Even if today’s computer has the help of smart algorithms and human assistants, but it may not be able to catch up all thing present in a room. But, recent research from Google might let us realize this incredible image recognition technique. This concept may need a lot of extra computing power.
The result is a far deeper scanning system that can both identify more objects and make better guesses — it can spot tons of items in a living room, including a flying cat as said by google research blog. This new incredible technology is still at early stages. Don’t be surprised if it gets much easier to look for things online.
Team GoogLeNet placed first in the classification and detection tasks, doubling the quality on both tasks over last year’s results. This effort was accomplished by using the DistBelief infrastructure, which makes it possible to train neural networks in a distributed manner and rapidly iterate.
At the core of the approach is a radically redesigned convolutional network architecture. Its seemingly complex structure is based on two insights: the Hebbian principle and scale invariance. As the consequence of a careful balancing act, the depth and width of the network are both increased significantly at the cost of a modest growth in evaluation time. The resultant architecture leads to over 10x reduction in the number of parameters compared to most state of the art vision networks.
These technological advances will enable even better image understanding which can be directly transferable to Google products such as photo search, image search, YouTube or self-driving cars.