Strategic insertion of Global Average Pooling layers in VGG-16 reduces trainable parameters by 98%, maintains 66.4% ImageNet Top-1 accuracy, doubles translation robustness, and yields superior Spearman correlations in perceptual IQA tasks.
Why do deep convolutional networks generalize so poorly to small image transformations?
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
The book presents principles from optimization and information theory to explain deep network architectures and enable new interpretable models.
citing papers explorer
-
Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs
Strategic insertion of Global Average Pooling layers in VGG-16 reduces trainable parameters by 98%, maintains 66.4% ImageNet Top-1 accuracy, doubles translation robustness, and yields superior Spearman correlations in perceptual IQA tasks.
-
Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory
The book presents principles from optimization and information theory to explain deep network architectures and enable new interpretable models.