# ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension

arXiv: https://arxiv.org/abs/2204.05991 · HTML: https://mlsanity.com/paper/2204.05991/

## Key facts

- Cited by 120 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 57 references that are in the map.
- First posted on arXiv 12 Apr 2022.

## Builds on (most cited first, 30 of 36)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [True Few-Shot Learning with Language Models](https://mlsanity.com/paper/2105.11447/) (2021)
- [How Much Can CLIP Benefit Vision-and-Language Tasks?](https://mlsanity.com/paper/2107.06383/) (2021)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [MERLOT: Multimodal Neural Script Knowledge Models](https://mlsanity.com/paper/2106.02636/) (2021)
- [CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models](https://mlsanity.com/paper/2109.11797/) (2021)
- [Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications](https://mlsanity.com/paper/2108.02818/) (2021)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Grounding of Textual Phrases in Images by Reconstruction](https://mlsanity.com/paper/1511.03745/) (2015)
- [Modeling Relationships in Referential Expressions with Compositional Modular Networks](https://mlsanity.com/paper/1611.09978/) (2016)
- [Grounding Referring Expressions in Images by Variational Context](https://mlsanity.com/paper/1712.01892/) (2017)
- [Zero-Shot Grounding of Objects from Natural Language Queries](https://mlsanity.com/paper/1908.07129/) (2019)

## Built on by (most cited first, 30 of 120)

- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Visual Spatial Reasoning](https://mlsanity.com/paper/2205.00363/) (2022)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [Alpha-CLIP: A CLIP Model Focusing on Wherever You Want](https://mlsanity.com/paper/2312.03818/) (2023)
- [Text-to-Image Diffusion Models are Zero-Shot Classifiers](https://mlsanity.com/paper/2303.15233/) (2023)
- [Language Conditioned Spatial Relation Reasoning for 3D Object Grounding](https://mlsanity.com/paper/2211.09646/) (2022)
- [VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations](https://mlsanity.com/paper/2207.00221/) (2022)
- [LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning](https://mlsanity.com/paper/2306.01293/) (2023)
- [Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models](https://mlsanity.com/paper/2207.11514/) (2022)
- [UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning](https://mlsanity.com/paper/2505.14231/) (2025)
- [Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding](https://mlsanity.com/paper/2503.06287/) (2025)
- [Perceptual Grouping in Contrastive Vision-Language Models](https://mlsanity.com/paper/2210.09996/) (2022)
- [Fine-Grained Visual Prompting](https://mlsanity.com/paper/2306.04356/) (2023)
- [AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP](https://mlsanity.com/paper/2503.06661/) (2025)
- [Zero-shot Referring Image Segmentation with Global-Local Context Features](https://mlsanity.com/paper/2303.17811/) (2023)
- [OpenBias: Open-set Bias Detection in Text-to-Image Generative Models](https://mlsanity.com/paper/2404.07990/) (2024)
- [VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution](https://mlsanity.com/paper/2306.12424/) (2023)
- [Toward Visual Grounding: A Survey](https://mlsanity.com/paper/2412.20206/) (2024)
- [Modular Visual Question Answering via Code Generation](https://mlsanity.com/paper/2306.05392/) (2023)
- [DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM](https://mlsanity.com/paper/2403.12488/) (2024)
- [Described Object Detection: Liberating Object Detection with Flexible Expressions](https://mlsanity.com/paper/2307.12813/) (2023)
- [MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs](https://mlsanity.com/paper/2410.12332/) (2024)
- [Diffusion Feedback Helps CLIP See Better](https://mlsanity.com/paper/2407.20171/) (2024)
- [GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection](https://mlsanity.com/paper/2304.04521/) (2023)
- [SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion](https://mlsanity.com/paper/2409.17531/) (2024)
- [CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding](https://mlsanity.com/paper/2305.08685/) (2023)

## Abstract (arXiv)

Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are useful for image classification across domains, it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC. We present ReCLIP, a simple but strong zero-shot baseline that repurposes CLIP, a state-of-the-art large-scale model, for ReC. Motivated by the close connection between ReC and CLIP's contrastive pre-training objective, the first component of ReCLIP is a region-scoring method that isolates object proposals via cropping and blurring, and passes them to CLIP. However, through controlled experiments on a synthetic dataset, we find that CLIP is largely incapable of performing spatial reasoning off-the-shelf. Thus, the second component of ReCLIP is a spatial relation resolver that handles several types of spatial relations. We reduce the gap between zero-shot baselines from prior work and supervised models by as much as 29% on RefCOCOg, and on RefGTA (video game imagery), ReCLIP's relative improvement over supervised ReC models trained on real images is 8%.