# UnseenNet: Fast Training Detector for Any Unseen Concept

arXiv: https://arxiv.org/abs/2203.08759 · HTML: https://mlsanity.com/paper/2203.08759/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 16 Mar 2022.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding](https://mlsanity.com/paper/2103.05950/) (2021)
- [Multiple Instance Detection Network with Online Instance Classifier Refinement](https://mlsanity.com/paper/1704.00138/) (2017)
- [Multi-Scale Positive Sample Refinement for Few-Shot Object Detection](https://mlsanity.com/paper/2007.09384/) (2020)
- [LSTD: A Low-Shot Transfer Detector for Object Detection](https://mlsanity.com/paper/1803.01529/) (2018)
- [WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection](https://mlsanity.com/paper/1909.04972/) (2019)
- [Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning](https://mlsanity.com/paper/1503.00949/) (2015)
- [LSDA: Large Scale Detection Through Adaptation](https://mlsanity.com/paper/1407.5035/) (2014)
- [Revisiting knowledge transfer for training object class detectors](https://mlsanity.com/paper/1708.06128/) (2017)
- [Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection](https://mlsanity.com/paper/1801.03145/) (2018)
- [Soft Proposal Networks for Weakly Supervised Object Localization](https://mlsanity.com/paper/1709.01829/) (2017)
- [Mixed Supervised Object Detection with Robust Objectness Transfer](https://mlsanity.com/paper/1802.09778/) (2018)
- [Improving Weakly-Supervised Object Localization By Micro-Annotation](https://mlsanity.com/paper/1605.05538/) (2016)
- [Transfer Learning by Ranking for Weakly Supervised Object Annotation](https://mlsanity.com/paper/1705.00873/) (2017)

## Abstract (arXiv)

Training of object detection models using less data is currently the focus of existing N-shot learning models in computer vision. Such methods use object-level labels and takes hours to train on unseen classes. There are many cases where we have large amount of image-level labels available for training but cannot be utilized by few shot object detection models for training. There is a need for a machine learning framework that can be used for training any unseen class and can become useful in real-time situations. In this paper, we proposed an "Unseen Class Detector" that can be trained within a very short time for any possible unseen class without bounding boxes with competitive accuracy. We build our approach on "Strong" and "Weak" baseline detectors, which we trained on existing object detection and image classification datasets, respectively. Unseen concepts are fine-tuned on the strong baseline detector using only image-level labels and further adapted by transferring the classifier-detector knowledge between baselines. We use semantic as well as visual similarities to identify the source class (i.e. Sheep) for the fine-tuning and adaptation of unseen class (i.e. Goat). Our model (UnseenNet) is trained on the ImageNet classification dataset for unseen classes and tested on an object detection dataset (OpenImages). UnseenNet improves the mean average precision (mAP) by 10% to 30% over existing baselines (semi-supervised and few-shot) of object detection on different unseen class splits. Moreover, training time of our model is <10 min for each unseen class. Qualitative results demonstrate that UnseenNet is suitable not only for few classes of Pascal VOC but for unseen classes of any dataset or web. Code is available at https://github.com/Asra-Aslam/UnseenNet.