# Teaching in adverse scenes: a statistically feedback-driven threshold and mask adjustment teacher-student framework for object detection in UAV images under adverse scenes

arXiv: https://arxiv.org/abs/2506.11175 · HTML: https://mlsanity.com/paper/2506.11175/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 21 of 21)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [FCOS: A simple and strong anchor-free object detector](https://mlsanity.com/paper/2006.09214/) (2020)
- [Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning](https://mlsanity.com/paper/2003.02437/) (2020)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training](https://mlsanity.com/paper/2004.06002/) (2020)
- [Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions](https://mlsanity.com/paper/2112.08088/) (2021)
- [An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing](https://mlsanity.com/paper/1810.12000/) (2018)
- [CrossKD: Cross-Head Knowledge Distillation for Object Detection](https://mlsanity.com/paper/2306.11369/) (2023)
- [Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers](https://mlsanity.com/paper/2107.12636/) (2021)
- [Cross Domain Object Detection by Target-Perceived Dual Branch Distillation](https://mlsanity.com/paper/2205.01291/) (2022)
- [Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images](https://mlsanity.com/paper/2303.14488/) (2023)
- [YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection](https://mlsanity.com/paper/2308.05480/) (2023)
- [Improving Transferability for Domain Adaptive Detection Transformers](https://mlsanity.com/paper/2204.14195/) (2022)
- [Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning](https://mlsanity.com/paper/2306.01598/) (2023)
- [OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images](https://mlsanity.com/paper/2304.11805/) (2023)
- [Boundary-semantic collaborative guidance network with dual-stream feedback mechanism for salient object detection in optical remote sensing imagery](https://mlsanity.com/paper/2303.02867/) (2023)
- [Boosting Semi-Supervised Object Detection in Remote Sensing Images With Active Teaching](https://mlsanity.com/paper/2402.18958/) (2024)
- [DREB-Net: Dual-stream Restoration Embedding Blur-feature Fusion Network for High-mobility UAV Object Detection](https://mlsanity.com/paper/2410.17822/) (2024)

## Built on by (most cited first, 1 of 1)

- [Adaptive Image Zoom-in with Bounding Box Transformation for UAV Object Detection](https://mlsanity.com/paper/2602.07512/) (2026)

## Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) has shown promise in effectively alleviating the performance degradation caused by domain gaps between source and target domains, and it can potentially be generalized to UAV object detection in adverse scenes. However, existing UDA studies are based on natural images or clear UAV imagery, and research focused on UAV imagery in adverse conditions is still in its infancy. Moreover, due to the unique perspective of UAVs and the interference from adverse conditions, these methods often fail to accurately align features and are influenced by limited or noisy pseudo-labels. To address this, we propose the first benchmark for UAV object detection in adverse scenes, the Statistical Feedback-Driven Threshold and Mask Adjustment Teacher-Student Framework (SF-TMAT). Specifically, SF-TMAT introduces a design called Dynamic Step Feedback Mask Adjustment Autoencoder (DSFMA), which dynamically adjusts the mask ratio and reconstructs feature maps by integrating training progress and loss feedback. This approach dynamically adjusts the learning focus at different training stages to meet the model's needs for learning features at varying levels of granularity. Additionally, we propose a unique Variance Feedback Smoothing Threshold (VFST) strategy, which statistically computes the mean confidence of each class and dynamically adjusts the selection threshold by incorporating a variance penalty term. This strategy improves the quality of pseudo-labels and uncovers potentially valid labels, thus mitigating domain bias. Extensive experiments demonstrate the superiority and generalization capability of the proposed SF-TMAT in UAV object detection under adverse scene conditions. The Code is released at https://github.com/ChenHuyoo .