Towards Instance Segmentation with Object Priority: Prominent Object Detection and Recognition

TL;DR

This paper introduces the problem of prominent object detection and recognition, aiming to identify, segment, and classify the most important scene element, inspired by human perception, and proposes a method to address this integrated task.

Contribution

It formulates a new unified problem combining saliency, segmentation, and recognition, and proposes a baseline method to tackle this challenging task.

Findings

Proposed a model that predicts the most important region and segments associated objects.

Evaluations against human data show promising performance but highlight the task's complexity.

The problem remains challenging and warrants further research.

Abstract

This manuscript introduces the problem of prominent object detection and recognition inspired by the fact that human seems to priorities perception of scene elements. The problem deals with finding the most important region of interest, segmenting the relevant item/object in that area, and assigning it an object class label. In other words, we are solving the three problems of saliency modeling, saliency detection, and object recognition under one umbrella. The motivation behind such a problem formulation is (1) the benefits to the knowledge representation-based vision pipelines, and (2) the potential improvements in emulating bio-inspired vision systems by solving these three problems together. We are foreseeing extending this problem formulation to fully semantically segmented scenes with instance object priority for high-level inferences in various applications including assistive vision. Along with a new problem definition, we also propose a method to achieve such a task. The proposed model predicts the most important area in the image, segments the associated objects, and labels them. The proposed problem and method are evaluated against human fixations, annotated segmentation masks, and object class categories. We define a chance level for each of the evaluation criterion to compare the proposed algorithm with. Despite the good performance of the proposed baseline, the overall evaluations indicate that the problem of prominent object detection and recognition is a challenging task that is still worth investigating further.