# Class Interference of Deep Neural Networks

arXiv: https://arxiv.org/abs/2211.01370 · HTML: https://mlsanity.com/paper/2211.01370/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 31 Oct 2022.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Sharp Minima Can Generalize For Deep Nets](https://mlsanity.com/paper/1703.04933/) (2017)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Essentially No Barriers in Neural Network Energy Landscape](https://mlsanity.com/paper/1803.00885/) (2018)
- [Train longer, generalize better: closing the generalization gap in large batch training of neural networks](https://mlsanity.com/paper/1705.08741/) (2017)
- [Three Factors Influencing Minima in SGD](https://mlsanity.com/paper/1711.04623/) (2017)
- [Qualitatively characterizing neural network optimization problems](https://mlsanity.com/paper/1412.6544/) (2014)
- [Generalization in Deep Learning](https://mlsanity.com/paper/1710.05468/) (2017)
- [Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes](https://mlsanity.com/paper/2104.11044/) (2021)
- [What can linear interpolation of neural network loss landscapes tell us?](https://mlsanity.com/paper/2106.16004/) (2021)
- [An empirical analysis of the optimization of deep network loss surfaces](https://mlsanity.com/paper/1612.04010/) (2016)
- [FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networks](https://mlsanity.com/paper/2204.04511/) (2022)

## Built on by (most cited first, 1 of 1)

- [The Vanishing Decision Boundary Complexity and the Strong First Component](https://mlsanity.com/paper/2211.16209/) (2022)

## Abstract (arXiv)

Recognizing and telling similar objects apart is even hard for human beings. In this paper, we show that there is a phenomenon of class interference with all deep neural networks. Class interference represents the learning difficulty in data, and it constitutes the largest percentage of generalization errors by deep networks. To understand class interference, we propose cross-class tests, class ego directions and interference models. We show how to use these definitions to study minima flatness and class interference of a trained model. We also show how to detect class interference during training through label dancing pattern and class dancing notes.