# CLIP-Guided Source-Free Object Detection in Aerial Images

arXiv: https://arxiv.org/abs/2401.05168 · HTML: https://mlsanity.com/paper/2401.05168/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 17 references that are in the map.
- First posted on arXiv 10 Jan 2024.

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15793/) (2022)
- [Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering](https://mlsanity.com/paper/2206.02721/) (2022)
- [Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization](https://mlsanity.com/paper/2309.14949/) (2023)
- [Few-Shot Object Detection via Variational Feature Aggregation](https://mlsanity.com/paper/2301.13411/) (2023)
- [Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training](https://mlsanity.com/paper/2303.10856/) (2023)
- [On the Robustness of Object Detection Models on Aerial Images](https://mlsanity.com/paper/2308.15378/) (2023)
- [Transformation-Invariant Network for Few-Shot Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2303.06817/) (2023)
- [Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Images](https://mlsanity.com/paper/2310.05498/) (2023)

## Built on by (most cited first, 4 of 4)

- [PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images](https://mlsanity.com/paper/2409.13401/) (2024)
- [Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection](https://mlsanity.com/paper/2504.20498/) (2025)
- [Few-Shot Remote Sensing Image Scene Classification with CLIP and Prompt Learning](https://mlsanity.com/paper/2510.24321/) (2025)
- [CLIP-Joint-Detect: End-to-End Joint Training of Object Detectors with Contrastive Vision-Language Supervision](https://mlsanity.com/paper/2512.22969/) (2025)

## Abstract (arXiv)

Domain adaptation is crucial in aerial imagery, as the visual representation of these images can significantly vary based on factors such as geographic location, time, and weather conditions. Additionally, high-resolution aerial images often require substantial storage space and may not be readily accessible to the public. To address these challenges, we propose a novel Source-Free Object Detection (SFOD) method. Specifically, our approach begins with a self-training framework, which significantly enhances the performance of baseline methods. To alleviate the noisy labels in self-training, we utilize Contrastive Language-Image Pre-training (CLIP) to guide the generation of pseudo-labels, termed CLIP-guided Aggregation (CGA). By leveraging CLIP's zero-shot classification capability, we aggregate its scores with the original predicted bounding boxes, enabling us to obtain refined scores for the pseudo-labels. To validate the effectiveness of our method, we constructed two new datasets from different domains based on the DIOR dataset, named DIOR-C and DIOR-Cloudy. Experimental results demonstrate that our method outperforms other comparative algorithms. The code is available at https://github.com/Lans1ng/SFOD-RS.