Robustness in Compressed Neural Networks for Object Detection

Abstract

Model compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving setting, which is considered in this work. It was shown in the paper that the sensitivity of compressed models to different distortion types is nuanced, and some of the corruptions are heavily impacted by the compression methods (i.e., additive noise), while others (blur effect) are only slightly affected. A common way to improve the robustness of models is to use data augmentation, which was confirmed to positively affect models' robustness, also for highly compressed models. It was further shown that while data imbalance methods brought only a slight increase in accuracy for the baseline model (without compression), the impact was more striking at higher compression rates for the structured pruning. Finally, methods for handling data imbalance brought a significant improvement of the pruned models' worst-detected class accuracy.

arXiv comment2021 International Joint Conference on Neural Networks (IJCNN), https://ieeexplore.ieee.org/document/9533773

References in corpus (17)

• SMOTE: Synthetic Minority Over-sampling Technique
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• A systematic study of the class imbalance problem in convolutional neural networks
• To prune, or not to prune: exploring the efficacy of pruning for model compression
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• The State of Sparsity in Deep Neural Networks
• Do ImageNet Classifiers Generalize to ImageNet?
• The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
• Exploring the Landscape of Spatial Robustness
• Adversarial Examples Are a Natural Consequence of Test Error in Noise
• Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
• What Do Compressed Deep Neural Networks Forget?
• An Investigation of Why Overparameterization Exacerbates Spurious Correlations
• Neural Network Distiller: A Python Package For DNN Compression Research
• No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
• Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy
• Class-dependent Compression of Deep Neural Networks

Cited by in corpus (1)

• Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift