The adaptation of a Generative Adversarial Network (GAN) aims to transfer a pre-trained GAN to a target domain with limited training data. In this paper, we focus on the one-shot case, which is more challenging and rarely explored in previous works. We consider that the adaptation from a source domain to a target domain can be decoupled into two parts: the transfer of global style like texture and color, and the emergence of new entities that do not belong to the source domain. While previous works mainly focus on style transfer, we propose a novel and concise framework to address the \textit{generalized one-shot adaptation} task for both style and entity transfer, in which a reference image and its binary entity mask are provided. Our core idea is to constrain the gap between the internal distributions of the reference and syntheses by sliced Wasserstein distance. To better achieve it, style fixation is used at first to roughly obtain the exemplary style, and an auxiliary network is introduced to the generator to disentangle entity and style transfer. Besides, to realize cross-domain correspondence, we propose the variational Laplacian regularization to constrain the smoothness of the adapted generator. Both quantitative and qualitative experiments demonstrate the effectiveness of our method in various scenarios.

Zero-shot semantic segmentation aims to recognize the semantics of pixels from unseen categories with zero training samples. Previous practice [1] proposed to train the classifiers for unseen categories using the visual features generated from semantic word embeddings. However, the generator is merely learned on the seen categories while no constraint is applied to the unseen categories, leading to poor generalization ability. In this work, we propose a Consistent Structural Relation Learning (CSRL) approach to constrain the generating of unseen visual features by exploiting the structural relations between seen and unseen categories. We observe that different categories are usually with similar relations in either semantic word embedding space or visual feature space.

To answer your question about the baseline, we experimented with two new sample audio generated by the same (Karplus-Strong) algorithm and tested against Alexa. The result is shown in Table.1. The musical audio does not fool Alexa. Thank you again for your constructive feedback! Currently, we are also trying to activate the wake-word using our adversary.

We thank the reviewers for their time and effort in providing helpful feedback. We address the comments in order. Reviewer #1 - No report submitted. This constrains the state transition densities that their models can express. Lyapunov networks and is readily applicable in both deterministic and stochastic settings. We will add variance info to our figures.

The adaptation of a Generative Adversarial Network (GAN) aims to transfer a pre-trained GAN to a target domain with limited training data. In this paper, we focus on the one-shot case, which is more challenging and rarely explored in previous works. We consider that the adaptation from a source domain to a target domain can be decoupled into two parts: the transfer of global style like texture and color, and the emergence of new entities that do not belong to the source domain. While previous works mainly focus on style transfer, we propose a novel and concise framework to address the \textit{generalized one-shot adaptation} task for both style and entity transfer, in which a reference image and its binary entity mask are provided. Our core idea is to constrain the gap between the internal distributions of the reference and syntheses by sliced Wasserstein distance.

Zero-shot semantic segmentation aims to recognize the semantics of pixels from unseen categories with zero training samples. Previous practice [1] proposed to train the classifiers for unseen categories using the visual features generated from semantic word embeddings. However, the generator is merely learned on the seen categories while no constraint is applied to the unseen categories, leading to poor generalization ability. In this work, we propose a Consistent Structural Relation Learning (CSRL) approach to constrain the generating of unseen visual features by exploiting the structural relations between seen and unseen categories. We observe that different categories are usually with similar relations in either semantic word embedding space or visual feature space.

Over the past few years, a plethora of advancements in Unmanned Areal Vehicle (UAV) technology has paved the way for UAV-based search and rescue operations with transformative impact to the outcome of critical life-saving missions. This paper dives into the challenging task of multiple castaway tracking using an autonomous UAV agent. Leveraging on the computing power of the modern embedded devices, we propose a Model Predictive Control (MPC) framework for tracking multiple castaways assumed to drift afloat in the aftermath of a maritime accident. We consider a stationary radar sensor that is responsible for signaling the search mission by providing noisy measurements of each castaway's initial state. The UAV agent aims at detecting and tracking the moving targets with its equipped onboard camera sensor that has limited sensing range. In this work, we also experimentally determine the probability of target detection from real-world data by training and evaluating various Convolutional Neural Networks (CNNs). Extensive qualitative and quantitative evaluations demonstrate the performance of the proposed approach.