# Learning of Visual Relations: The Devil is in the Tails

arXiv: https://arxiv.org/abs/2108.09668 · HTML: https://mlsanity.com/paper/2108.09668/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 53 references that are in the map.
- First posted on arXiv 22 Aug 2021.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [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)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020)
- [Image Generation from Scene Graphs](https://mlsanity.com/paper/1804.01622/) (2018)
- [Graph R-CNN for Scene Graph Generation](https://mlsanity.com/paper/1808.00191/) (2018)
- [Learning to Compose Dynamic Tree Structures for Visual Contexts](https://mlsanity.com/paper/1812.01880/) (2018)
- [Auto-Encoding Scene Graphs for Image Captioning](https://mlsanity.com/paper/1812.02378/) (2018)
- [Exploring Visual Relationship for Image Captioning](https://mlsanity.com/paper/1809.07041/) (2018)
- [Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification](https://mlsanity.com/paper/2001.01536/) (2020)
- [Knowledge-Embedded Routing Network for Scene Graph Generation](https://mlsanity.com/paper/1903.03326/) (2019)
- [Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective](https://mlsanity.com/paper/2003.10780/) (2020)
- [Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2104.00308/) (2021)
- [Scene Graph Generation with External Knowledge and Image Reconstruction](https://mlsanity.com/paper/1904.00560/) (2019)
- [Bridging Knowledge Graphs to Generate Scene Graphs](https://mlsanity.com/paper/2001.02314/) (2020)
- [Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation](https://mlsanity.com/paper/1806.11538/) (2018)
- [PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2009.00893/) (2020)
- [Class Rectification Hard Mining for Imbalanced Deep Learning](https://mlsanity.com/paper/1712.03162/) (2017)
- [Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval](https://mlsanity.com/paper/1910.05134/) (2019)
- [LinkNet: Relational Embedding for Scene Graph](https://mlsanity.com/paper/1811.06410/) (2018)
- [Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction](https://mlsanity.com/paper/1802.05451/) (2018)

## Built on by (most cited first, 30 of 65)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models](https://mlsanity.com/paper/2109.11797/) (2021)
- [Panoptic Scene Graph Generation](https://mlsanity.com/paper/2207.11247/) (2022)
- [SGTR: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2112.12970/) (2021)
- [RelTR: Relation Transformer for Scene Graph Generation](https://mlsanity.com/paper/2201.11460/) (2022)
- [The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation](https://mlsanity.com/paper/2206.03014/) (2022)
- [Fine-Grained Scene Graph Generation with Data Transfer](https://mlsanity.com/paper/2203.11654/) (2022)
- [Unbiased Scene Graph Generation in Videos](https://mlsanity.com/paper/2304.00733/) (2023)
- [Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World](https://mlsanity.com/paper/2303.13233/) (2023)
- [PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models](https://mlsanity.com/paper/2205.11169/) (2022)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [Fine-Grained Predicates Learning for Scene Graph Generation](https://mlsanity.com/paper/2204.02597/) (2022)
- [Iterative Scene Graph Generation](https://mlsanity.com/paper/2207.13440/) (2022)
- [Devil's on the Edges: Selective Quad Attention for Scene Graph Generation](https://mlsanity.com/paper/2304.03495/) (2023)
- [NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation](https://mlsanity.com/paper/2207.13316/) (2022)
- [HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation](https://mlsanity.com/paper/2303.15994/) (2023)
- [Vision Relation Transformer for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2308.09472/) (2023)
- [Delving into the Trajectory Long-tail Distribution for Muti-object Tracking](https://mlsanity.com/paper/2403.04700/) (2024)
- [Unbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural Network](https://mlsanity.com/paper/2212.00443/) (2022)
- [Hierarchical Memory Learning for Fine-Grained Scene Graph Generation](https://mlsanity.com/paper/2203.06907/) (2022)
- [Compositional Feature Augmentation for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2308.06712/) (2023)
- [Adaptive Fine-Grained Predicates Learning for Scene Graph Generation](https://mlsanity.com/paper/2207.04602/) (2022)
- [Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2208.03763/) (2022)
- [HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation](https://mlsanity.com/paper/2403.12033/) (2024)
- [A Causal Adjustment Module for Debiasing Scene Graph Generation](https://mlsanity.com/paper/2503.17862/) (2025)
- [Unified Visual Relationship Detection with Vision and Language Models](https://mlsanity.com/paper/2303.08998/) (2023)
- [Adaptive Self-training Framework for Fine-grained Scene Graph Generation](https://mlsanity.com/paper/2401.09786/) (2024)
- [DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation](https://mlsanity.com/paper/2403.14886/) (2024)
- [Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection](https://mlsanity.com/paper/2403.17709/) (2024)
- [DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation](https://mlsanity.com/paper/2503.13957/) (2025)

## Abstract (arXiv)

Significant effort has been recently devoted to modeling visual relations. This has mostly addressed the design of architectures, typically by adding parameters and increasing model complexity. However, visual relation learning is a long-tailed problem, due to the combinatorial nature of joint reasoning about groups of objects. Increasing model complexity is, in general, ill-suited for long-tailed problems due to their tendency to overfit. In this paper, we explore an alternative hypothesis, denoted the Devil is in the Tails. Under this hypothesis, better performance is achieved by keeping the model simple but improving its ability to cope with long-tailed distributions. To test this hypothesis, we devise a new approach for training visual relationships models, which is inspired by state-of-the-art long-tailed recognition literature. This is based on an iterative decoupled training scheme, denoted Decoupled Training for Devil in the Tails (DT2). DT2 employs a novel sampling approach, Alternating Class-Balanced Sampling (ACBS), to capture the interplay between the long-tailed entity and predicate distributions of visual relations. Results show that, with an extremely simple architecture, DT2-ACBS significantly outperforms much more complex state-of-the-art methods on scene graph generation tasks. This suggests that the development of sophisticated models must be considered in tandem with the long-tailed nature of the problem.