Review: PolyNet — 2nd Runner Up in ILSVRC 2016 (Image Classification)

Review: PolyNet — 2nd Runner Up in ILSVRC 2016 (Image Classification)By Using PolyInception Module, Better Than Inception-ResNet-v2In this story, PolyNet, by CUHK and SenseTime, is reviewed..Compared to Inception-ResNet-v2, PolyNet reduces the Top-5 validation error on single crops from 4.9% to 4.25%, and that on multi-crops from 3.7% to 3.45%.PolyNet, By using PolyInception module, better than Inception-ResNet-v2As a result, PolyNet (with the team name CU-DeepLink) obtains 2nd Runner Up in ILSVRC 2016 classification task as below..The second path is the first-order Inception block..The third path is the second-order term which consists of two Inception blocks.(b) poly-2: As the first Inception F is used for the first-order path and second-order path, the first Inception F can be shared..For each time, one of the six PolyInception modules is replaced with Inception-A, Inception-B, or Inception-C modules, as below.From above figures, we can find that:Any second-order PolyInception module is better than Inception module.Enhancing Inception-B leads to largest gain..Some Training DetailsInitialization by Insertion: To speed up the convergence, as shown above, second order Inception module is removed first, and interleaved modules are trained first..19.10% Top-1 Error and 4.48% Top-5 Error are obtained.Verp Deep PolyNet (10–20–10 mix): 18.71% Top-1 Error and 4.25% Top-5 Error are obtained.With multi-crop, Very Deep PolyNet got 17.36% Top-1 Error and 3.45% Top-5 Error, which is consistently better than Very Deep Inception-ResNet-v2.Thus, the second-order PolyInception module does help to improve the accuracy.As image classification has only one objective, that is to recognize the single object within the image, a good model used in image classification usually become the backbone of the network for object detection, and semantic segmentation, etc.. More details

Leave a Reply