ConvMix: Combining Intermediate Latent Features in Deep Convolutional Neural Networks

Mofassir ul Islam Arif, Johannes Burchert, Lars Schmidt-Thieme

Abstract: In traditional deep learning models, latent features to the downstream task are received only from the terminal layer of the feature extractor. The intermediate layers of a feature extractor contain significant spatially salient information which, when pooled by the interleaved pooling operations, is lost. These intermediate latent embeddings can improve the overall performance for vision tasks when leveraged properly. Recently, more complex combination schemes leveraging the intermediate embeddings directly for the downstream task have been proposed, but often require additional hyperparameters, increasing their computational cost and have limited generalizability between datasets.