# Co-training for Deep Object Detection: Comparing Single-modal and Multi-modal Approaches

arXiv: https://arxiv.org/abs/2104.11619 · HTML: https://mlsanity.com/paper/2104.11619/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 23 Apr 2021.

## Builds on (most cited first, 17 of 17)

- [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)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Revisiting Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1901.09005/) (2019)
- [Enforcing geometric constraints of virtual normal for depth prediction](https://mlsanity.com/paper/1907.12209/) (2019)
- [PolarMask: Single Shot Instance Segmentation with Polar Representation](https://mlsanity.com/paper/1909.13226/) (2019)
- [Deep Co-Training for Semi-Supervised Image Recognition](https://mlsanity.com/paper/1803.05984/) (2018)
- [Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation](https://mlsanity.com/paper/1904.01870/) (2019)
- [SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation](https://mlsanity.com/paper/2006.04026/) (2020)
- [Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision](https://mlsanity.com/paper/2103.12209/) (2021)
- [On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation](https://mlsanity.com/paper/2010.06626/) (2020)
- [Generating Accurate Pseudo-labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations](https://mlsanity.com/paper/1909.05479/) (2019)
- [Co-training for On-board Deep Object Detection](https://mlsanity.com/paper/2008.05534/) (2020)

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

- [Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models](https://mlsanity.com/paper/2205.15781/) (2022)
- [UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentation](https://mlsanity.com/paper/2405.09682/) (2024)

## Abstract (arXiv)

Top-performing computer vision models are powered by convolutional neural networks (CNNs). Training an accurate CNN highly depends on both the raw sensor data and their associated ground truth (GT). Collecting such GT is usually done through human labeling, which is time-consuming and does not scale as we wish. This data labeling bottleneck may be intensified due to domain shifts among image sensors, which could force per-sensor data labeling. In this paper, we focus on the use of co-training, a semi-supervised learning (SSL) method, for obtaining self-labeled object bounding boxes (BBs), i.e., the GT to train deep object detectors. In particular, we assess the goodness of multi-modal co-training by relying on two different views of an image, namely, appearance (RGB) and estimated depth (D). Moreover, we compare appearance-based single-modal co-training with multi-modal. Our results suggest that in a standard SSL setting (no domain shift, a few human-labeled data) and under virtual-to-real domain shift (many virtual-world labeled data, no human-labeled data) multi-modal co-training outperforms single-modal. In the latter case, by performing GAN-based domain translation both co-training modalities are on pair; at least, when using an off-the-shelf depth estimation model not specifically trained on the translated images.