Generative deep learning architectures can produce realistic, high-resolution fake imagery -- with potentially drastic societal implications. A key question in this context is: How easy is it to generate realistic imagery, in particular for niche domains. The iterative process required to achieve specific image content is difficult to automate and control. Especially for rare classes, it remains difficult to assess fidelity, meaning whether generative approaches produce realistic imagery and alignment, meaning how (well) the generation can be guided by human input. In this work, we present a large-scale empirical evaluation of generative architectures which we fine-tuned to generate synthetic satellite imagery. We focus on nuclear power plants as an example of a rare object category - as there are only around 400 facilities worldwide, this restriction is exemplary for many other scenarios in which training and test data is limited by the restricted number of occurrences of real-world examples. We generate synthetic imagery by conditioning on two kinds of modalities, textual input and image input obtained from a game engine that allows for detailed specification of the building layout. The generated images are assessed by commonly used metrics for automatic evaluation and then compared with human judgement from our conducted user studies to assess their trustworthiness. Our results demonstrate that even for rare objects, generation of authentic synthetic satellite imagery with textual or detailed building layouts is feasible. In line with previous work, we find that automated metrics are often not aligned with human perception -- in fact, we find strong negative correlations between commonly used image quality metrics and human ratings.

What to expect: these are interactive conversations where the interviewer will give you a scenario at Instacart that is related to ML. The goal is to come up with an end-to-end approach to implement the functionality/ You are also expected to explain the rationale behind your design, for example, the choices of models and metrics. You are welcome to use Google Draws, whiteboard, CodeSignal diagram tool (link provided by interview. Feel free to choose which every whiteboarding tool you feel most comfortable with What we look for: communication of ideas, asking clarifying questions, clarifying and making necessary assumptions, etc. Discuss topics like model management and monitoring, performance, business needs, scale, datastore, etc. Ability to look at trade-offs and articulate various definitions and approaches What to expect: these are interactive conversations where the interviewer will give you a scenario at Instacart that is related to ML. The goal is to come up with an end-to-end approach to implement the functionality/ You are also expected to explain the rationale behind your design, for example, the choices of models and metrics.