# Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection

arXiv: https://arxiv.org/abs/2603.18541 · HTML: https://mlsanity.com/paper/2603.18541/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 47 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Segmentation-Based Deep-Learning Approach for Surface-Defect Detection](https://mlsanity.com/paper/1903.08536/) (2019)
- [What Do Self-Supervised Vision Transformers Learn?](https://mlsanity.com/paper/2305.00729/) (2023)
- [A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis](https://mlsanity.com/paper/2008.12603/) (2020)
- [Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation](https://mlsanity.com/paper/2210.04524/) (2022)
- [Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector](https://mlsanity.com/paper/2402.03094/) (2024)
- [Few-shot Adaptive Faster R-CNN](https://mlsanity.com/paper/1903.09372/) (2019)
- [Domain-Adaptive Few-Shot Learning](https://mlsanity.com/paper/2003.08626/) (2020)
- [Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2403.00567/) (2024)
- [AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection](https://mlsanity.com/paper/2209.10904/) (2022)
- [NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli](https://mlsanity.com/paper/2405.02814/) (2024)
- [Compositional Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2405.17022/) (2024)
- [CD-FSOD: A Benchmark for Cross-domain Few-shot Object Detection](https://mlsanity.com/paper/2210.05311/) (2022)
- [Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection](https://mlsanity.com/paper/2506.05872/) (2025)
- [Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning](https://mlsanity.com/paper/2507.09183/) (2025)
- [Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2408.13373/) (2024)
- [Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2603.05235/) (2026)
- [Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning](https://mlsanity.com/paper/2512.08606/) (2025)
- [Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning](https://mlsanity.com/paper/2603.13341/) (2026)
- [Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment](https://mlsanity.com/paper/2603.17655/) (2026)

## Built on by (most cited first, 2 of 2)

- [Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection](https://mlsanity.com/paper/2608.04394/) (2026)
- [The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering](https://mlsanity.com/paper/2608.04589/) (2026)

## Abstract (arXiv)

Cross-domain few-shot object detection (CD-FSOD) aims to adapt pretrained detectors from a source domain to target domains with limited annotations, suffering from severe domain shifts and data scarcity problems. In this work, we find a previously overlooked phenomenon: models exhibit dispersed and unfocused attention in target domains, leading to imprecise localization and redundant predictions, just like a human cannot focus on visual objects. Therefore, we call it the target-domain Astigmatism problem. Analysis on attention distances across transformer layers reveals that regular fine-tuning inherently shows a trend to remedy this problem, but results are still far from satisfactory, which we aim to enhance in this paper. Biologically inspired by the human fovea-style visual system, we enhance the fine-tuning's inherent trend through a center-periphery attention refinement framework, which contains (1) a Positive Pattern Refinement module to reshape attention toward semantic objects using class-specific prototypes, simulating the visual center region; (2) a Negative Context Modulation module to enhance boundary discrimination by modeling background context, simulating the visual periphery region; and (3) a Textual Semantic Alignment module to strengthen center-periphery distinction through cross-modal cues. Our bio-inspired approach transforms astigmatic attention into focused patterns, substantially improving adaptation to target domains. Experiments on six challenging CD-FSOD benchmarks consistently demonstrate improved detection accuracy and establish new state-of-the-art results.