# Zero-Shot Detection

arXiv: https://arxiv.org/abs/1803.07113 · HTML: https://mlsanity.com/paper/1803.07113/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2018.

## Built on by (most cited first, 27 of 27)

- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model](https://mlsanity.com/paper/2203.14940/) (2022)
- [GLIPv2: Unifying Localization and Vision-Language Understanding](https://mlsanity.com/paper/2206.05836/) (2022)
- [CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation](https://mlsanity.com/paper/2203.10421/) (2022)
- [Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection](https://mlsanity.com/paper/2207.03482/) (2022)
- [Open Vocabulary Object Detection with Pseudo Bounding-Box Labels](https://mlsanity.com/paper/2111.09452/) (2021)
- [Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2303.05892/) (2023)
- [Detecting Everything in the Open World: Towards Universal Object Detection](https://mlsanity.com/paper/2303.11749/) (2023)
- [A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future](https://mlsanity.com/paper/2307.09220/) (2023)
- [Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2104.06601/) (2021)
- [Exemplar Free Class Agnostic Counting](https://mlsanity.com/paper/2205.14212/) (2022)
- [FindIt: Generalized Localization with Natural Language Queries](https://mlsanity.com/paper/2203.17273/) (2022)
- [World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models](https://mlsanity.com/paper/2306.08685/) (2023)
- [Zero-shot Object Detection Through Vision-Language Embedding Alignment](https://mlsanity.com/paper/2109.12066/) (2021)
- [A Survey of Deep Learning for Low-Shot Object Detection](https://mlsanity.com/paper/2112.02814/) (2021)
- [Lesion Guided Explainable Few Weak-shot Medical Report Generation](https://mlsanity.com/paper/2211.08732/) (2022)
- [Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection](https://mlsanity.com/paper/2504.07060/) (2025)
- [Zero-Shot Automatic Annotation and Instance Segmentation using LLM-Generated Datasets: Eliminating Field Imaging and Manual Annotation for Deep Learning Model Development](https://mlsanity.com/paper/2411.11285/) (2024)
- [Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2402.02094/) (2024)
- [Resolving Semantic Confusions for Improved Zero-Shot Detection](https://mlsanity.com/paper/2212.06097/) (2022)
- [NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation](https://mlsanity.com/paper/2401.03771/) (2024)
- [Incrementally Zero-Shot Detection by an Extreme Value Analyzer](https://mlsanity.com/paper/2103.12609/) (2021)
- [Morphable Detector for Object Detection on Demand](https://mlsanity.com/paper/2110.04917/) (2021)
- [HazardNet: Road Debris Detection by Augmentation of Synthetic Models](https://mlsanity.com/paper/2303.07547/) (2023)
- [Zero-sample surface defect detection and classification based on semantic feedback neural network](https://mlsanity.com/paper/2106.07959/) (2021)
- [Weak Novel Categories without Tears: A Survey on Weak-Shot Learning](https://mlsanity.com/paper/2110.02651/) (2021)
- [Dr. Tongue: Sign-Oriented Multi-label Detection for Remote Tongue Diagnosis](https://mlsanity.com/paper/2501.03053/) (2025)

## Abstract (arXiv)

As we move towards large-scale object detection, it is unrealistic to expect annotated training data, in the form of bounding box annotations around objects, for all object classes at sufficient scale, and so methods capable of unseen object detection are required. We propose a novel zero-shot method based on training an end-to-end model that fuses semantic attribute prediction with visual features to propose object bounding boxes for seen and unseen classes. While we utilize semantic features during training, our method is agnostic to semantic information for unseen classes at test-time. Our method retains the efficiency and effectiveness of YOLOv2 for objects seen during training, while improving its performance for novel and unseen objects. The ability of state-of-art detection methods to learn discriminative object features to reject background proposals also limits their performance for unseen objects. We posit that, to detect unseen objects, we must incorporate semantic information into the visual domain so that the learned visual features reflect this information and leads to improved recall rates for unseen objects. We test our method on PASCAL VOC and MS COCO dataset and observed significant improvements on the average precision of unseen classes.