# Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migration

arXiv: https://arxiv.org/abs/2211.12735 · HTML: https://mlsanity.com/paper/2211.12735/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 76 of its 88 references that are in the map.
- First posted on arXiv 23 Nov 2022.

## Builds on (most cited first, 30 of 76)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [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)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)

## Built on by (most cited first, 24 of 24)

- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [Artemis: Towards Referential Understanding in Complex Videos](https://mlsanity.com/paper/2406.00258/) (2024)
- [Robust Tracking via Mamba-based Context-aware Token Learning](https://mlsanity.com/paper/2412.13611/) (2024)
- [What You Have is What You Track: Adaptive and Robust Multimodal Tracking](https://mlsanity.com/paper/2507.05899/) (2025)
- [Personalized Large Vision-Language Models](https://mlsanity.com/paper/2412.17610/) (2024)
- [CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features](https://mlsanity.com/paper/2505.19434/) (2025)
- [ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking](https://mlsanity.com/paper/2507.19875/) (2025)
- [Explicit Context Reasoning with Supervision for Visual Tracking](https://mlsanity.com/paper/2507.16191/) (2025)
- [RELO: Reinforcement Learning to Localize for Visual Object Tracking](https://mlsanity.com/paper/2605.07379/) (2026)
- [Omni Survey for Multimodality Analysis in Visual Object Tracking](https://mlsanity.com/paper/2508.13000/) (2025)
- [UETrack: A Unified and Efficient Framework for Single Object Tracking](https://mlsanity.com/paper/2603.01412/) (2026)
- [UAUTrack: Towards Unified Multimodal Anti-UAV Visual Tracking](https://mlsanity.com/paper/2512.02668/) (2025)
- [SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking](https://mlsanity.com/paper/2602.01677/) (2026)
- [Unified Multimodal Visual Tracking with Dual Mixture-of-Experts](https://mlsanity.com/paper/2605.03716/) (2026)
- [VL-UniTrack: A Unified Framework with Visual-Language Prompts for UAV-Ground Visual Tracking](https://mlsanity.com/paper/2605.04574/) (2026)
- [An Efficient Token Compression Framework for Visual Object Tracking](https://mlsanity.com/paper/2605.08329/) (2026)
- [Semantic-Aware Temporal Adaptation for UAV Anti-UAV Tracking](https://mlsanity.com/paper/2607.26511/) (2026)
- [HMSViT: A Hierarchical Masked Self-Supervised Vision Transformer for Corneal Nerve Segmentation and Diabetic Neuropathy Diagnosis](https://mlsanity.com/paper/2506.19474/) (2025)
- [RGBX-R1: Visual Modality Chain-of-Thought Guided Reinforcement Learning for Multimodal Grounding](https://mlsanity.com/paper/2602.00504/) (2026)
- [Revisiting Cross-Attention Mechanisms: Leveraging Beneficial Noise for Domain-Adaptive Learning](https://mlsanity.com/paper/2603.17474/) (2026)
- [SpecTrack: Spectral Prompt Guided Adaptive Experts for Multispectral Object Tracking](https://mlsanity.com/paper/2607.05988/) (2026)
- [Towards Compact Unified Multimodal Tracking: Synergizing Knowledge Distillation with Structural Pruning](https://mlsanity.com/paper/2608.01488/) (2026)
- [Learning to Track from Privileged Target Appearances](https://mlsanity.com/paper/2609.02471/) (2026)
- [LoopTrack: A Simple Baseline for Parameter-Efficient Transformer Tracking](https://mlsanity.com/paper/2609.33306/) (2026)

## Abstract (arXiv)

We propose integrally pre-trained transformer pyramid network (iTPN), towards jointly optimizing the network backbone and the neck, so that transfer gap between representation models and downstream tasks is minimal. iTPN is born with two elaborated designs: 1) The first pre-trained feature pyramid upon vision transformer (ViT). 2) Multi-stage supervision to the feature pyramid using masked feature modeling (MFM). iTPN is updated to Fast-iTPN, reducing computational memory overhead and accelerating inference through two flexible designs. 1) Token migration: dropping redundant tokens of the backbone while replenishing them in the feature pyramid without attention operations. 2) Token gathering: reducing computation cost caused by global attention by introducing few gathering tokens. The base/large-level Fast-iTPN achieve 88.75%/89.5% top-1 accuracy on ImageNet-1K. With 1x training schedule using DINO, the base/large-level Fast-iTPN achieves 58.4%/58.8% box AP on COCO object detection, and a 57.5%/58.7% mIoU on ADE20K semantic segmentation using MaskDINO. Fast-iTPN can accelerate the inference procedure by up to 70%, with negligible performance loss, demonstrating the potential to be a powerful backbone for downstream vision tasks. The code is available at: github.com/sunsmarterjie/iTPN.