# A stepped sampling method for video detection using LSTM

arXiv: https://arxiv.org/abs/2107.08471 · HTML: https://mlsanity.com/paper/2107.08471/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 18 Jul 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Flow-Guided Feature Aggregation for Video Object Detection](https://mlsanity.com/paper/1703.10025/) (2017)
- [All you need is a good init](https://mlsanity.com/paper/1511.06422/) (2015)
- [Subspace Inference for Bayesian Deep Learning](https://mlsanity.com/paper/1907.07504/) (2019)
- [Seq-NMS for Video Object Detection](https://mlsanity.com/paper/1602.08465/) (2016)
- [The Bouncy Particle Sampler: A Non-Reversible Rejection-Free Markov Chain Monte Carlo Method](https://mlsanity.com/paper/1510.02451/) (2015)
- [Stein Neural Sampler](https://mlsanity.com/paper/1810.03545/) (2018)
- [Sampler Design for Implicit Feedback Data by Noisy-label Robust Learning](https://mlsanity.com/paper/2007.07204/) (2020)
- [Energy-Inspired Models: Learning with Sampler-Induced Distributions](https://mlsanity.com/paper/1910.14265/) (2019)
- [A Modular Benchmarking Infrastructure for High-Performance and Reproducible Deep Learning](https://mlsanity.com/paper/1901.10183/) (2019)
- [Stochastic Bouncy Particle Sampler](https://mlsanity.com/paper/1609.00770/) (2016)
- [NeuralSampler: Euclidean Point Cloud Auto-Encoder and Sampler](https://mlsanity.com/paper/1901.09394/) (2019)
- [SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data](https://mlsanity.com/paper/1804.00248/) (2018)

## Abstract (arXiv)

Artificial neural networks that simulate human achieves great successes. From the perspective of simulating human memory method, we propose a stepped sampler based on the "repeated input". We repeatedly inputted data to the LSTM model stepwise in a batch. The stepped sampler is used to strengthen the ability of fusing the temporal information in LSTM. We tested the stepped sampler on the LSTM built-in in PyTorch. Compared with the traditional sampler of PyTorch, such as sequential sampler, batch sampler, the training loss of the proposed stepped sampler converges faster in the training of the model, and the training loss after convergence is more stable. Meanwhile, it can maintain a higher test accuracy. We quantified the algorithm of the stepped sampler. We assume that, the artificial neural networks have human-like characteristics, and human learning method could be used for machine learning.