# Synthesizing the Unseen for Zero-shot Object Detection

arXiv: https://arxiv.org/abs/2010.09425 · HTML: https://mlsanity.com/paper/2010.09425/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 30 of 32)

- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models](https://mlsanity.com/paper/2209.15639/) (2022)
- [Aligning Bag of Regions for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2302.13996/) (2023)
- [Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2305.07011/) (2023)
- [A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future](https://mlsanity.com/paper/2307.09220/) (2023)
- [MedFuse: Multi-modal fusion with clinical time-series data and chest X-ray images](https://mlsanity.com/paper/2207.07027/) (2022)
- [Zero-shot object goal visual navigation](https://mlsanity.com/paper/2206.07423/) (2022)
- [Contrastive Feature Masking Open-Vocabulary Vision Transformer](https://mlsanity.com/paper/2309.00775/) (2023)
- [Semantics-Guided Contrastive Network for Zero-Shot Object detection](https://mlsanity.com/paper/2109.06062/) (2021)
- [Semantic Diversity Learning for Zero-Shot Multi-label Classification](https://mlsanity.com/paper/2105.05926/) (2021)
- [Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection](https://mlsanity.com/paper/2304.05096/) (2023)
- [Robust Region Feature Synthesizer for Zero-Shot Object Detection](https://mlsanity.com/paper/2201.00103/) (2022)
- [Generative Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2101.11606/) (2021)
- [Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2211.00849/) (2022)
- [Zero-Shot Aerial Object Detection with Visual Description Regularization](https://mlsanity.com/paper/2402.18233/) (2024)
- [Zero-shot Object Detection Through Vision-Language Embedding Alignment](https://mlsanity.com/paper/2109.12066/) (2021)
- [Fine-Grained Zero-Shot Object Detection](https://mlsanity.com/paper/2507.10358/) (2025)
- [A Survey of Deep Learning for Low-Shot Object Detection](https://mlsanity.com/paper/2112.02814/) (2021)
- [On Hyperbolic Embeddings in 2D Object Detection](https://mlsanity.com/paper/2203.08049/) (2022)
- [SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection](https://mlsanity.com/paper/2310.04689/) (2023)
- [Multi-Label Generalized Zero Shot Learning for the Classification of Disease in Chest Radiographs](https://mlsanity.com/paper/2107.06563/) (2021)
- [Frustratingly Simple but Effective Zero-shot Detection and Segmentation: Analysis and a Strong Baseline](https://mlsanity.com/paper/2302.07319/) (2023)
- [Balanced Classification: A Unified Framework for Long-Tailed Object Detection](https://mlsanity.com/paper/2308.02213/) (2023)
- [Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection](https://mlsanity.com/paper/2402.09242/) (2024)
- [AssemAI: Interpretable Image-Based Anomaly Detection for Manufacturing Pipelines](https://mlsanity.com/paper/2408.02181/) (2024)
- [Resolving Semantic Confusions for Improved Zero-Shot Detection](https://mlsanity.com/paper/2212.06097/) (2022)
- [Meta-ZSDETR: Zero-shot DETR with Meta-learning](https://mlsanity.com/paper/2308.09540/) (2023)
- [Review of Zero-Shot and Few-Shot AI Algorithms in The Medical Domain](https://mlsanity.com/paper/2406.16143/) (2024)
- [OASIS: Open-world Adaptive Self-supervised and Imbalanced-aware System](https://mlsanity.com/paper/2508.16656/) (2025)
- [ChatGPT-guided Semantics for Zero-shot Learning](https://mlsanity.com/paper/2310.11657/) (2023)

## Abstract (arXiv)

The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference. However, since the unseen objects are never visualized during training, the detection model is skewed towards seen content, thereby labeling unseen as background or a seen class. In this work, we propose to synthesize visual features for unseen classes, so that the model learns both seen and unseen objects in the visual domain. Consequently, the major challenge becomes, how to accurately synthesize unseen objects merely using their class semantics? Towards this ambitious goal, we propose a novel generative model that uses class-semantics to not only generate the features but also to discriminatively separate them. Further, using a unified model, we ensure the synthesized features have high diversity that represents the intra-class differences and variable localization precision in the detected bounding boxes. We test our approach on three object detection benchmarks, PASCAL VOC, MSCOCO, and ILSVRC detection, under both conventional and generalized settings, showing impressive gains over the state-of-the-art methods. Our codes are available at https://github.com/nasir6/zero_shot_detection.