Slashdot Mirror

← Back to Stories (view on slashdot.org)

Baidu's Supercomputer Beats Google At Image Recognition

Posted by samzenpus on from the all-the-better-to-see-you-with dept.

catchblue22 writes: Using the ImageNet object classification benchmark, Baidu’s Minwa supercomputer scanned more than 1 million images and taught itself to sort them into about 1,000 categories and achieved an image identification error rate of just 4.58 percent, beating humans, Microsoft and Google. Google's system scored a 95.2% and Microsoft's, a 95.06%, Baidu said. “Our company is now leading the race in computer intelligence,” said Ren Wu, a Baidu scientist working on the project. “I think this is the fastest supercomputer dedicated to deep learning,” he said. “We have great power in our hands—much greater than our competitors.”

3 of 115 comments (clear)

  1. Bad summary by Anonymous Coward · · Score: 5, Insightful

    The summary is written to imply that Google/MS have error rates in the 90's, while the competition only has about 5% error. The values got inverted - Google/MS also have error rates around 5%, but are behind by fractions.

  2. Your maths is off... by ZG-Rules · · Score: 5, Insightful

    As a pedant, I need to point out that the improvement is 0.24%

    "The system trained on Baidu’s new computer was wrong only 4.58 percent of the time. The previous best was 4.82 percent, reported by Google in March. One month before that, Microsoft had reported achieving 4.94 percent, becoming the first to better average human performance of 5.1 percent."

    Also why are the numbers reversed to quote success rates for Google and Microsoft in the summary on Slashdot - it would have been much clearer if the actual numbers in the article (which were all error rates) were quoted!

    1. Re:Your maths is off... by bouldin · · Score: 5, Informative

      My main question is how damn stupid are the humans they are using to have a >5% error rate looking at pictures.

      This was the first thing I thought after reading the summary, too. I had to dig into a paper about the 2014 ImageNet challenge, but here is the likely answer:

      The most common error that an untrained annotator is susceptible to is a failure to consider a relevant class as a possible label because they are unaware of its existence.

      My second question was, if humans failed to label the images correctly, how did they get a correct label in the first place?

      The methodology they used just to label the images is impressively sophisticated. Briefly, they crowdsourced through Amazon Mechanical Turk. A first person would draw bounding boxes around individual items in each image, then additional people would classify the items in each box. Only when a majority of labelers agreed on a label did they consider the label correct.