# FocusNet: Classifying Better by Focusing on Confusing Classes

arXiv: https://arxiv.org/abs/2110.07307 · HTML: https://mlsanity.com/paper/2110.07307/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [Knowledge Distillation by On-the-Fly Native Ensemble](https://mlsanity.com/paper/1806.04606/) (2018)
- [Regularizing Class-wise Predictions via Self-knowledge Distillation](https://mlsanity.com/paper/2003.13964/) (2020)
- [Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation](https://mlsanity.com/paper/2103.08273/) (2021)
- [Deep Attention Aware Feature Learning for Person Re-Identification](https://mlsanity.com/paper/2003.00517/) (2020)
- [Integrating Information Theory and Adversarial Learning for Cross-modal Retrieval](https://mlsanity.com/paper/2104.04991/) (2021)
- [DropMax: Adaptive Variational Softmax](https://mlsanity.com/paper/1712.07834/) (2017)

## Built on by (most cited first, 3 of 3)

- [TFDet: Target-Aware Fusion for RGB-T Pedestrian Detection](https://mlsanity.com/paper/2305.16580/) (2023)
- [Data Efficient Acoustic Scene Classification using Teacher-Informed Confusing Class Instruction](https://mlsanity.com/paper/2409.11964/) (2024)
- [Physics-informed generative real-time lens-free imaging](https://mlsanity.com/paper/2403.07786/) (2024)

## Abstract (arXiv)

Nowadays, most classification networks use one-hot encoding to represent categorical data because of its simplicity. However, one-hot encoding may affect the generalization ability as it neglects inter-class correlations. We observe that, even when a neural network trained with one-hot labels produces incorrect predictions, it still pays attention to the target image region and reveals which classes confuse the network. Inspired by this observation, we propose a confusion-focusing mechanism to address the class-confusion issue. Our confusion-focusing mechanism is implemented by a two-branch network architecture. Its baseline branch generates confusing classes, and its FocusNet branch, whose architecture is flexible, discriminates correct labels from these confusing classes. We also introduce a novel focus-picking loss function to improve classification accuracy by encouraging FocusNet to focus on the most confusing classes. The experimental results validate that our FocusNet is effective for image classification on common datasets, and that our focus-picking loss function can also benefit the current neural networks in improving their classification accuracy.