# Domain-wise Invariant Learning for Panoptic Scene Graph Generation

arXiv: https://arxiv.org/abs/2310.05867 · HTML: https://mlsanity.com/paper/2310.05867/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 26 references that are in the map.
- First posted on arXiv 9 Oct 2023.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Scene Graph Generation by Iterative Message Passing](https://mlsanity.com/paper/1701.02426/) (2017)
- [Neural Motifs: Scene Graph Parsing with Global Context](https://mlsanity.com/paper/1711.06640/) (2017)
- [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020)
- [Learning to Compose Dynamic Tree Structures for Visual Contexts](https://mlsanity.com/paper/1812.01880/) (2018)
- [CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models](https://mlsanity.com/paper/2109.11797/) (2021)
- [GPS-Net: Graph Property Sensing Network for Scene Graph Generation](https://mlsanity.com/paper/2003.12962/) (2020)
- [Knowledge-Embedded Routing Network for Scene Graph Generation](https://mlsanity.com/paper/1903.03326/) (2019)
- [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)
- [Panoptic Scene Graph Generation](https://mlsanity.com/paper/2207.11247/) (2022)
- [VPGTrans: Transfer Visual Prompt Generator across LLMs](https://mlsanity.com/paper/2305.01278/) (2023)
- [CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2009.07526/) (2020)
- [Fine-Grained Scene Graph Generation with Data Transfer](https://mlsanity.com/paper/2203.11654/) (2022)
- [Panoptic Scene Graph Generation with Semantics-Prototype Learning](https://mlsanity.com/paper/2307.15567/) (2023)
- [PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models](https://mlsanity.com/paper/2205.11169/) (2022)
- [Generating Visual Spatial Description via Holistic 3D Scene Understanding](https://mlsanity.com/paper/2305.11768/) (2023)
- [Towards Complex-query Referring Image Segmentation: A Novel Benchmark](https://mlsanity.com/paper/2309.17205/) (2023)

## Built on by (most cited first, 7 of 7)

- [Treble Counterfactual VLMs: A Causal Approach to Hallucination](https://mlsanity.com/paper/2503.06169/) (2025)
- [Charts Are Not Images: On the Challenges of Scientific Chart Editing](https://mlsanity.com/paper/2512.00752/) (2025)
- [Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration](https://mlsanity.com/paper/2406.01601/) (2024)
- [A Fair Ranking and New Model for Panoptic Scene Graph Generation](https://mlsanity.com/paper/2407.09216/) (2024)
- [Geometry over Density: Few-Shot Cross-Domain OOD Detection](https://mlsanity.com/paper/2605.03410/) (2026)
- [Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image](https://mlsanity.com/paper/2410.15312/) (2024)
- [DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtime](https://mlsanity.com/paper/2603.10538/) (2026)

## Abstract (arXiv)

Panoptic Scene Graph Generation (PSG) involves the detection of objects and the prediction of their corresponding relationships (predicates). However, the presence of biased predicate annotations poses a significant challenge for PSG models, as it hinders their ability to establish a clear decision boundary among different predicates. This issue substantially impedes the practical utility and real-world applicability of PSG models. To address the intrinsic bias above, we propose a novel framework to infer potentially biased annotations by measuring the predicate prediction risks within each subject-object pair (domain), and adaptively transfer the biased annotations to consistent ones by learning invariant predicate representation embeddings. Experiments show that our method significantly improves the performance of benchmark models, achieving a new state-of-the-art performance, and shows great generalization and effectiveness on PSG dataset.