# Efficient CNN with uncorrelated Bag of Features pooling

arXiv: https://arxiv.org/abs/2209.10865 · HTML: https://mlsanity.com/paper/2209.10865/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 51 references that are in the map.
- First posted on arXiv 22 Sep 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better](https://mlsanity.com/paper/2106.08962/) (2021)
- [Orthogonal Convolutional Neural Networks](https://mlsanity.com/paper/1911.12207/) (2019)
- [Reducing Overfitting in Deep Networks by Decorrelating Representations](https://mlsanity.com/paper/1511.06068/) (2015)
- [Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression](https://mlsanity.com/paper/1812.04368/) (2018)
- [Bag of Color Features For Color Constancy](https://mlsanity.com/paper/1906.04445/) (2019)
- [Attention-based Neural Bag-of-Features Learning for Sequence Data](https://mlsanity.com/paper/2005.12250/) (2020)
- [Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1707.08105/) (2017)
- [Supervised Dictionary Learning and Sparse Representation-A Review](https://mlsanity.com/paper/1502.05928/) (2015)
- [Reducing Redundancy in the Bottleneck Representation of the Autoencoders](https://mlsanity.com/paper/2202.04629/) (2022)
- [Self-Attention Neural Bag-of-Features](https://mlsanity.com/paper/2201.11092/) (2022)

## Abstract (arXiv)

Despite the superior performance of CNN, deploying them on low computational power devices is still limited as they are typically computationally expensive. One key cause of the high complexity is the connection between the convolution layers and the fully connected layers, which typically requires a high number of parameters. To alleviate this issue, Bag of Features (BoF) pooling has been recently proposed. BoF learns a dictionary, that is used to compile a histogram representation of the input. In this paper, we propose an approach that builds on top of BoF pooling to boost its efficiency by ensuring that the items of the learned dictionary are non-redundant. We propose an additional loss term, based on the pair-wise correlation of the items of the dictionary, which complements the standard loss to explicitly regularize the model to learn a more diverse and rich dictionary. The proposed strategy yields an efficient variant of BoF and further boosts its performance, without any additional parameters.