Learning Semantic Part-Based Models from Google Images

D. Modolo, V. Ferrari

Research output: Contribution to journalArticlepeer-review

Abstract

We propose a technique to train semantic part-based models of object classes from Google Images. Our models encompass the appearance of parts and their spatial arrangement on the object, specific to each viewpoint. We learn these rich models by collecting training instances for both parts and objects, and automatically connecting the two levels. Our framework works incrementally, by learning from easy examples first, and then gradually adapting to harder ones. A key benefit of this approach is that it requires no manual part location annotations. We evaluate our models on the challenging PASCAL-Part dataset [1] and show how their performance increases at every step of the learning, with the final models more than doubling the performance of directly training from images retrieved by querying for part names (from 12.9 to 27.2 AP). Moreover, we show that our part models can help object detection performance by enriching the R-CNN detector with parts.
Original languageEnglish
Pages (from-to)1-8
Number of pages8
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
VolumePP
Issue number99
Early online date7 Jul 2017
DOIs
Publication statusE-pub ahead of print - 7 Jul 2017

Fingerprint

Dive into the research topics of 'Learning Semantic Part-Based Models from Google Images'. Together they form a unique fingerprint.

Cite this