mlsanityData to 7 Oct 2026

Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers

arXiv 2210.13053 ↗First posted 24 Oct 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Unsupervised object discovery (UOD) has recently shown encouraging progress with the adoption of pre-trained Transformer features. However, current methods based on Transformers mainly focus on designing the localization head (e.g., seed selection-expansion and normalized cut) and overlook the importance of improving Transformer features. In this work, we handle UOD task from the perspective of feature enhancement and propose FOReground guidance and MUlti-LAyer feature fusion for unsupervised object discovery, dubbed FORMULA. Firstly, we present a foreground guidance strategy with an off-the-shelf UOD detector to highlight the foreground regions on the feature maps and then refine object locations in an iterative fashion. Moreover, to solve the scale variation issues in object detection, we design a multi-layer feature fusion module that aggregates features responding to objects at different scales. The experiments on VOC07, VOC12, and COCO 20k show that the proposed FORMULA achieves new state-of-the-art results on unsupervised object discovery. The code will be released at https://github.com/VDIGPKU/FORMULA.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 47 of its 60 references that are in the map. First posted on arXiv 24 Oct 2022.

Builds on

47 of 60 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  7. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  8. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  9. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  10. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  11. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  12. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
35 more
  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  4. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  8. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  9. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  10. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  11. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  12. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  13. 2016Colorful Image Colorizationcited by 1,113
  14. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  15. 2015Weakly Supervised Deep Detection Networkscited by 183
  16. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  17. 2021Efficient Self-supervised Vision Transformers for Representation Learningcited by 149
  18. 2014Hypercolumns for Object Segmentation and Fine-grained Localizationcited by 128
  19. 2020TransPose: Keypoint Localization via Transformercited by 126
  20. 2021MST: Masked Self-Supervised Transformer for Visual Representationcited by 114
  21. 2021Aligning Pretraining for Detection via Object-Level Contrastive Learningcited by 110
  22. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  23. 2016MultiNet: Real-time Joint Semantic Reasoning for Autonomous Drivingcited by 90
  24. 2016A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detectioncited by 83
  25. 2015Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networkscited by 80
  26. 2015Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposalscited by 69
  27. 2020Toward unsupervised, multi-object discovery in large-scale image collectionscited by 65
  28. 2021Large-Scale Unsupervised Object Discoverycited by 54
  29. 2016HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detectioncited by 46
  30. 2019Unsupervised Image Matching and Object Discovery as Optimizationcited by 42
  31. 2021MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Drivingcited by 41
  32. 2021Feature Fusion Vision Transformer for Fine-Grained Visual Categorizationcited by 40
  33. 2017Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transformingcited by 15
  34. 2021Self-Supervised Learning by Estimating Twin Class Distributionscited by 12
  35. 2022GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classescited by 22
  2. 2024Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policiescited by 6
  3. 2026MUFASA: A Multi-Layer Framework for Slot Attentioncited by 1
  4. 2025PCaM: A Progressive Focus Attention-Based Information Fusion Method for Improving Vision Transformer Domain Adaptationcited by 0