mlsanityData to 14 Oct 2026

Fine-Grained Zero-Shot Object Detection

arXiv 2507.10358 ↗First posted 14 Jul 2025cs.CVcited by 8

Not on the map. Why?

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.

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

32 of 61 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2016Generative Adversarial Text to Image Synthesiscited by 735
  6. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 577
  7. 2019DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesiscited by 308
  8. 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
  9. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  10. 2018Zero-Shot Object Detectioncited by 189
  11. 2021AP-10K: A Benchmark for Animal Pose Estimation in the Wildcited by 123
  12. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
20 more
  1. 2025HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animationcited by 59
  2. 2019Dont Even Look Once: Synthesizing Features for Zero-Shot Detectioncited by 58
  3. 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
  4. 2018Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Conceptscited by 48
  5. 2024Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesiscited by 48
  6. 2021Zero-Shot Instance Segmentationcited by 40
  7. 2020Synthesizing the Unseen for Zero-shot Object Detectioncited by 32
  8. 2020Background Learnable Cascade for Zero-Shot Object Detectioncited by 31
  9. 2020GTNet: Generative Transfer Network for Zero-Shot Object Detectioncited by 25
  10. 2019Fine-grained Recognition: Accounting for Subtle Differences between Similar Classescited by 24
  11. 2025Multimodal LLMs Can Reason about Aesthetics in Zero-Shotcited by 14
  12. 2024Generative Regression Based Watch Time Prediction for Short-Video Recommendationcited by 13
  13. 2025Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusioncited by 12
  14. 2025VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximizationcited by 12
  15. 2017Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localizationcited by 9
  16. 2022Hierarchical Few-Shot Object Detection: Problem, Benchmark and Methodcited by 8
  17. 2023SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detectioncited by 6
  18. 2019Hierarchical Prototype Learning for Zero-Shot Recognitioncited by 5
  19. 2023Meta-ZSDETR: Zero-shot DETR with Meta-learningcited by 2
  20. 2024PixelFade: Privacy-preserving Person Re-identification with Noise-guided Progressive Replacementcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026RAM: Recover Any 3D Human Motion in-the-Wildcited by 12
  2. 2026RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformercited by 3
  3. 2026RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360degImage Quality Assessmentcited by 2
  4. 2025FSP-DETR: Few-Shot Prototypical Parasitic Ova Detectioncited by 1
  5. 2026DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regressioncited by 1
  6. 2026Learnable Instance Attention Filtering for Adaptive Detector Distillationcited by 0
  7. 2026FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priorscited by 0
  8. 2026Hierarchical Fine-Grained Aerial Object Detectioncited by 0