In this paper, we propose a novel method to incorporate partial evidence in the inference of deep convolutional neural networks. Contrary to the existing, top-performing methods, which either iteratively modify the input of the network or exploit external label taxonomy to take the partial evidence into account, we add separate network modules ("Plugin Networks") to the intermediate layers of a pretrained convolutional network. The goal of these modules is to incorporate additional signal, i.e. information about known labels, into the inference procedure, and adjust the predicted output accordingly. Since the attached plugins have a simple structure, consisting of only fully connected layers, we drastically reduced the computational cost of training and inference. Also, the proposed architecture allows propagating information about known labels directly to the intermediate layers to improve the final representation. Extensive evaluation of the proposed method confirms that our Plugin Networks outperform the state-of-the-art in a variety of tasks, including scene categorization, multilabel image annotation, and semantic segmentation.

In this paper, we propose a novel regularization method for Generative Adversarial Networks that allows the model to learn discriminative yet compact binary representations of image patches (image descriptors). We exploit the dimensionality reduction that takes place in the intermediate layers of the discriminator network and train the binarized penultimate layer's low-dimensional representation to mimic the distribution of the higher-dimensional preceding layers. To achieve this, we introduce two loss terms that aim at: (i) reducing the correlation between the dimensions of the binarized penultimate layer's low-dimensional representation (i.e. maximizing joint entropy) and (ii) propagating the relations between the dimensions in the high-dimensional space to the low-dimensional space. We evaluate the resulting binary image descriptors on two challenging applications, image matching and retrieval, where they achieve state-of-the-art results.

This work presents a method of classification of text documents using deep neural network with LSTM (long shortterm memory) units.We have tested different approaches to build feature vectors, which represent documents to be classified: we used feature vectors constructed as sequences of words included in the documents, or, alternatively, we first converted words into vector representations using word2vec tool and used sequences of these vector representations as features of documents.We evaluated feasibility of this approach for the task of subject classification of documents using a collection of Wikipedia articles representing 7 subject categories.Our experiments show that the approach based on an LSTM network with documents represented as sequences of words coded into word2vec vectors outperformed a standard, bag-of-word approach with documents represented as frequency-of-words feature vectors.