# Robust Classification with Convolutional Prototype Learning

arXiv: https://arxiv.org/abs/1805.03438 · HTML: https://mlsanity.com/paper/1805.03438/

## Key facts

- Cited by 123 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2018.

## Built on by (most cited first, 30 of 123)

- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [SPICE: Semantic Pseudo-labeling for Image Clustering](https://mlsanity.com/paper/2103.09382/) (2021)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [D4M: Dataset Distillation via Disentangled Diffusion Model](https://mlsanity.com/paper/2407.15138/) (2024)
- [Visual Recognition with Deep Nearest Centroids](https://mlsanity.com/paper/2209.07383/) (2022)
- [BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation](https://mlsanity.com/paper/2203.02533/) (2022)
- [Deep Metric Learning for Open World Semantic Segmentation](https://mlsanity.com/paper/2108.04562/) (2021)
- [FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning](https://mlsanity.com/paper/2401.03230/) (2024)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds](https://mlsanity.com/paper/2210.08064/) (2022)
- [OpenAUC: Towards AUC-Oriented Open-Set Recognition](https://mlsanity.com/paper/2210.13458/) (2022)
- [Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation](https://mlsanity.com/paper/2203.02925/) (2022)
- [Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks](https://mlsanity.com/paper/2208.04441/) (2022)
- [Open-set 3D Object Detection](https://mlsanity.com/paper/2112.01135/) (2021)
- [Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition](https://mlsanity.com/paper/2411.18941/) (2024)
- [PTaRL: Prototype-based Tabular Representation Learning via Space Calibration](https://mlsanity.com/paper/2407.05364/) (2024)
- [PMAL: Open Set Recognition via Robust Prototype Mining](https://mlsanity.com/paper/2203.08569/) (2022)
- [CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection](https://mlsanity.com/paper/2212.00244/) (2022)
- [Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning](https://mlsanity.com/paper/2309.01083/) (2023)
- [OpenTAL: Towards Open Set Temporal Action Localization](https://mlsanity.com/paper/2203.05114/) (2022)
- [Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations](https://mlsanity.com/paper/2311.16681/) (2023)
- [A Survey of Historical Document Image Datasets](https://mlsanity.com/paper/2203.08504/) (2022)
- [Attribute Prototype Network for Any-Shot Learning](https://mlsanity.com/paper/2204.01208/) (2022)
- [PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning](https://mlsanity.com/paper/2401.02094/) (2024)
- [Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation](https://mlsanity.com/paper/2203.02135/) (2022)
- [Latent Discriminant deterministic Uncertainty](https://mlsanity.com/paper/2207.10130/) (2022)
- [Temporal Action Segmentation with High-level Complex Activity Labels](https://mlsanity.com/paper/2108.06706/) (2021)
- [Bootstrap Generalization Ability from Loss Landscape Perspective](https://mlsanity.com/paper/2209.08473/) (2022)
- [COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation](https://mlsanity.com/paper/2210.01784/) (2022)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have been widely used for image classification. Despite its high accuracies, CNN has been shown to be easily fooled by some adversarial examples, indicating that CNN is not robust enough for pattern classification. In this paper, we argue that the lack of robustness for CNN is caused by the softmax layer, which is a totally discriminative model and based on the assumption of closed world (i.e., with a fixed number of categories). To improve the robustness, we propose a novel learning framework called convolutional prototype learning (CPL). The advantage of using prototypes is that it can well handle the open world recognition problem and therefore improve the robustness. Under the framework of CPL, we design multiple classification criteria to train the network. Moreover, a prototype loss (PL) is proposed as a regularization to improve the intra-class compactness of the feature representation, which can be viewed as a generative model based on the Gaussian assumption of different classes. Experiments on several datasets demonstrate that CPL can achieve comparable or even better results than traditional CNN, and from the robustness perspective, CPL shows great advantages for both the rejection and incremental category learning tasks.