FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting
Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks. From an image and signal processing point of view, this success might be a bit surprising as the inherent spatial pyramid design of most CNNs is apparently violating basic signal processing laws, i.e. Sampling Theorem in their down-sampling operations. However, since poor sampling appeared not to affect model accuracy, this issue has been broadly neglected until model robustness started to receive more attention. Recent work [17] in the context of adversarial attacks and distribution shifts, showed after all, that there is a strong correlation between the vulnerability of CNNs and aliasing artifacts induced by poor down-sampling operations. This paper builds on these findings and introduces an aliasing free down-sampling operation which can easily be plugged into any CNN architecture: FrequencyLowCut pooling. Our experiments show, that in combination with simple and fast FGSM adversarial training, our hyper-parameter free operator significantly improves model robustness and avoids catastrophic overfitting.
Code (1)
Similar Papers 제목 키워드 기반
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing. In this paper, beyond conventional spatial pooling that usually has …
Scene ParsingSemantic SegmentationUnlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models
While the robustness of vision models is often measured, their dependence on specific architectural design choices is rarely dissected. We investigate why certain vision architectures are inherently more robust to additi…
Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition
Skeleton-based human action recognition is becoming increasingly important in a variety of fields. Most existing works train a CNN or GCN based backbone to extract spatial-temporal features, and use temporal average/…
Action RecognitionSkeleton Based Action RecognitionTemporal Action LocalizationMitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners
Large Language Models (LLMs) show strong reasoning abilities, often amplified by Chain-of-Thought (CoT) prompting and reinforcement learning (RL). Although RL algorithms can substantially improve reasoning, they struggle…
Reinforcement LearningLAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fields
Neural distance fields offer a compact and continuous representation of 3D geometry, making them attractive for incremental LiDAR mapping. However, their online optimization is vulnerable to catastrophic forgetting, wher…