AI Case Study
Aucnet, a Japanese car auction service, automatically classifies cars and uploads images to an online auction site saving over 50,000 man hours annually
Aucnet, a Japanese car auction service, conducts over four million auctions per year. Each auction could take up to twenty minutes of manual work to classify and upload images of the car. Using TensorFlow, transfer learning, and advanced engineering solutions the time per auction was reduced from up to 20 minutes to "minutes." It is estimated this could save over 50,000 man hours of time annually.
Consumer Goods And Services
Automobiles And Parts
"By training their existing IT engineers in the basics of ML, they were able to build Konpeki , a real-time car image recognition system, powered by TensorFlow. By integrating various deep learning technologies, ML APIs and Google Cloud services, they shortened the amount of time it took to list a car auction to just a few minutes, down from 20. Also, Aucnet was able to apply Cloud Machine Learning Engine to increase the speed of ML training process by 86 times."
Creative And Brand
"Japanese car auction service Aucnet...is one of the largest real-time auction service providers in the world, handling four million auctions every year. But one of their pain points was image classification. Entering a single car to auction required uploading 20 photos from various angles with labels like 'front view,' 'side view,' 'tire, 'handle,' 'seat and so on. This time consuming task could take up to 20 minutes per car." The question was whether this could be automated.
Each auction took up to 20 minutes to classify and upload 20 images. With ML the time was reduced to "minutes." With over four million car auctions per year the time saving is estimated at 50,000 hours per year.
"One important technique BrainPad [the vendor] brought to Aucnet is transfer learning. If you want to train a deep neural network model in image recognition from scratch, it’d take several weeks and millions of training images. But with transfer learning, you can reuse a pre-trained image recognition model combined with a smaller neural network model.
"Continuous Integration (CI) of ML models: Just like in software development, Aucnet had to to build a CI framework for production deployment of ML models. This meant the continuous training of models with the latest data, as well as automated evaluation, version control and deployment of models."
"Adjusting the Inception v3 model so it could recognize the difference between left and right camera angles: The Inception v3 model is trained to recognize objects at any angle. This made it hard for Aucnet to classify whether an image was from the left or right angle. To solve for this, Aucnet’s ML engineers created a standalone model just for recognizing the camera angle in a photo."
"Splitting models into different parts, then combining it with Vision API for higher accuracy: Initially, Aucnet was using a single big model for classifying all car types at once. With the current system, they split the models into multiple parts: models for recognizing the angle of a car image ( front, side, rear, etc.), and models for recognizing 40 different car parts (steering wheel, tires, etc). Also, they used Vision API to detect the car manufacturer. By combining all of these methods, the system can classify the exact car model far more accurately."
"In Konpeki [the solution], Aucnet used the pre-trained Inception-v3 model combined with a smaller neural network model, which significantly reduced the number of training images required. The current system uses about 200 photos for each car model, with a total of 150,000 images used to classify more than 700 different car models at high accuracy."