Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?

Abstract

Various methods of measuring unit selectivity have been developed with the aim of better understanding how neural networks work. But the different measures provide divergent estimates of selectivity, and this has led to different conclusions regarding the conditions in which selective object representations are learned and the functional relevance of these representations. In an attempt to better characterize object selectivity, we undertake a comparison of various selectivity measures on a large set of units in AlexNet, including localist selectivity, precision, class-conditional mean activity selectivity (CCMAS), network dissection,the human interpretation of activation maximization (AM) images, and standard signal-detection measures. We find that the different measures provide different estimates of object selectivity, with precision and CCMAS measures providing misleadingly high estimates. Indeed, the most selective units had a poor hit-rate or a high false-alarm rate (or both) in object classification, making them poor object detectors. We fail to find any units that are even remotely as selective as the 'grandmother cell' units reported in recurrent neural networks. In order to generalize these results, we compared selectivity measures on units in VGG-16 and GoogLeNet trained on the ImageNet or Places-365 datasets that have been described as 'object detectors'. Again, we find poor hit-rates and high false-alarm rates for object classification. We conclude that signal-detection measures provide a better assessment of single-unit selectivity compared to common alternative approaches, and that deep convolutional networks of image classification do not learn object detectors in their hidden layers.

arXiv commentPublished in Vision Research 2020, 19 pages, 8 figures

References in corpus (10)

• Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Understanding Neural Networks Through Deep Visualization
• Visualizing and Understanding Recurrent Networks
• Learning to Generate Reviews and Discovering Sentiment
• Understanding disentangling in $\beta$-VAE
• Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
• Revisiting the Importance of Individual Units in CNNs via Ablation
• The emergence of number and syntax units in LSTM language models
• Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs