# Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes

arXiv: https://arxiv.org/abs/1908.05217 · HTML: https://mlsanity.com/paper/1908.05217/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2019.

## Built on by (most cited first, 17 of 17)

- [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)
- [Decoupled Adaptation for Cross-Domain Object Detection](https://mlsanity.com/paper/2110.02578/) (2021)
- [Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding](https://mlsanity.com/paper/2206.03484/) (2022)
- [On Label Granularity and Object Localization](https://mlsanity.com/paper/2207.10225/) (2022)
- [Semi-supervised Open-World Object Detection](https://mlsanity.com/paper/2402.16013/) (2024)
- [Open-Vocabulary Object Detection via Language Hierarchy](https://mlsanity.com/paper/2410.20371/) (2024)
- [Re-examining Distillation For Continual Object Detection](https://mlsanity.com/paper/2204.01407/) (2022)
- [Fine-Grained Visual Entailment](https://mlsanity.com/paper/2203.15704/) (2022)
- [V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotations](https://mlsanity.com/paper/2412.11412/) (2024)
- [Improving Apparel Detection with Category Grouping and Multi-grained Branches](https://mlsanity.com/paper/2101.06770/) (2021)
- [Domain Adaptation for Large-Vocabulary Object Detectors](https://mlsanity.com/paper/2401.06969/) (2024)
- [CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection](https://mlsanity.com/paper/2503.18430/) (2025)
- [VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection](https://mlsanity.com/paper/2511.18075/) (2025)
- [On Utilizing Relationships for Transferable Few-Shot Fine-Grained Object Detection](https://mlsanity.com/paper/2212.00770/) (2022)
- [Multi-Domain Learning with Global Expert Mapping](https://mlsanity.com/paper/2604.18842/) (2026)
- [HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images](https://mlsanity.com/paper/2604.18866/) (2026)

## Abstract (arXiv)

Recent advances in deep learning greatly boost the performance of object detection. State-of-the-art methods such as Faster-RCNN, FPN and R-FCN have achieved high accuracy in challenging benchmark datasets. However, these methods require fully annotated object bounding boxes for training, which are incredibly hard to scale up due to the high annotation cost. Weakly-supervised methods, on the other hand, only require image-level labels for training, but the performance is far below their fully-supervised counterparts. In this paper, we propose a semi-supervised large scale fine-grained detection method, which only needs bounding box annotations of a smaller number of coarse-grained classes and image-level labels of large scale fine-grained classes, and can detect all classes at nearly fully-supervised accuracy. We achieve this by utilizing the correlations between coarse-grained and fine-grained classes with shared backbone, soft-attention based proposal re-ranking, and a dual-level memory module. Experiment results show that our methods can achieve close accuracy on object detection to state-of-the-art fully-supervised methods on two large scale datasets, ImageNet and OpenImages, with only a small fraction of fully annotated classes.