Învățare cu marjă largă pentru analiza imaginilor / Large margin learning for image analysis
Andrei-Mircea RACOVIȚEANU
Data și ora: 2023-10-17 11:00
Locația: ETTI, Sala consiliu și Microsoft Teams
Rezumat teză de doctorat: Accesează
Data și ora: 2023-10-17 11:00
Locația: ETTI, Sala consiliu și Microsoft Teams
Rezumat teză de doctorat: Accesează
In the last decade, deep learning has developed rapidly due to the interest generated in the community which was based on achieved performance but also making use of the significant improvement of hardware resources. Thus, automatic learning algorithms have become increasingly attractive to researchers in numerous fields. The main goal of the thesis was to improve techniques based on convolutional networks. One of the impediments encountered very often in this field is represented by the small amount of data or non-compliant labels, which have a bad influence on approaches that use supervised learning. In an effort to combat these limitations, a number of new methods were proposed in this work. To take advantage of unlabeled data, semi-supervised learning techniques, transfer learning, and novel methods of augmentation and regularization were used. Another common issue in automatic learning is the overlap of data in the descriptor space, which negatively impacts the separation boundary and the network's predictions. In order to mitigate this effect, a new loss function was proposed to group the descriptive space more efficiently. The main topics addressed were the recognition of facial expressions and image retrieval. n the case of facial expressions, the emphasis centered on identifying the type of emotion, but experiments to identify facial movements were also conducted. The second area of research was based on obtaining embeddings based on convolutional networks trained with a new clustering loss function. The results for both fields proved satisfactory and confirmed the potential of the proposed methods.
Conducător de doctorat
Prof. dr. ing. Corneliu-Nicolae FLOREA, Universitatea Politehnica din București, România.
Comisie de doctorat
Prof. dr. ing. Mihai CIUC, Universitatea Politehnica din București, România
Prof. dr. ing. Cătălin CĂLEANU, Universitatea Politehnica din Timișoara, România
Conf. dr. ing. Ioan BUCIU, Universitatea din Oradea, România
Prof. dr. ing. Constantin VERTAN, Universitatea Politehnica din București, România.
Prof. dr. ing. Cătălin CĂLEANU, Universitatea Politehnica din Timișoara, România
Conf. dr. ing. Ioan BUCIU, Universitatea din Oradea, România
Prof. dr. ing. Constantin VERTAN, Universitatea Politehnica din București, România.
Comisie de îndrumare
Prof. dr. ing. Constantin VERTAN, Universitatea Politehnica din București, România
Prof. dr. ing. Mihai CIUC, Universitatea Politehnica din București, România
Prof. dr. ing. Bogdan IONESCU, Universitatea Politehnica din București, România.
Prof. dr. ing. Mihai CIUC, Universitatea Politehnica din București, România
Prof. dr. ing. Bogdan IONESCU, Universitatea Politehnica din București, România.
Info: Teza poate fi consultată la Biblioteca Universității Politehnica din București, situată în Splaiul Independenței nr. 313.