# TDFormer: A Top-Down Attention-Controlled Spiking Transformer

arXiv: https://arxiv.org/abs/2505.15840 · HTML: https://mlsanity.com/paper/2505.15840/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 17 May 2025.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips](https://mlsanity.com/paper/2404.03663/) (2024)
- [Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation](https://mlsanity.com/paper/2205.00459/) (2022)
- [SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks](https://mlsanity.com/paper/2302.13939/) (2023)
- [Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection](https://mlsanity.com/paper/2407.20708/) (2024)
- [Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training](https://mlsanity.com/paper/2411.16061/) (2024)
- [Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation](https://mlsanity.com/paper/2110.07742/) (2021)
- [QKFormer: Hierarchical Spiking Transformer using Q-K Attention](https://mlsanity.com/paper/2403.16552/) (2024)
- [Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks](https://mlsanity.com/paper/2302.14311/) (2023)
- [Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket](https://mlsanity.com/paper/2401.02020/) (2024)
- [CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks](https://mlsanity.com/paper/2402.04663/) (2024)
- [Top-Down Visual Attention from Analysis by Synthesis](https://mlsanity.com/paper/2303.13043/) (2023)
- [Spiking Transformer with Spatial-Temporal Attention](https://mlsanity.com/paper/2409.19764/) (2024)
- [Rethinking Spiking Neural Networks from an Ensemble Learning Perspective](https://mlsanity.com/paper/2502.14218/) (2025)
- [Spiking Convolutional Neural Networks for Text Classification](https://mlsanity.com/paper/2406.19230/) (2024)
- [A Comprehensive Review of Spiking Neural Networks: Interpretation, Optimization, Efficiency, and Best Practices](https://mlsanity.com/paper/2303.10780/) (2023)

## Abstract (arXiv)

Traditional spiking neural networks (SNNs) can be viewed as a combination of multiple subnetworks with each running for one time step, where the parameters are shared, and the membrane potential serves as the only information link between them. However, the implicit nature of the membrane potential limits its ability to effectively represent temporal information. As a result, each time step cannot fully leverage information from previous time steps, seriously limiting the model's performance. Inspired by the top-down mechanism in the brain, we introduce TDFormer, a novel model with a top-down feedback structure that functions hierarchically and leverages high-order representations from earlier time steps to modulate the processing of low-order information at later stages. The feedback structure plays a role from two perspectives: 1) During forward propagation, our model increases the mutual information across time steps, indicating that richer temporal information is being transmitted and integrated in different time steps. 2) During backward propagation, we theoretically prove that the feedback structure alleviates the problem of vanishing gradients along the time dimension. We find that these mechanisms together significantly and consistently improve the model performance on multiple datasets. In particular, our model achieves state-of-the-art performance on ImageNet with an accuracy of 86.83%.