# Refining CLIP's Spatial Awareness: A Visual-Centric Perspective

arXiv: https://arxiv.org/abs/2504.02328 · HTML: https://mlsanity.com/paper/2504.02328/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 80 references that are in the map.
- First posted on arXiv 3 Apr 2025.

## Builds on (most cited first, 30 of 69)

- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (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)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [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)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model](https://mlsanity.com/paper/2203.14940/) (2022)
- [Scaling Language-Image Pre-training via Masking](https://mlsanity.com/paper/2212.00794/) (2022)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)

## Built on by (most cited first, 13 of 13)

- [Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception](https://mlsanity.com/paper/2508.11256/) (2025)
- [Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation](https://mlsanity.com/paper/2509.15772/) (2025)
- [β-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment](https://mlsanity.com/paper/2512.12678/) (2025)
- [Open-Vocabulary Domain Generalization in Urban-Scene Segmentation](https://mlsanity.com/paper/2602.18853/) (2026)
- [PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignment](https://mlsanity.com/paper/2603.18891/) (2026)
- [Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation](https://mlsanity.com/paper/2511.14271/) (2025)
- [FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding](https://mlsanity.com/paper/2511.14901/) (2025)
- [AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving](https://mlsanity.com/paper/2601.01762/) (2026)
- [XAI-CLIP: ROI-Guided Perturbation Framework for Explainable Medical Image Segmentation in Multimodal Vision-Language Models](https://mlsanity.com/paper/2602.07017/) (2026)
- [UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register](https://mlsanity.com/paper/2605.19622/) (2026)
- [Sparse Attention for Dense Open-Vocabulary Prediction in CLIP](https://mlsanity.com/paper/2607.07135/) (2026)
- [Foveated Probes Recover Localized Binding Information in Vision Foundation Models](https://mlsanity.com/paper/2608.00726/) (2026)
- [DT-LoRA: Reaching Beyond the Tangent Space of Low-Rank Adaptation](https://mlsanity.com/paper/2610.17730/) (2026)

## Abstract (arXiv)

Contrastive Language-Image Pre-training (CLIP) excels in global alignment with language but exhibits limited sensitivity to spatial information, leading to strong performance in zero-shot classification tasks but underperformance in tasks requiring precise spatial understanding. Recent approaches have introduced Region-Language Alignment (RLA) to enhance CLIP's performance in dense multimodal tasks by aligning regional visual representations with corresponding text inputs. However, we find that CLIP ViTs fine-tuned with RLA suffer from notable loss in spatial awareness, which is crucial for dense prediction tasks. To address this, we propose the Spatial Correlation Distillation (SCD) framework, which preserves CLIP's inherent spatial structure and mitigates the above degradation. To further enhance spatial correlations, we introduce a lightweight Refiner that extracts refined correlations directly from CLIP before feeding them into SCD, based on an intriguing finding that CLIP naturally captures high-quality dense features. Together, these components form a robust distillation framework that enables CLIP ViTs to integrate both visual-language and visual-centric improvements, achieving state-of-the-art results across various open-vocabulary dense prediction benchmarks.