# Gram-SLD: Automatic Self-labeling and Detection for Instance Objects

arXiv: https://arxiv.org/abs/2112.03641 · HTML: https://mlsanity.com/paper/2112.03641/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 55 references that are in the map.
- First posted on arXiv 7 Dec 2021.

## Builds on (most cited first, 14 of 14)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [A Dataset for Developing and Benchmarking Active Vision](https://mlsanity.com/paper/1702.08272/) (2017)
- [Recent Advances in Deep Learning for Object Detection](https://mlsanity.com/paper/1908.03673/) (2019)
- [Synthesizing Training Data for Object Detection in Indoor Scenes](https://mlsanity.com/paper/1702.07836/) (2017)
- [Multiview RGB-D Dataset for Object Instance Detection](https://mlsanity.com/paper/1609.07826/) (2016)
- [Target Driven Instance Detection](https://mlsanity.com/paper/1803.04610/) (2018)
- [Feature Agglomeration Networks for Single Stage Face Detection](https://mlsanity.com/paper/1712.00721/) (2017)
- [Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection](https://mlsanity.com/paper/1803.08208/) (2018)

## Abstract (arXiv)

Instance object detection plays an important role in intelligent monitoring, visual navigation, human-computer interaction, intelligent services and other fields. Inspired by the great success of Deep Convolutional Neural Network (DCNN), DCNN-based instance object detection has become a promising research topic. To address the problem that DCNN always requires a large-scale annotated dataset to supervise its training while manual annotation is exhausting and time-consuming, we propose a new framework based on co-training called Gram Self-Labeling and Detection (Gram-SLD). The proposed Gram-SLD can automatically annotate a large amount of data with very limited manually labeled key data and achieve competitive performance. In our framework, gram loss is defined and used to construct two fully redundant and independent views and a key sample selection strategy along with an automatic annotating strategy that comprehensively consider precision and recall are proposed to generate high quality pseudo-labels. Experiments on the public GMU Kitchen Dataset , Active Vision Dataset and the self-made BHID-ITEM Datasetdemonstrate that, with only 5% labeled training data, our Gram-SLD achieves competitive performance in object detection (less than 2% mAP loss), compared with the fully supervised methods. In practical applications with complex and changing environments, the proposed method can satisfy the real-time and accuracy requirements on instance object detection.