Semantic Aware Attention Based Deep Object Co-segmentation

TL;DR

This paper introduces a novel attention mechanism in deep neural networks for object co-segmentation, achieving state-of-the-art results with reduced computational time by efficiently selecting semantically related features.

Contribution

It proposes a new attention-based approach in the bottleneck layer for object co-segmentation, enabling linear time segmentation of multiple images.

Findings

Achieves state-of-the-art performance on multiple datasets.

Reduces computational time significantly.

Efficiently segments multiple images in linear time.

Abstract

Object co-segmentation is the task of segmenting the same objects from multiple images. In this paper, we propose the Attention Based Object Co-Segmentation for object co-segmentation that utilize a novel attention mechanism in the bottleneck layer of deep neural network for the selection of semantically related features. Furthermore, we take the benefit of attention learner and propose an algorithm to segment multi-input images in linear time complexity. Experiment results demonstrate that our model achieves state of the art performance on multiple datasets, with a significant reduction of computational time.