acquisition protocol for visual object recognition on the iCub humanoid robot. Analyzing the performance of off-the-shelf models trained off-line on large-scale image retrieval datasets, we show the necessity for knowledge transfer. We evaluate different ways in which this last step can be done, and identify the major bottlenecks affecting robotic scenarios. By studying both object categorization and identification problems, we highlight key differences between object recognition in robotics applications and in image retrieval tasks, for which the considered deep learning approaches have been originally designed. In a nutshell, our results confirm the remarkable improvements yield by deep learning in this setting, while pointing to specific open challenges that need be addressed for seamless deployment in robotics.