Title

Object Augmentation for Out-of-Context Object Recognition

Abstract

Abstract

The visual context in an image contains rich information about and between foreground objects and the background. Deep learning models learn contextual information implicitly in general. However, since training datasets generally do not include all possible contexts, deep models tend to memorize contextual details. This can lead to poor recognition performance when models are deployed in real-world applications since objects may appear in unexpected contexts or places. These types of objects are called out-of-context objects. In this work, we propose an object-level augmentation framework for more robust recognition of out-of-context objects. Our proposed augmentation methodology applies random object removal and object placement operations to images at the training phase. Our results show that, by using object-level augmentations, the out-of-context recognition performance of models can increase without losing performance on regular images. To analyze the effectiveness of the proposed method, we conduct a series of experiments for a multi-label image classification problem on the MS COCO dataset. Moreover, we provide a tool to generate images with out-of-context objects using the proposed augmentation framework.

Supervisor(s)

Supervisor(s)

OGUL CAN ERYUKSEL

Date and Location

Date and Location

2022-02-09 14:00:00

Category

Category

MSc_Thesis