Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks
Not on the map. Why?
Abstract (arXiv)
It has been established that training a box-based detector network can enhance the localization performance of weakly supervised and unsupervised methods. Moreover, we extend this understanding by demonstrating that these detectors can be utilized to improve the original network, paving the way for further advancements. To accomplish this, we train the detectors on top of the network output instead of the image data and apply suitable loss backpropagation. Our findings reveal a significant improvement in phrase grounding for the ``what is where by looking'' task, as well as various methods of unsupervised object discovery. Our code is available at https://github.com/eyalgomel/box-based-refinement.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 43 of its 64 references that are in the map. First posted on arXiv 7 Sep 2023.
Builds on
43 of 64 references.
References · 43
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2020End-to-End Object Detection with Transformerscited by 7,414
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 2022Generative Adversarial Networkscited by 5,627
- 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
- 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,362
- 2021Grounded Language-Image Pre-trainingcited by 1,156
- 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 819
31 more
- 2020Transformer Interpretability Beyond Attention Visualizationcited by 627
- 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
- 2016Top-down Neural Attention by Excitation Backpropcited by 321
- 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 320
- 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
- 2015Named Entity Recognition with Bidirectional LSTM-CNNscited by 201
- 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 187
- 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 167
- 2014From Captions to Visual Concepts and Backcited by 109
- 2020Evaluating Weakly Supervised Object Localization Methods Rightcited by 105
- 2015Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposalscited by 69
- 2022Unsupervised Object Localization: Observing the Background to Discover Objectscited by 66
- 2020Toward unsupervised, multi-object discovery in large-scale image collectionscited by 65
- 2019Emergence of Object Segmentation in Perturbed Generative Modelscited by 57
- 2022Unsupervised Salient Object Detection with Spectral Cluster Votingcited by 56
- 2021Large-Scale Unsupervised Object Discoverycited by 54
- 2020Object Segmentation Without Labels with Large-Scale Generative Modelscited by 52
- 2021Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identificationcited by 45
- 2019Unsupervised Image Matching and Object Discovery as Optimizationcited by 42
- 2022Point-Level Region Contrast for Object Detection Pre-Trainingcited by 41
- 2017Weakly-supervised Visual Grounding of Phrases with Linguistic Structurescited by 40
- 2017Query-guided Regression Network with Context Policy for Phrase Groundingcited by 34
- 2018Multi-level Multimodal Common Semantic Space for Image-Phrase Groundingcited by 32
- 2019Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimatorcited by 25
- 2019Generative Modeling for Small-Data Object Detectioncited by 20
- 2022NamedMask: Distilling Segmenters from Complementary Foundation Modelscited by 20
- 2022MOVE: Unsupervised Movable Object Segmentation and Detectioncited by 20
- 2021Detector-Free Weakly Supervised Grounding by Separationcited by 16
- 2022What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputscited by 11
- 2022Semi-Supervised Semantic Segmentation with Cross Teacher Trainingcited by 11
- 2018Learning Unsupervised Visual Grounding Through Semantic Self-Supervisioncited by 10
Built on by
Citing papers per year: 2023: 2; 2024: 1.
3 papers.