# Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning

arXiv: https://arxiv.org/abs/2312.02021 · HTML: https://mlsanity.com/paper/2312.02021/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 95 of its 119 references that are in the map.
- First posted on arXiv 4 Dec 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 95)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)

## Built on by (most cited first, 20 of 20)

- [Textual Query-Driven Mask Transformer for Domain Generalized Segmentation](https://mlsanity.com/paper/2407.09033/) (2024)
- [FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation](https://mlsanity.com/paper/2503.17940/) (2025)
- [Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art](https://mlsanity.com/paper/2503.08695/) (2025)
- [VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detection](https://mlsanity.com/paper/2409.17330/) (2024)
- [The Missing Point in Vision Transformers for Universal Image Segmentation](https://mlsanity.com/paper/2505.19795/) (2025)
- [VFM-UDA++: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2503.10685/) (2025)
- [Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation](https://mlsanity.com/paper/2507.11955/) (2025)
- [Optimization of DNN-based HSI Segmentation FPGA-based SoC for ADS: A Practical Approach](https://mlsanity.com/paper/2507.16556/) (2025)
- [Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts](https://mlsanity.com/paper/2510.19487/) (2025)
- [Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation](https://mlsanity.com/paper/2511.07238/) (2025)
- [XAMI -- A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Images](https://mlsanity.com/paper/2406.17323/) (2024)
- [Domain Generalization through Attenuation of Domain-Specific Information](https://mlsanity.com/paper/2504.06781/) (2025)
- [Boosting Single-domain Generalized Object Detection via Vision-Language Knowledge Interaction](https://mlsanity.com/paper/2504.19086/) (2025)
- [Bridging Clear and Adverse Driving Conditions](https://mlsanity.com/paper/2508.13592/) (2025)
- [Learning to Detect Label Errors by Making Them: A Method for Segmentation and Object Detection Datasets](https://mlsanity.com/paper/2508.17930/) (2025)
- [Domain Generalization for Semantic Segmentation: A Survey](https://mlsanity.com/paper/2510.03540/) (2025)
- [Out-of-Distribution Object Detection in Street Scenes via Synthetic Outlier Exposure and Transfer Learning](https://mlsanity.com/paper/2603.16122/) (2026)
- [RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2603.28142/) (2026)
- [Combining Foundation Model Confidence and Monocular Depth for Training-Free Out-of-Distribution Segmentation](https://mlsanity.com/paper/2609.22896/) (2026)
- [MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentation](https://mlsanity.com/paper/2609.39681/) (2026)

## Abstract (arXiv)

Domain generalization (DG) remains a significant challenge for perception based on deep neural networks (DNNs), where domain shifts occur due to synthetic data, lighting, weather, or location changes. Vision-language models (VLMs) marked a large step for the generalization capabilities and have been already applied to various tasks. Very recently, first approaches utilized VLMs for domain generalized segmentation and object detection and obtained strong generalization. However, all these approaches rely on complex modules, feature augmentation frameworks or additional models. Surprisingly and in contrast to that, we found that simple fine-tuning of vision-language pre-trained models yields competitive or even stronger generalization results while being extremely simple to apply. Moreover, we found that vision-language pre-training consistently provides better generalization than the previous standard of vision-only pre-training. This challenges the standard of using ImageNet-based transfer learning for domain generalization. Fully fine-tuning a vision-language pre-trained model is capable of reaching the domain generalization SOTA when training on the synthetic GTA5 dataset. Moreover, we confirm this observation for object detection on a novel synthetic-to-real benchmark. We further obtain superior generalization capabilities by reaching 77.9% mIoU on the popular Cityscapes-to-ACDC benchmark. We also found improved in-domain generalization, leading to an improved SOTA of 86.4% mIoU on the Cityscapes test set marking the first place on the leaderboard.