Enhanced Data Transfer Cooperating with Artificial Triplets for Scene Graph Generation
Not on the map. Why?
Abstract (arXiv)
This work focuses on training dataset enhancement of informative relational triplets for Scene Graph Generation (SGG). Due to the lack of effective supervision, the current SGG model predictions perform poorly for informative relational triplets with inadequate training samples. Therefore, we propose two novel training dataset enhancement modules: Feature Space Triplet Augmentation (FSTA) and Soft Transfer. FSTA leverages a feature generator trained to generate representations of an object in relational triplets. The biased prediction based sampling in FSTA efficiently augments artificial triplets focusing on the challenging ones. In addition, we introduce Soft Transfer, which assigns soft predicate labels to general relational triplets to make more supervisions for informative predicate classes effectively. Experimental results show that integrating FSTA and Soft Transfer achieve high levels of both Recall and mean Recall in Visual Genome dataset. The mean of Recall and mean Recall is the highest among all the existing model-agnostic methods.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 40 references that are in the map. First posted on arXiv 27 Jun 2024.
Builds on
33 of 40 references.
References · 33
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
- 2017Scene Graph Generation by Iterative Message Passingcited by 462
- 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
- 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
- 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
- 2016Visual Relationship Detection with Language Priorscited by 333
- 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 258
21 more
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
- 2019Knowledge-Embedded Routing Network for Scene Graph Generationcited by 163
- 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
- 2020Visual Compositional Learning for Human-Object Interaction Detectioncited by 129
- 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
- 2019Graphical Contrastive Losses for Scene Graph Parsingcited by 100
- 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
- 2019Unpaired Image Captioning via Scene Graph Alignmentscited by 82
- 2021Detecting Human-Object Interaction via Fabricated Compositional Learningcited by 79
- 2020PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generationcited by 75
- 2021Recovering the Unbiased Scene Graphs from the Biased Onescited by 71
- 2021Learning of Visual Relations: The Devil is in the Tailscited by 65
- 2021Learning to Generate Scene Graph from Natural Language Supervisioncited by 64
- 2020CogTree: Cognition Tree Loss for Unbiased Scene Graph Generationcited by 62
- 2022The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generationcited by 60
- 2022Fine-Grained Scene Graph Generation with Data Transfercited by 57
- 2022Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuningcited by 54
- 2018Learning Compositional Representations for Few-Shot Recognitioncited by 50
- 2022Fine-Grained Predicates Learning for Scene Graph Generationcited by 27
- 2021Image Scene Graph Generation (SGG) Benchmarkcited by 15
- 2022Probabilistic Debiasing of Scene Graphscited by 8
Built on by
Not cited yet.