Odjel za računarstvo Hrvatske sekcije IEEE, projekt DATACROSS ZCI-ja za znanost o podatcima i kooperativne sustave, Istraživačka jedinica ACROSS i FER-ZEMRIS pozivaju Vas na predavanje
Ranking on manifolds for learning with limited supervision
koje će održati doc. dr. sc. Giorgos Tolias
s Češkog tehničkog sveučilišta u Pragu
u petak, 2. srpnja 2021., u 10.00 sati
u dvorani D346 Fakulteta elektrotehnike i računarstva Sveučilišta u Zagrebu.
Očekivano trajanje predavanja je 45 minuta nakon čega bi slijedila pitanja iz publike.
Više o predavanju i predavaču pročitajte u opširnijem sadržaju obavijesti.
Training Convolutional Neural Networks for computer vision tasks is an annotation demanding process. This talk presents our contributions (CVPR 2018, CVPR 2019, ECCV 2020) that rely on graph-based methods to dispense with or reduce the need for manually annotated data. In particular, we rely on ranking on manifolds that exploits the smoothness assumption, "if two points are close, then, so should be the corresponding output".
The first part of the talk includes two approaches that rely on classical graph-based methods. First, we present an unsupervised framework for hard training example mining. The only input to the method is a collection of images relevant to the target application and a meaningful initial representation, provided e.g. by pre-trained CNN. We mine hard positive and hard negative examples by disagreements between Euclidean and manifold similarities. The discovered examples are used in training for metric learning with any pairwise loss. Second, we employ label propagation to make predictions on the entire dataset and use these predictions to generate pseudo-labels for the unlabeled data and train a deep neural network. This approach is shown effective for semi-supervised learning (SSL), especially in the few labels regime, and complementary to other SSL methods.
The second part of the talk includes a recent approach that departs from classical label propagation and employs Graph Convolutional Networks (GCN) for noisy data cleaning. We consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a graph per class and a GCN is used to predict class relevance of noisy examples, which is then used for classifier learning. This method is evaluated on an extended version of a few-shot learning problem, where the few clean examples of novel classes are supplemented with additional noisy data.
Giorgos Tolias is an assistant professor at the Czech Technical University in Prague and a member of the Visual Recognition Group (VRG). Before he was a postdoc at the LinkMedia team of Inria Rennes. He obtained the Ph.D. degree from the National Technical University of Athens where he worked with the Image and Video Analysis Team (IVA). He is a recipient of the Junior Star grant from the Czech Science foundation and is currently leading a team within VRG. His research is on computer vision with a focus on large scale visual recognition.