# Revisiting knowledge transfer for training object class detectors

arXiv: https://arxiv.org/abs/1708.06128 · HTML: https://mlsanity.com/paper/1708.06128/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2017.

## Built on by (most cited first, 26 of 26)

- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types](https://mlsanity.com/paper/2103.13318/) (2021)
- [Webly Supervised Concept Expansion for General Purpose Vision Models](https://mlsanity.com/paper/2202.02317/) (2022)
- [MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection](https://mlsanity.com/paper/2102.08884/) (2021)
- [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)
- [Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification](https://mlsanity.com/paper/2208.08741/) (2022)
- [On Label Granularity and Object Localization](https://mlsanity.com/paper/2207.10225/) (2022)
- [Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity](https://mlsanity.com/paper/2110.14191/) (2021)
- [Open-Vocabulary Object Detection via Language Hierarchy](https://mlsanity.com/paper/2410.20371/) (2024)
- [W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection](https://mlsanity.com/paper/2207.12104/) (2022)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)
- [Compacting Deep Neural Networks for Internet of Things: Methods and Applications](https://mlsanity.com/paper/2103.11083/) (2021)
- [Re-examining Distillation For Continual Object Detection](https://mlsanity.com/paper/2204.01407/) (2022)
- [Atom-Level Optical Chemical Structure Recognition with Limited Supervision](https://mlsanity.com/paper/2404.01743/) (2024)
- [Few-shot Weakly-Supervised Object Detection via Directional Statistics](https://mlsanity.com/paper/2103.14162/) (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)
- [SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection](https://mlsanity.com/paper/2101.01260/) (2021)
- [Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection](https://mlsanity.com/paper/2303.05148/) (2023)
- [OmViD: Omni-supervised active learning for video action detection](https://mlsanity.com/paper/2508.13983/) (2025)
- [Similarity Transfer for Knowledge Distillation](https://mlsanity.com/paper/2103.10047/) (2021)
- [UnseenNet: Fast Training Detector for Any Unseen Concept](https://mlsanity.com/paper/2203.08759/) (2022)
- [Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning](https://mlsanity.com/paper/2210.05568/) (2022)

## Abstract (arXiv)

We propose to revisit knowledge transfer for training object detectors on target classes from weakly supervised training images, helped by a set of source classes with bounding-box annotations. We present a unified knowledge transfer framework based on training a single neural network multi-class object detector over all source classes, organized in a semantic hierarchy. This generates proposals with scores at multiple levels in the hierarchy, which we use to explore knowledge transfer over a broad range of generality, ranging from class-specific (bicycle to motorbike) to class-generic (objectness to any class). Experiments on the 200 object classes in the ILSVRC 2013 detection dataset show that our technique: (1) leads to much better performance on the target classes (70.3% CorLoc, 36.9% mAP) than a weakly supervised baseline which uses manually engineered objectness [11] (50.5% CorLoc, 25.4% mAP). (2) delivers target object detectors reaching 80% of the mAP of their fully supervised counterparts. (3) outperforms the best reported transfer learning results on this dataset (+41% CorLoc and +3% mAP over [18, 46], +16.2% mAP over [32]). Moreover, we also carry out several across-dataset knowledge transfer experiments [27, 24, 35] and find that (4) our technique outperforms the weakly supervised baseline in all dataset pairs by 1.5x-1.9x, establishing its general applicability.