# Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking

arXiv: https://arxiv.org/abs/2407.13646 · HTML: https://mlsanity.com/paper/2407.13646/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 54 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Builds on (most cited first, 30 of 36)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Mitigating Adversarial Effects Through Randomization](https://mlsanity.com/paper/1711.01991/) (2017)
- [Adversarially Robust Generalization Requires More Data](https://mlsanity.com/paper/1804.11285/) (2018)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients](https://mlsanity.com/paper/1711.09404/) (2017)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [Stochastic Activation Pruning for Robust Adversarial Defense](https://mlsanity.com/paper/1803.01442/) (2018)
- [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017)
- [Towards Deep Neural Network Architectures Robust to Adversarial Examples](https://mlsanity.com/paper/1412.5068/) (2014)
- [Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/1904.01990/) (2019)
- [Pose-Normalized Image Generation for Person Re-identification](https://mlsanity.com/paper/1712.02225/) (2017)
- [Camera Style Adaptation for Person Re-identification](https://mlsanity.com/paper/1711.10295/) (2017)
- [Person Re-identification Method Based on Color Attack and Joint Defence](https://mlsanity.com/paper/2111.09571/) (2021)
- [Efficient Defenses Against Adversarial Attacks](https://mlsanity.com/paper/1707.06728/) (2017)
- [Improving the Generalization of Adversarial Training with Domain Adaptation](https://mlsanity.com/paper/1810.00740/) (2018)
- [Cross-Modality Perturbation Synergy Attack for Person Re-identification](https://mlsanity.com/paper/2401.10090/) (2024)
- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [Parameter-Efficient Person Re-identification in the 3D Space](https://mlsanity.com/paper/2006.04569/) (2020)
- [SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification](https://mlsanity.com/paper/1807.00537/) (2018)
- [Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2401.06825/) (2024)

## Built on by (most cited first, 19 of 19)

- [Phy124: Fast Physics-Driven 4D Content Generation from a Single Image](https://mlsanity.com/paper/2409.07179/) (2024)
- [PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement](https://mlsanity.com/paper/2505.12266/) (2025)
- [Adversarial Learning for Neural PDE Solvers with Sparse Data](https://mlsanity.com/paper/2409.02431/) (2024)
- [RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions](https://mlsanity.com/paper/2508.03077/) (2025)
- [Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization](https://mlsanity.com/paper/2409.17977/) (2024)
- [StruSR: Structure-Aware Symbolic Regression with Physics-Informed Taylor Guidance](https://mlsanity.com/paper/2510.06635/) (2025)
- [Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models](https://mlsanity.com/paper/2408.08989/) (2024)
- [Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment](https://mlsanity.com/paper/2508.01602/) (2025)
- [SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution](https://mlsanity.com/paper/2509.18593/) (2025)
- [Geometrically Regularized Transfer Learning with On-Manifold and Off-Manifold Perturbation](https://mlsanity.com/paper/2505.15191/) (2025)
- [GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting](https://mlsanity.com/paper/2604.18047/) (2026)
- [A Review of Image Retrieval Techniques: Data Augmentation and Adversarial Learning Approaches](https://mlsanity.com/paper/2409.01219/) (2024)
- [Fusing Physics-Driven Strategies and Cross-Modal Adversarial Learning: Toward Multi-Domain Applications](https://mlsanity.com/paper/2412.00341/) (2024)
- [On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning](https://mlsanity.com/paper/2505.12681/) (2025)
- [GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation](https://mlsanity.com/paper/2505.15194/) (2025)
- [Disentangled Geometric Alignment with Adaptive Contrastive Perturbation for Reliable Domain Transfer](https://mlsanity.com/paper/2505.15241/) (2025)
- [Dynamic Epsilon Scheduling: A Multi-Factor Adaptive Perturbation Budget for Adversarial Training](https://mlsanity.com/paper/2506.04263/) (2025)
- [Dynamic Modality Scheduling for Multimodal Large Models via Confidence, Uncertainty, and Semantic Consistency](https://mlsanity.com/paper/2506.12724/) (2025)
- [DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Deraining](https://mlsanity.com/paper/2510.06746/) (2025)

## Abstract (arXiv)

In the contemporary of deep learning, where models often grapple with the challenge of simultaneously achieving robustness against adversarial attacks and strong generalization capabilities, this study introduces an innovative Local Feature Masking (LFM) strategy aimed at fortifying the performance of Convolutional Neural Networks (CNNs) on both fronts. During the training phase, we strategically incorporate random feature masking in the shallow layers of CNNs, effectively alleviating overfitting issues, thereby enhancing the model's generalization ability and bolstering its resilience to adversarial attacks. LFM compels the network to adapt by leveraging remaining features to compensate for the absence of certain semantic features, nurturing a more elastic feature learning mechanism. The efficacy of LFM is substantiated through a series of quantitative and qualitative assessments, collectively showcasing a consistent and significant improvement in CNN's generalization ability and resistance against adversarial attacks--a phenomenon not observed in current and prior methodologies. The seamless integration of LFM into established CNN frameworks underscores its potential to advance both generalization and adversarial robustness within the deep learning paradigm. Through comprehensive experiments, including robust person re-identification baseline generalization experiments and adversarial attack experiments, we demonstrate the substantial enhancements offered by LFM in addressing the aforementioned challenges. This contribution represents a noteworthy stride in advancing robust neural network architectures.