Supplementary Material: Synthesized Classifiers for Zero-Shot Learning
نویسندگان
چکیده
There are a few free hyper-parameters in our approach (cf. Section 3.2 of the main text). To choose the hyper-parameters in the conventional cross-validation (CV) for multi-way classification, one splits the training data into several folds such that they share the same set of class labels with one another. Clearly, this strategy is not sensible for zero-shot learning as it does not imitate what actually happens at the test stage. We thus introduce a new strategy for performing CV, inspired by the hyper-parameter tuning in [25]. The key difference of the new scheme to the conventional CV is that we split the data into several folds such that the class labels of these folds are disjoint. For clarity, we denote the conventional CV as sample-wise CV and our scheme as class-wise CV. Figure 1(b) and 1(c) illustrate the two scenarios, respectively. We empirically compare them in Section 5.1. Note that several existing models [2, 7, 25, 34] also follow similar hyper-prameter tuning procedures.
منابع مشابه
Supplementary Material: An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
– Section 1: Hyper-parameter tuning strategies (Section 4.2 of the main text). – Section 2: Novelty detection approaches: details and additional results (Section 4.3 and 5.2 of the main text). – Section 3: Comparison between zero-shot learning approaches: additional ZSL algorithm, dataset, and results (Section 5 of the main text). – Section 4: Analysis on (generalized) zero-shot learning: detai...
متن کاملSynthesizing Samples for Zero-shot Learning
Zero-shot learning (ZSL) is to construct recognition models for unseen target classes that have no labeled samples for training. It utilizes the class attributes or semantic vectors as side information and transfers supervision information from related source classes with abundant labeled samples. Existing ZSL approaches adopt an intermediary embedding space to measure the similarity between a ...
متن کاملSynthesizing Samples for Zero-shot Learning
Zero-shot learning (ZSL) is to construct recognition models for unseen target classes that have no labeled samples for training. It utilizes the class attributes or semantic vectors as side information and transfers supervision information from related source classes with abundant labeled samples. Existing ZSL approaches adopt an intermediary embedding space to measure the similarity between a ...
متن کاملSupplementary Material: Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
Inter/Extrapolation. In this experiment, a task is defined by three parameters: action, object, and number. The agent should repeat the same subtask for a given number of times. The agent is trained on all configurations of actions and target objects. However, only a subset of numbers is used during training. In order to interpolate and extrapolate, we define analogies based on simple arithmeti...
متن کاملLink the Head to the "Beak": Zero Shot Learning from Noisy Text Description at Part Precision
In this paper, we study learning visual classifiers from unstructured text descriptions at part precision with no training images. We propose a learning framework that is able to connect text terms to its relevant parts and suppress connections to non-visual text terms without any part-text annotations. For instance, this learning process enables terms like “beak” to be sparsely linked to the v...
متن کامل