Władysław Skarbek

Wladyslaw Skarbek

In deep learning classifiers, the cost function usually takes the form of a combination of SoftMax and CrossEntropy functions. The SoftMax unit transforms the scores predicted by the model network into assessments of the degree (probabilities) of an object's membership to a given class. On the other hand, CrossEntropy measures the divergence of this prediction from the distribution of target scores. This work introduces the ISBE functionality, justifying the thesis about the redundancy of cross entropy computation in deep learning of classifiers. Not only can we omit the calculation of entropy, but also, during back-propagation, there is no need to direct the error to the normalization unit for its backward transformation. Instead, the error is sent directly to the model's network. Using examples of perceptron and convolutional networks as classifiers of images from the MNIST collection, it is observed for ISBE that results are not degraded with SoftMax only, but also with other activation functions such as Sigmoid, Tanh, or their hard variants HardSigmoid and HardTanh. Moreover, up to three percent of time is saved within the total time of forward and backward stages. The article is addressed mainly to programmers and students interested in deep model learning. For example, it illustrates in code snippets possible ways to implement ISBE units, but also formally proves that the softmax trick only applies to the class of softmax functions with relocations.

Michał Król, Michał Salamonowicz, Władysław Skarbek et al.

Accurate geometric calibration of RGB-thermal infrared (TIR) stereo camera systems is essential for multimodal building envelope analysis, yet remains challenging when low-cost thermal sensors with very low spatial resolution are employed. This paper presents a practical stereo calibration framework for an RGB camera (2028 x 1520 px) paired with a TIR camera operating at only 80 x 62 px - a pixel-count ratio of approximately 1:625. An active OLED screen dynamically switches modality-specific patterns (checkerboard for TIR, ChArUco for RGB) on a single physical surface, providing controlled and repeatable thermal contrast. A dedicated corner detection algorithm combining perspective rectification, Hessian saddle-point analysis, and Mean Shift localisation achieves reliable checkerboard detection at 80 x 62 px without per-frame parameter tuning. A baseline-constrained bundle adjustment enforces physically consistent rig geometry under the planar-calibration-object degeneracy, yielding a stereo baseline of 32.7 mm (nominal 30 mm) with an overall reprojection error of 0.382 px. The system is validated on a thermally active building mock-up using constant-depth and per-pixel depth estimation, demonstrating consistent TIR-to-RGB projection suitable for building energy performance assessment.

Xin Chang, Władysław Skarbek

Audio-Video Emotion Recognition is now attacked with Deep Neural Network modeling tools. In published papers, as a rule, the authors show only cases of the superiority in multi-modality over audio-only or video-only modality. However, there are cases superiority in uni-modality can be found. In our research, we hypothesize that for fuzzy categories of emotional events, the within-modal and inter-modal noisy information represented indirectly in the parameters of the modeling neural network impedes better performance in the existing late fusion and end-to-end multi-modal network training strategies. To take advantage and overcome the deficiencies in both solutions, we define a Multi-modal Residual Perceptron Network which performs end-to-end learning from multi-modal network branches, generalizing better multi-modal feature representation. For the proposed Multi-modal Residual Perceptron Network and the novel time augmentation for streaming digital movies, the state-of-art average recognition rate was improved to 91.4% for The Ryerson Audio-Visual Database of Emotional Speech and Song dataset and to 83.15% for Crowd-sourced Emotional multi-modal Actors dataset. Moreover, the Multi-modal Residual Perceptron Network concept shows its potential for multi-modal applications dealing with signal sources not only of optical and acoustical types.

Rafal Pilarczyk, Wladyslaw Skarbek

A novel technique for deep learning of image classifiers is presented. The learned CNN models offer better separation of deep features (also known as embedded vectors) measured by Euclidean proximity and also no deterioration of the classification results by class membership probability. The latter feature can be used for enhancing image classifiers having the classes at the model's exploiting stage different from from classes during the training stage. While the Shannon information of SoftMax probability for target class is extended for mini-batch by the intra-class variance, the trained network itself is extended by the Hadamard layer with the parameters representing the class centers. Contrary to the existing solutions, this extra neural layer enables interfacing of the training algorithm to the standard stochastic gradient optimizers, e.g. AdaM algorithm. Moreover, this approach makes the computed centroids immediately adapting to the updating embedded vectors and finally getting the comparable accuracy in less epochs.

Rafal Pilarczyk, Xin Chang, Wladyslaw Skarbek

Several computer algorithms for recognition of visible human emotions are compared at the web camera scenario using CNN/MMOD face detector. The recognition refers to four face expressions: smile, surprise, anger, and neutral. At the feature extraction stage, the following three concepts of face description are confronted: (a) static 2D face geometry represented by its 68 characteristic landmarks (FP68); (b) dynamic 3D geometry defined by motion parameters for eight distinguished face parts (denoted as AU8) of personalized Candide-3 model; (c) static 2D visual description as 2D array of gray scale pixels (known as facial raw image). At the classification stage, the performance of two major models are analyzed: (a) support vector machine (SVM) with kernel options; (b) convolutional neural network (CNN) with variety of relevant tensor processing layers and blocks of them. The models are trained for frontal views of human faces while they are tested for arbitrary head poses. For geometric features, the success rate (accuracy) indicate nearly triple increase of performance of CNN with respect to SVM classifiers. For raw images, CNN outperforms in accuracy its best geometric counterpart (AU/CNN) by about 30 percent while the best SVM solutions are inferior nearly four times. For F-score the high advantage of raw/CNN over geometric/CNN and geometric/SVM is observed, as well. We conclude that contrary to CNN based emotion classifiers, the generalization capability wrt human head pose is for SVM based emotion classifiers poor.

Wladyslaw Skarbek

This tutorial material on Convolutional Neural Networks (CNN) and its applications in digital media research is based on the concept of Symbolic Tensor Neural Networks. The set of STNN expressions is specified in Backus-Naur Form (BNF) which is annotated by constraints typical for labeled acyclic directed graphs (DAG). The BNF induction begins from a collection of neural unit symbols with extra (up to five) decoration fields (including tensor depth and sharing fields). The inductive rules provide not only the general graph structure but also the specific shortcuts for residual blocks of units. A syntactic mechanism for network fragments modularization is introduced via user defined units and their instances. Moreover, the dual BNF rules are specified in order to generate the Dual Symbolic Tensor Neural Network (DSTNN). The joined interpretation of STNN and DSTNN provides the correct flow of gradient tensors, back propagated at the training stage. The proposed symbolic representation of CNNs is illustrated for six generic digital media applications (CREAMS): Compression, Recognition, Embedding, Annotation, 3D Modeling for human-computer interfacing, and data Security based on digital media objects. In order to make the CNN description and its gradient flow complete, for all presented applications, the symbolic representations of mathematically defined loss/gain functions and gradient flow equations for all used core units, are given. The tutorial is to convince the reader that STNN is not only a convenient symbolic notation for public presentations of CNN based solutions for CREAMS problems but also that it is a design blueprint with a potential for automatic generation of application source code.