Correction to: Person search via class activation map transferring

Skin Lesion Classification using Class Activation Map

We proposed a two stage framework with only one network to analyze skin lesion images, we firstly trained a convolutional network to classify these images, and cropped the import regions which the network has the maximum activation value. In the second stage, we retrained this CNN with the image regions extracted from stage one and output the final probabilities. The two stage framework achieve...

Computing class fields via the Artin map

Based on an explicit representation of the Artin map for Kummer extensions, we present a method to compute arbitrary class fields. As in the proofs of the existence theorem, the problem is first reduced to the case where the field contains sufficiently many roots of unity. Using Kummer theory and an explicit version of the Artin reciprocity law we show how to compute class fields in this case. ...

Transferring Learned Search Heuristics Investigators

Transferring Knowledge to Smaller Net- Work with Class-distance Loss

Training a network with small capacity that can perform as well as a larger capacity network is an important problem that needs to be solved in real life applications which require fast inference time and small memory requirement. Previous approaches that transfer knowledge from a bigger network to a smaller network show little benefit when applied to state-of-the-art convolutional neural netwo...

Person Search Made Easy

In this study, we present a method to extensively reduce the number of retrieved images and increase the retrieval performance for the person queries on the broadcast news videos. A multi-modal approach which integrates face and text information is proposed. A state-of-theart face detection algorithm is improved using a skin color based method to eliminate the false alarms. This pruned set is c...