# ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation

arXiv: https://arxiv.org/abs/2408.04883 · HTML: https://mlsanity.com/paper/2408.04883/

## Key facts

- Cited by 111 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 74 references that are in the map.
- First posted on arXiv 9 Aug 2024.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (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)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference](https://mlsanity.com/paper/2312.01597/) (2023)
- [SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2211.14813/) (2022)
- [Open-Vocabulary Universal Image Segmentation with MaskCLIP](https://mlsanity.com/paper/2208.08984/) (2022)
- [CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction](https://mlsanity.com/paper/2310.01403/) (2023)
- [ReCo: Retrieve and Co-segment for Zero-shot Transfer](https://mlsanity.com/paper/2206.07045/) (2022)
- [A Closer Look at the Explainability of Contrastive Language-Image Pre-training](https://mlsanity.com/paper/2304.05653/) (2023)
- [CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation](https://mlsanity.com/paper/2312.12359/) (2023)
- [Grounding Everything: Emerging Localization Properties in Vision-Language Transformers](https://mlsanity.com/paper/2312.00878/) (2023)
- [Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter](https://mlsanity.com/paper/2309.02773/) (2023)
- [Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively](https://mlsanity.com/paper/2401.02955/) (2024)
- [SILC: Improving Vision Language Pretraining with Self-Distillation](https://mlsanity.com/paper/2310.13355/) (2023)
- [Hierarchical Open-vocabulary Universal Image Segmentation](https://mlsanity.com/paper/2307.00764/) (2023)
- [ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency](https://mlsanity.com/paper/2302.10307/) (2023)

## Built on by (most cited first, 30 of 111)

- [DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment](https://mlsanity.com/paper/2412.16334/) (2024)
- [Text4Seg: Reimagining Image Segmentation as Text Generation](https://mlsanity.com/paper/2410.09855/) (2024)
- [Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2411.19331/) (2024)
- [Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation](https://mlsanity.com/paper/2411.09219/) (2024)
- [CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2411.10086/) (2024)
- [Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2411.15869/) (2024)
- [ResCLIP: Residual Attention for Training-free Dense Vision-language Inference](https://mlsanity.com/paper/2411.15851/) (2024)
- [SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images](https://mlsanity.com/paper/2410.01768/) (2024)
- [Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2411.17150/) (2024)
- [Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers](https://mlsanity.com/paper/2509.18096/) (2025)
- [LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models](https://mlsanity.com/paper/2504.14032/) (2025)
- [DynamicEarth: How Far are We from Open-Vocabulary Change Detection?](https://mlsanity.com/paper/2501.12931/) (2025)
- [LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation](https://mlsanity.com/paper/2503.19777/) (2025)
- [FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering](https://mlsanity.com/paper/2506.21710/) (2025)
- [CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2411.13836/) (2024)
- [Exploring the Underwater World Segmentation without Extra Training](https://mlsanity.com/paper/2511.07923/) (2025)
- [SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images](https://mlsanity.com/paper/2512.08730/) (2025)
- [DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks](https://mlsanity.com/paper/2409.06809/) (2024)
- [Vision Transformers Need More Than Registers](https://mlsanity.com/paper/2602.22394/) (2026)
- [Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2508.20265/) (2025)
- [Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception](https://mlsanity.com/paper/2508.11256/) (2025)
- [Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction](https://mlsanity.com/paper/2412.06244/) (2024)
- [ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2506.21233/) (2025)
- [ViLU: Learning Vision-Language Uncertainties for Failure Prediction](https://mlsanity.com/paper/2507.07620/) (2025)
- [Training-Free Class Purification for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2508.00557/) (2025)
- [Text4Seg++: Advancing Image Segmentation via Generative Language Modeling](https://mlsanity.com/paper/2509.06321/) (2025)
- [Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images](https://mlsanity.com/paper/2508.18067/) (2025)
- [TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models](https://mlsanity.com/paper/2505.23769/) (2025)
- [FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text](https://mlsanity.com/paper/2507.10095/) (2025)
- [NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering](https://mlsanity.com/paper/2511.18452/) (2025)

## Abstract (arXiv)

Open-vocabulary semantic segmentation requires models to effectively integrate visual representations with open-vocabulary semantic labels. While Contrastive Language-Image Pre-training (CLIP) models shine in recognizing visual concepts from text, they often struggle with segment coherence due to their limited localization ability. In contrast, Vision Foundation Models (VFMs) excel at acquiring spatially consistent local visual representations, yet they fall short in semantic understanding. This paper introduces ProxyCLIP, an innovative framework designed to harmonize the strengths of both CLIP and VFMs, facilitating enhanced open-vocabulary semantic segmentation. ProxyCLIP leverages the spatial feature correspondence from VFMs as a form of proxy attention to augment CLIP, thereby inheriting the VFMs' robust local consistency and maintaining CLIP's exceptional zero-shot transfer capacity. We propose an adaptive normalization and masking strategy to get the proxy attention from VFMs, allowing for adaptation across different VFMs. Remarkably, as a training-free approach, ProxyCLIP significantly improves the average mean Intersection over Union (mIoU) across eight benchmarks from 40.3 to 44.4, showcasing its exceptional efficacy in bridging the gap between spatial precision and semantic richness for the open-vocabulary segmentation task.