Discriminative Learning of Deep Convolutional Feature Point Descriptors

ICCV 2015 Edgar Simo-SerraEduard TrullsLuis FerrazIasonas KokkinosPascal FuaFrancesc Moreno-Noguer

Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e.g. SIFT. In this paper we use Convolutional Neural Networks (CNNs) to learn discriminant patch representations and in particular train a Siamese network with pairs of (non-)corresponding patches... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Satellite Image Classification SAT-4 Contrastive loss Accuracy 98.74 # 2
Satellite Image Classification SAT-6 Contrastive loss Accuracy 98.55 # 2

Methods used in the Paper