# DOCK: Detecting Objects by transferring Common-sense Knowledge

arXiv: https://arxiv.org/abs/1804.01077 · HTML: https://mlsanity.com/paper/1804.01077/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2018.

## Built on by (most cited first, 8 of 8)

- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection](https://mlsanity.com/paper/2309.01093/) (2023)
- [Beyond Object Recognition: A New Benchmark towards Object Concept Learning](https://mlsanity.com/paper/2212.02710/) (2022)
- [Improving Scene Graph Classification by Exploiting Knowledge from Texts](https://mlsanity.com/paper/2102.04760/) (2021)
- [Open-Vocabulary Object Detection via Language Hierarchy](https://mlsanity.com/paper/2410.20371/) (2024)
- [Large Model Based Referring Camouflaged Object Detection](https://mlsanity.com/paper/2311.17122/) (2023)
- [Envisioning Narrative Intelligence: A Creative Visual Storytelling Anthology](https://mlsanity.com/paper/2310.04529/) (2023)
- [Physical Rule-Guided Convolutional Neural Network](https://mlsanity.com/paper/2409.02081/) (2024)

## Abstract (arXiv)

We present a scalable approach for Detecting Objects by transferring Common-sense Knowledge (DOCK) from source to target categories. In our setting, the training data for the source categories have bounding box annotations, while those for the target categories only have image-level annotations. Current state-of-the-art approaches focus on image-level visual or semantic similarity to adapt a detector trained on the source categories to the new target categories. In contrast, our key idea is to (i) use similarity not at the image-level, but rather at the region-level, and (ii) leverage richer common-sense (based on attribute, spatial, etc.) to guide the algorithm towards learning the correct detections. We acquire such common-sense cues automatically from readily-available knowledge bases without any extra human effort. On the challenging MS COCO dataset, we find that common-sense knowledge can substantially improve detection performance over existing transfer-learning baselines.