# DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception

arXiv: https://arxiv.org/abs/2505.04410 · HTML: https://mlsanity.com/paper/2505.04410/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 78 of its 89 references that are in the map.
- First posted on arXiv 7 May 2025.

## Builds on (most cited first, 30 of 78)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [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)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [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)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [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)

## Built on by (most cited first, 30 of 33)

- [Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe](https://mlsanity.com/paper/2605.03677/) (2026)
- [Mitigating Object Hallucinations via Sentence-Level Early Intervention](https://mlsanity.com/paper/2507.12455/) (2025)
- [FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging](https://mlsanity.com/paper/2602.08024/) (2026)
- [Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior](https://mlsanity.com/paper/2512.06866/) (2025)
- [Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective](https://mlsanity.com/paper/2511.16170/) (2025)
- [PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation](https://mlsanity.com/paper/2603.17520/) (2026)
- [Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM](https://mlsanity.com/paper/2606.26120/) (2026)
- [Open-Vocabulary Domain Generalization in Urban-Scene Segmentation](https://mlsanity.com/paper/2602.18853/) (2026)
- [Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning](https://mlsanity.com/paper/2505.11945/) (2025)
- [NoOVD: Novel Category Discovery and Embedding for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2603.21069/) (2026)
- [ConInfer: Context-Aware Inference for Training-Free Open-Vocabulary Remote Sensing Segmentation](https://mlsanity.com/paper/2603.29271/) (2026)
- [The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models](https://mlsanity.com/paper/2601.08876/) (2026)
- [Orthogonalized Multimodal Contrastive Learning with Asymmetric Masking for Structured Representations](https://mlsanity.com/paper/2602.14983/) (2026)
- [Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic Segmentation](https://mlsanity.com/paper/2603.21386/) (2026)
- [ODOV: Benchmark the Open-Domain Open-Vocabulary Object Detection](https://mlsanity.com/paper/2508.01253/) (2025)
- [Multimodal Dataset Distillation via Phased Teacher Models](https://mlsanity.com/paper/2603.25388/) (2026)
- [Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models](https://mlsanity.com/paper/2604.11576/) (2026)
- [FitPro: A Zero-Shot Framework for Interactive Text-based Pedestrian Retrieval in Open World](https://mlsanity.com/paper/2509.16674/) (2025)
- [Auto-Vocabulary 3D Object Detection](https://mlsanity.com/paper/2512.16077/) (2025)
- [Data-Efficient Semantic Segmentation of 3D Point Clouds via Open-Vocabulary Image Segmentation-based Pseudo-Labeling](https://mlsanity.com/paper/2604.11007/) (2026)
- [SENSE: Stereo OpEN Vocabulary SEmantic Segmentation](https://mlsanity.com/paper/2604.15946/) (2026)
- [Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors](https://mlsanity.com/paper/2604.17914/) (2026)
- [MASRA: MLLM-Assisted Semantic-Relational Consistent Alignment for Video Temporal Grounding](https://mlsanity.com/paper/2605.03398/) (2026)
- [Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignment](https://mlsanity.com/paper/2605.17341/) (2026)
- [TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval](https://mlsanity.com/paper/2605.18434/) (2026)
- [COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection](https://mlsanity.com/paper/2605.27116/) (2026)
- [LV-OSD: Language-Vision-Complementary Open-Set Object Detection](https://mlsanity.com/paper/2605.28271/) (2026)
- [ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification](https://mlsanity.com/paper/2606.09360/) (2026)
- [SynCLIP: Synonym-Coherent Language-Image Pretraining for Robust Open-Vocabulary Dense Perception](https://mlsanity.com/paper/2607.11008/) (2026)
- [Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition](https://mlsanity.com/paper/2607.19889/) (2026)

## Abstract (arXiv)

Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have shown promise in open-vocabulary tasks, their direct application to dense prediction often leads to suboptimal performance due to limitations in local feature representation. In this work, we present our observation that CLIP's image tokens struggle to effectively aggregate information from spatially or semantically related regions, resulting in features that lack local discriminability and spatial consistency. To address this issue, we propose DeCLIP, a novel framework that enhances CLIP by decoupling the self-attention module to obtain ``content'' and ``context'' features respectively. The ``content'' features are aligned with image crop representations to improve local discriminability, while ``context'' features learn to retain the spatial correlations under the guidance of vision foundation models, such as DINO. Extensive experiments demonstrate that DeCLIP significantly outperforms existing methods across multiple open-vocabulary dense prediction tasks, including object detection and semantic segmentation. Code is available at textcolormagentahttps://github.com/xiaomoguhz/DeCLIP.