# ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detection

arXiv: https://arxiv.org/abs/2603.12409 · HTML: https://mlsanity.com/paper/2603.12409/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 40 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Git Re-Basin: Merging Models modulo Permutation Symmetries](https://mlsanity.com/paper/2209.04836/) (2022)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [VeRA: Vector-based Random Matrix Adaptation](https://mlsanity.com/paper/2310.11454/) (2023)
- [PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models](https://mlsanity.com/paper/2404.02948/) (2024)
- [Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models](https://mlsanity.com/paper/2305.12827/) (2023)
- [Open-Vocabulary DETR with Conditional Matching](https://mlsanity.com/paper/2203.11876/) (2022)
- [Revisiting Model Stitching to Compare Neural Representations](https://mlsanity.com/paper/2106.07682/) (2021)
- [ZipIt! Merging Models from Different Tasks without Training](https://mlsanity.com/paper/2305.03053/) (2023)
- [Modular Deep Learning](https://mlsanity.com/paper/2302.11529/) (2023)
- [SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors](https://mlsanity.com/paper/2405.19597/) (2024)
- [VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks](https://mlsanity.com/paper/2405.15179/) (2024)
- [ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing](https://mlsanity.com/paper/2210.11539/) (2022)
- [Stitchable Neural Networks](https://mlsanity.com/paper/2302.06586/) (2023)
- [Self Paced Deep Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1605.07651/) (2016)
- [CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection](https://mlsanity.com/paper/2403.19278/) (2024)
- [Update Your Transformer to the Latest Release: Re-Basin of Task Vectors](https://mlsanity.com/paper/2505.22697/) (2025)
- [Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection](https://mlsanity.com/paper/2403.01680/) (2024)
- [Model Stitching: Looking For Functional Similarity Between Representations](https://mlsanity.com/paper/2303.11277/) (2023)

## Abstract (arXiv)

Although recent Open-Vocabulary Object Detection architectures, such as Grounding DINO, demonstrate strong zero-shot capabilities, their performance degrades significantly under domain shifts. Moreover, many domains of practical interest, such as nighttime or foggy scenes, lack large annotated datasets, preventing direct fine-tuning. In this paper, we introduce Aligned Basis Relocation for Adaptation(ABRA), a method that transfers class-specific detection knowledge from a labeled source domain to a target domain where no training images containing these classes are accessible. ABRA formulates this adaptation as a geometric transport problem in the weight space of a pretrained detector, aligning source and target domain experts to transport class-specific knowledge. Extensive experiments across challenging domain shifts demonstrate that ABRA successfully teleports class-level specialization under multiple adverse conditions. Our code will be made public upon acceptance.