# RLIPv2: Fast Scaling of Relational Language-Image Pre-training

arXiv: https://arxiv.org/abs/2308.09351 · HTML: https://mlsanity.com/paper/2308.09351/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 94 of its 109 references that are in the map.
- First posted on arXiv 18 Aug 2023.

## Builds on (most cited first, 30 of 94)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)

## Built on by (most cited first, 30 of 45)

- [Make Continual Learning Stronger via C-Flat](https://mlsanity.com/paper/2404.00986/) (2024)
- [HUMOTO: A 4D Dataset of Mocap Human Object Interactions](https://mlsanity.com/paper/2504.10414/) (2025)
- [Open-World Human-Object Interaction Detection via Multi-modal Prompts](https://mlsanity.com/paper/2406.07221/) (2024)
- [EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection](https://mlsanity.com/paper/2410.23904/) (2024)
- [CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding](https://mlsanity.com/paper/2311.03354/) (2023)
- [Revisiting Neural Networks for Continual Learning: An Architectural Perspective](https://mlsanity.com/paper/2404.14829/) (2024)
- [Enhancing Descriptive Captions with Visual Attributes for Multimodal Perception](https://mlsanity.com/paper/2412.14233/) (2024)
- [BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting](https://mlsanity.com/paper/2504.09097/) (2025)
- [Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection](https://mlsanity.com/paper/2403.14270/) (2024)
- [DAWN: Designing Distributed Agents in a Worldwide Network](https://mlsanity.com/paper/2410.22339/) (2024)
- [OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad](https://mlsanity.com/paper/2503.18695/) (2025)
- [A Review of Human-Object Interaction Detection](https://mlsanity.com/paper/2408.10641/) (2024)
- [An Image-like Diffusion Method for Human-Object Interaction Detection](https://mlsanity.com/paper/2503.18134/) (2025)
- [Weakly Supervised Video Scene Graph Generation via Natural Language Supervision](https://mlsanity.com/paper/2502.15370/) (2025)
- [Enhancing HOI Detection with Contextual Cues from Large Vision-Language Models](https://mlsanity.com/paper/2311.16475/) (2023)
- [End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting](https://mlsanity.com/paper/2409.12499/) (2024)
- [Egocentric Human-Object Interaction Detection: A New Benchmark and Method](https://mlsanity.com/paper/2506.14189/) (2025)
- [RoHOI: Robustness Benchmark for Human-Object Interaction Detection](https://mlsanity.com/paper/2507.09111/) (2025)
- [TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring](https://mlsanity.com/paper/2508.04943/) (2025)
- [No More Sibling Rivalry: Debiasing Human-Object Interaction Detection](https://mlsanity.com/paper/2509.00760/) (2025)
- [Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection](https://mlsanity.com/paper/2510.25094/) (2025)
- [Towards Flexible Visual Relationship Segmentation](https://mlsanity.com/paper/2408.08305/) (2024)
- [Orchestrating the Symphony of Prompt Distribution Learning for Human-Object Interaction Detection](https://mlsanity.com/paper/2412.08506/) (2024)
- [Streamlined Open-Vocabulary Human-Object Interaction Detection](https://mlsanity.com/paper/2603.27500/) (2026)
- [Rethinking Video Human-Object Interaction: Set Prediction over Time for Unified Detection and Anticipation](https://mlsanity.com/paper/2604.10397/) (2026)
- [CL-HOI: Cross-Level Human-Object Interaction Distillation from Vision Large Language Models](https://mlsanity.com/paper/2410.15657/) (2024)
- [VLM-HOI: Vision Language Models for Interpretable Human-Object Interaction Analysis](https://mlsanity.com/paper/2411.18038/) (2024)
- [RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios](https://mlsanity.com/paper/2412.14643/) (2024)
- [Dynamic Scene Understanding from Vision-Language Representations](https://mlsanity.com/paper/2501.11653/) (2025)
- [QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction Detection](https://mlsanity.com/paper/2508.08590/) (2025)

## Abstract (arXiv)

Relational Language-Image Pre-training (RLIP) aims to align vision representations with relational texts, thereby advancing the capability of relational reasoning in computer vision tasks. However, hindered by the slow convergence of RLIPv1 architecture and the limited availability of existing scene graph data, scaling RLIPv1 is challenging. In this paper, we propose RLIPv2, a fast converging model that enables the scaling of relational pre-training to large-scale pseudo-labelled scene graph data. To enable fast scaling, RLIPv2 introduces Asymmetric Language-Image Fusion (ALIF), a mechanism that facilitates earlier and deeper gated cross-modal fusion with sparsified language encoding layers. ALIF leads to comparable or better performance than RLIPv1 in a fraction of the time for pre-training and fine-tuning. To obtain scene graph data at scale, we extend object detection datasets with free-form relation labels by introducing a captioner (e.g., BLIP) and a designed Relation Tagger. The Relation Tagger assigns BLIP-generated relation texts to region pairs, thus enabling larger-scale relational pre-training. Through extensive experiments conducted on Human-Object Interaction Detection and Scene Graph Generation, RLIPv2 shows state-of-the-art performance on three benchmarks under fully-finetuning, few-shot and zero-shot settings. Notably, the largest RLIPv2 achieves 23.29mAP on HICO-DET without any fine-tuning, yields 32.22mAP with just 1% data and yields 45.09mAP with 100% data. Code and models are publicly available at https://github.com/JacobYuan7/RLIPv2.