Objects in Context

TLDR

Semantic context can reduce visual ambiguity in object categorization. The study proposes adding semantic object context as a post‑processing step to any existing categorization model. A conditional random field maximizes label agreement using either training‑derived or Google Sets context, and the approach is evaluated on PASCAL and MSRC datasets. Adding context significantly improves categorization accuracy.

Abstract

In the task of visual object categorization, semantic context can play the very important role of reducing ambiguity in objects' visual appearance. In this work we propose to incorporate semantic object context as a post-processing step into any off-the-shelf object categorization model. Using a conditional random field (CRF) framework, our approach maximizes object label agreement according to contextual relevance. We compare two sources of context: one learned from training data and another queried from Google Sets. The overall performance of the proposed framework is evaluated on the PASCAL and MSRC datasets. Our findings conclude that incorporating context into object categorization greatly improves categorization accuracy.