# Fine-Grained Zero-Shot Object Detection

arXiv: https://arxiv.org/abs/2507.10358 · HTML: https://mlsanity.com/paper/2507.10358/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 61 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (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)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis](https://mlsanity.com/paper/1904.01310/) (2019)
- [StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1710.10916/) (2017)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [Zero-Shot Object Detection](https://mlsanity.com/paper/1804.04340/) (2018)
- [AP-10K: A Benchmark for Animal Pose Estimation in the Wild](https://mlsanity.com/paper/2108.12617/) (2021)
- [Few-Shot Object Detection with Fully Cross-Transformer](https://mlsanity.com/paper/2203.15021/) (2022)
- [HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation](https://mlsanity.com/paper/2503.18860/) (2025)
- [Dont Even Look Once: Synthesizing Features for Zero-Shot Detection](https://mlsanity.com/paper/1911.07933/) (2019)
- [HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning](https://mlsanity.com/paper/2109.15163/) (2021)
- [Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts](https://mlsanity.com/paper/1803.06049/) (2018)
- [Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis](https://mlsanity.com/paper/2402.18078/) (2024)
- [Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2104.06601/) (2021)
- [Synthesizing the Unseen for Zero-shot Object Detection](https://mlsanity.com/paper/2010.09425/) (2020)
- [Background Learnable Cascade for Zero-Shot Object Detection](https://mlsanity.com/paper/2010.04502/) (2020)
- [GTNet: Generative Transfer Network for Zero-Shot Object Detection](https://mlsanity.com/paper/2001.06812/) (2020)
- [Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes](https://mlsanity.com/paper/1912.06842/) (2019)
- [Multimodal LLMs Can Reason about Aesthetics in Zero-Shot](https://mlsanity.com/paper/2501.09012/) (2025)
- [Generative Regression Based Watch Time Prediction for Short-Video Recommendation](https://mlsanity.com/paper/2412.20211/) (2024)
- [Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion](https://mlsanity.com/paper/2504.00430/) (2025)
- [VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization](https://mlsanity.com/paper/2505.10917/) (2025)
- [Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localization](https://mlsanity.com/paper/1710.01168/) (2017)
- [Hierarchical Few-Shot Object Detection: Problem, Benchmark and Method](https://mlsanity.com/paper/2210.03940/) (2022)
- [SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection](https://mlsanity.com/paper/2310.04689/) (2023)
- [Hierarchical Prototype Learning for Zero-Shot Recognition](https://mlsanity.com/paper/1910.11671/) (2019)

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

- [RAM: Recover Any 3D Human Motion in-the-Wild](https://mlsanity.com/paper/2603.19929/) (2026)
- [RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer](https://mlsanity.com/paper/2603.14290/) (2026)
- [RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360degImage Quality Assessment](https://mlsanity.com/paper/2603.14297/) (2026)
- [FSP-DETR: Few-Shot Prototypical Parasitic Ova Detection](https://mlsanity.com/paper/2510.09583/) (2025)
- [DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression](https://mlsanity.com/paper/2606.07599/) (2026)
- [Learnable Instance Attention Filtering for Adaptive Detector Distillation](https://mlsanity.com/paper/2603.26088/) (2026)
- [FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors](https://mlsanity.com/paper/2606.01352/) (2026)
- [Hierarchical Fine-Grained Aerial Object Detection](https://mlsanity.com/paper/2606.16448/) (2026)

## Abstract (arXiv)

Zero-shot object detection (ZSD) aims to leverage semantic descriptions to localize and recognize objects of both seen and unseen classes. Existing ZSD works are mainly coarse-grained object detection, where the classes are visually quite different, thus are relatively easy to distinguish. However, in real life we often have to face fine-grained object detection scenarios, where the classes are too similar to be easily distinguished. For example, detecting different kinds of birds, fishes, and flowers. In this paper, we propose and solve a new problem called Fine-Grained Zero-Shot Object Detection (FG-ZSD for short), which aims to detect objects of different classes with minute differences in details under the ZSD paradigm. We develop an effective method called MSHC for the FG-ZSD task, which is based on an improved two-stage detector and employs a multi-level semantics-aware embedding alignment loss, ensuring tight coupling between the visual and semantic spaces. Considering that existing ZSD datasets are not suitable for the new FG-ZSD task, we build the first FG-ZSD benchmark dataset FGZSD-Birds, which contains 148,820 images falling into 36 orders, 140 families, 579 genera and 1432 species. Extensive experiments on FGZSD-Birds show that our method outperforms existing ZSD models.