mlsanityData to 7 Oct 2026

ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues

arXiv 2201.06696 ↗First posted 18 Jan 2022cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

Object proposal generation is an important and fundamental task in computer vision. In this paper, we propose ProposalCLIP, a method towards unsupervised open-category object proposal generation. Unlike previous works which require a large number of bounding box annotations and/or can only generate proposals for limited object categories, our ProposalCLIP is able to predict proposals for a large variety of object categories without annotations, by exploiting CLIP (contrastive language-image pre-training) cues. Firstly, we analyze CLIP for unsupervised open-category proposal generation and design an objectness score based on our empirical analysis on proposal selection. Secondly, a graph-based merging module is proposed to solve the limitations of CLIP cues and merge fragmented proposals. Finally, we present a proposal regression module that extracts pseudo labels based on CLIP cues and trains a lightweight network to further refine proposals. Extensive experiments on PASCAL VOC, COCO and Visual Genome datasets show that our ProposalCLIP can better generate proposals than previous state-of-the-art methods. Our ProposalCLIP also shows benefits for downstream tasks, such as unsupervised object detection.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 18 Jan 2022.

Builds on

36 of 52 references.

References · 36

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2017Mask R-CNNcited by 7,259
  9. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  12. 2015Fast R-CNNcited by 2,930
24 more
  1. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  2. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  3. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  4. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  5. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  6. 2018MAttNet: Modular Attention Network for Referring Expression Comprehensioncited by 427
  7. 2020Open-Vocabulary Object Detection Using Captionscited by 427
  8. 2021Towards Open World Object Detectioncited by 297
  9. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  10. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  11. 2020BlendMask: Top-Down Meets Bottom-Up for Instance Segmentationcited by 144
  12. 2015Natural Language Object Retrievalcited by 124
  13. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  14. 2021MDMMT: Multidomain Multimodal Transformer for Video Retrievalcited by 78
  15. 2020Toward unsupervised, multi-object discovery in large-scale image collectionscited by 65
  16. 2021LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrievalcited by 44
  17. 2020Concept Generalization in Visual Representation Learningcited by 35
  18. 2017Deep Self-Taught Learning for Weakly Supervised Object Localizationcited by 27
  19. 2020Diverse Image Captioning with Context-Object Split Latent Spacescited by 22
  20. 2021Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillationcited by 22
  21. 2017Soft Proposal Networks for Weakly Supervised Object Localizationcited by 21
  22. 2015DeepBox: Learning Objectness with Convolutional Networkscited by 14
  23. 2021Connecting Language and Vision for Natural Language-Based Vehicle Retrievalcited by 12
  24. 2015Sequential Optimization for Efficient High-Quality Object Proposal Generationcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 6; 2023: 21; 2024: 9; 2025: 6.

42 papers.

Sort:

By area:

  1. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  2. 2023What does CLIP know about a red circle? Visual prompt engineering for VLMscited by 215
  3. 2022CREPE: Can Vision-Language Foundation Models Reason Compositionally?cited by 177
  4. 2023Aligning Bag of Regions for Open-Vocabulary Object Detectioncited by 119
  5. 2022Exploiting Unlabeled Data with Vision and Language Models for Object Detectioncited by 97
  6. 2023Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinementcited by 84
  7. 2025Vision-Language Models Do Not Understand Negationcited by 69
  8. 2023SATR: Zero-Shot Semantic Segmentation of 3D Shapescited by 62
  9. 2024Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentationcited by 61
  10. 2023CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Modelcited by 47
  11. 2023CLIP-guided Prototype Modulating for Few-shot Action Recognitioncited by 41
  12. 2023Progressive Visual Prompt Learning with Contrastive Feature Re-formationcited by 35
30 more
  1. 2024TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detectioncited by 21
  2. 2023SGDiff: A Style Guided Diffusion Model for Fashion Synthesiscited by 20
  3. 2022CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulationcited by 19
  4. 2023Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyondcited by 19
  5. 2022Transformer Scale Gate for Semantic Segmentationcited by 17
  6. 2025ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Modelscited by 15
  7. 2023Investigating the Limitation of CLIP Models: The Worst-Performing Categoriescited by 12
  8. 2024MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detectioncited by 11
  9. 2022Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignmentcited by 8
  10. 2023Open-Vocabulary Object Detection via Scene Graph Discoverycited by 7
  11. 2023Weakly-Supervised HOI Detection from Interaction Labels Only and Language/Vision-Language Priorscited by 6
  12. 2023BDC-Adapter: Brownian Distance Covariance for Better Vision-Language Reasoningcited by 6
  13. 2023Unsupervised Prototype Adapter for Vision-Language Modelscited by 5
  14. 2024A Review of Human-Object Interaction Detectioncited by 5
  15. 2023IPA-CLIP: Integrating Phonetic Priors into Vision and Language Pretrainingcited by 4
  16. 2024A Survey on Large Language Models from Concept to Implementationcited by 4
  17. 2024Beyond Mask: Rethinking Guidance Types in Few-shot Segmentationcited by 3
  18. 2025Early Estimation of Language to Latent Alignment in Diffusion Modelscited by 3
  19. 2024ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modelingcited by 2
  20. 2023AAN: Attributes-Aware Network for Temporal Action Detectioncited by 1
  21. 2023DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detectioncited by 1
  22. 2023GazeCLIP: Enhancing Gaze Estimation Through Text-Guided Multimodal Learningcited by 1
  23. 2024Anomaly Detection by Adapting a pre-trained Vision Language Modelcited by 1
  24. 2024Progressive Multi-modal Conditional Prompt Tuningcited by 1
  25. 2023VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detectioncited by 0
  26. 2023Hypernymization of named entity-rich captions for grounding-based multi-modal pretrainingcited by 0
  27. 2023Read, look and detect: Bounding box annotation from image-caption pairscited by 0
  28. 2025MPT: Motion Prompt Tuning for Micro-Expression Recognitioncited by 0
  29. 2025Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulationscited by 0
  30. 2025Structure-Aware Feature Rectification with Region Adjacency Graphs for Training-Free Open-Vocabulary Semantic Segmentationcited by 0