# Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection

arXiv: https://arxiv.org/abs/1801.03145 · HTML: https://mlsanity.com/paper/1801.03145/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jan 2018.

## Built on by (most cited first, 22 of 22)

- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Humble Teachers Teach Better Students for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.10456/) (2021)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [Active Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2303.08348/) (2023)
- [MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection](https://mlsanity.com/paper/2102.08884/) (2021)
- [Artificial Intelligence for the Metaverse: A Survey](https://mlsanity.com/paper/2202.10336/) (2022)
- [Group R-CNN for Weakly Semi-supervised Object Detection with Points](https://mlsanity.com/paper/2205.05920/) (2022)
- [Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters](https://mlsanity.com/paper/2108.01499/) (2021)
- [Robust Object Detection With Inaccurate Bounding Boxes](https://mlsanity.com/paper/2207.09697/) (2022)
- [Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity](https://mlsanity.com/paper/2110.14191/) (2021)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [A Survey on Visual Transfer Learning using Knowledge Graphs](https://mlsanity.com/paper/2201.11794/) (2022)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)
- [Towards Single Stage Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2106.10309/) (2021)
- [Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion](https://mlsanity.com/paper/2204.09186/) (2022)
- [Attention Regularized Laplace Graph for Domain Adaptation](https://mlsanity.com/paper/2210.08170/) (2022)
- [Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation](https://mlsanity.com/paper/2101.04563/) (2021)
- [Bridging Gap between Image Pixels and Semantics via Supervision: A Survey](https://mlsanity.com/paper/2107.13757/) (2021)
- [CaT: Weakly Supervised Object Detection with Category Transfer](https://mlsanity.com/paper/2108.07487/) (2021)
- [Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer](https://mlsanity.com/paper/2407.08460/) (2024)
- [Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition](https://mlsanity.com/paper/2401.07061/) (2024)
- [UnseenNet: Fast Training Detector for Any Unseen Concept](https://mlsanity.com/paper/2203.08759/) (2022)

## Abstract (arXiv)

Deep CNN-based object detection systems have achieved remarkable success on several large-scale object detection benchmarks. However, training such detectors requires a large number of labeled bounding boxes, which are more difficult to obtain than image-level annotations. Previous work addresses this issue by transforming image-level classifiers into object detectors. This is done by modeling the differences between the two on categories with both image-level and bounding box annotations, and transferring this information to convert classifiers to detectors for categories without bounding box annotations. We improve this previous work by incorporating knowledge about object similarities from visual and semantic domains during the transfer process. The intuition behind our proposed method is that visually and semantically similar categories should exhibit more common transferable properties than dissimilar categories, e.g. a better detector would result by transforming the differences between a dog classifier and a dog detector onto the cat class, than would by transforming from the violin class. Experimental results on the challenging ILSVRC2013 detection dataset demonstrate that each of our proposed object similarity based knowledge transfer methods outperforms the baseline methods. We found strong evidence that visual similarity and semantic relatedness are complementary for the task, and when combined notably improve detection, achieving state-of-the-art detection performance in a semi-supervised setting.