![]() ![]() By using our scene classification model (again a CNN), we enable our product team to weigh certain scenes more than the others based on their criteria of relevance.For each of the above models, we used CNN architecture very similar to the GoogleNet model that won the ILSVRC 2014 competition. Similarly, a kitchen photo might appeal more than a bathroom photo. For example, it might make more sense to prefer an indoor photo of the property to an outdoor view of the neighborhood. This matched our above definition for image quality and we trained a Deep Convolutional Neural Network (CNN) to learn to differentiate between photos from luxury homes (positive class) from photos from fixer homes (negative class).Īnother key aspect in determining the hero image is understanding which scene or room type the photo belongs to, ensuring the content is relevant and representative of the property. To overcome this we resorted to using predictions from another machine learned attribute based model that categorizes properties as either “Luxury” or “Fixer,” based on features like price, keywords, etc.When we did this, we found the homes scored as “Luxury” often had high resolution and professionally taken photos of attractive spaces, while “Fixer” homes usually had low resolution and poorly captured photos. One of the challenges in training such a visual model for image quality is collecting a large enough labeled dataset of high and low quality images. Image quality is subjective, but for the purpose of selecting our hero images, we want photos that are staged and professionally captured, are high resolution, and contain luxury elements, like chandeliers, fireplaces, etc., to score higher, while images that are low resolution, have clutter, etc., score lower. Like before, we trained another CNN to differentiate between appropriate and inappropriate photos using the curated dataset maintained by our quality control team. This includes photos with prominent text and watermarks, advertisements, humans, animals, non-real estate content, etc. Unlike image quality, image appropriateness can be easily defined in terms of artifacts that violate Trulia photo upload policies. To test our hypothesis, we focused on Trulia Rentals and scored each photo in the property collection across three parameters: We hypothesized that by selecting a more attractive and relevant photo from the collection to be the hero image, we would be able to improve the user experience while increasing the likelihood of properties getting clicked on. Looking for a Change: Our Hypothesis and Methodology ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |