# Tackling the Unannotated: Scene Graph Generation with Bias-Reduced Models

arXiv: https://arxiv.org/abs/2008.07832 · HTML: https://mlsanity.com/paper/2008.07832/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2020.

## Built on by (most cited first, 19 of 19)

- [Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2104.00308/) (2021)
- [A Comprehensive Survey of Scene Graphs: Generation and Application](https://mlsanity.com/paper/2104.01111/) (2021)
- [SGTR: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2112.12970/) (2021)
- [Scene Graph Generation: A Comprehensive Survey](https://mlsanity.com/paper/2201.00443/) (2022)
- [Recovering the Unbiased Scene Graphs from the Biased Ones](https://mlsanity.com/paper/2107.02112/) (2021)
- [The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation](https://mlsanity.com/paper/2206.03014/) (2022)
- [Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning](https://mlsanity.com/paper/2208.08165/) (2022)
- [Devil's on the Edges: Selective Quad Attention for Scene Graph Generation](https://mlsanity.com/paper/2304.03495/) (2023)
- [Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation](https://mlsanity.com/paper/2111.13517/) (2021)
- [NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation](https://mlsanity.com/paper/2207.13316/) (2022)
- [Vision Relation Transformer for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2308.09472/) (2023)
- [Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2208.03763/) (2022)
- [Semantic Compositional Learning for Low-shot Scene Graph Generation](https://mlsanity.com/paper/2108.08600/) (2021)
- [Single-Stage Visual Relationship Learning using Conditional Queries](https://mlsanity.com/paper/2306.05689/) (2023)
- [Explore Contextual Information for 3D Scene Graph Generation](https://mlsanity.com/paper/2210.06240/) (2022)
- [RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation](https://mlsanity.com/paper/2309.03240/) (2023)
- [Hyper-relationship Learning Network for Scene Graph Generation](https://mlsanity.com/paper/2202.07271/) (2022)
- [SGTR+: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2401.12835/) (2024)
- [SrTR: Self-reasoning Transformer with Visual-linguistic Knowledge for Scene Graph Generation](https://mlsanity.com/paper/2212.09329/) (2022)

## Abstract (arXiv)

Predicting a scene graph that captures visual entities and their interactions in an image has been considered a crucial step towards full scene comprehension. Recent scene graph generation (SGG) models have shown their capability of capturing the most frequent relations among visual entities. However, the state-of-the-art results are still far from satisfactory, e.g. models can obtain 31% in overall recall R@100, whereas the likewise important mean class-wise recall mR@100 is only around 8% on Visual Genome (VG). The discrepancy between R and mR results urges to shift the focus from pursuing a high R to a high mR with a still competitive R. We suspect that the observed discrepancy stems from both the annotation bias and sparse annotations in VG, in which many visual entity pairs are either not annotated at all or only with a single relation when multiple ones could be valid. To address this particular issue, we propose a novel SGG training scheme that capitalizes on self-learned knowledge. It involves two relation classifiers, one offering a less biased setting for the other to base on. The proposed scheme can be applied to most of the existing SGG models and is straightforward to implement. We observe significant relative improvements in mR (between +6.6% and +20.4%) and competitive or better R (between -2.4% and 0.3%) across all standard SGG tasks.