Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation

TL;DR

This paper introduces a class-agnostic segmentation loss that learns region clusters without predefined class labels, improving salient object detection especially with noisy data and general segmentation tasks.

Contribution

The novel CAS loss function enables weakly-supervised learning of region clusters, showing robustness to class imbalance and significant performance gains in salient object detection.

Findings

Outperforms state-of-the-art in low-fidelity training scenarios by ~50%

Matches or exceeds performance of existing methods with high-fidelity data

Significantly improves general segmentation results across datasets

Abstract

In this paper we present a novel loss function, called class-agnostic segmentation (CAS) loss. With CAS loss the class descriptors are learned during training of the network. We don't require to define the label of a class a-priori, rather the CAS loss clusters regions with similar appearance together in a weakly-supervised manner. Furthermore, we show that the CAS loss function is sparse, bounded, and robust to class-imbalance. We first apply our CAS loss function with fully-convolutional ResNet101 and DeepLab-v3 architectures to the binary segmentation problem of salient object detection. We investigate the performance against the state-of-the-art methods in two settings of low and high-fidelity training data on seven salient object detection datasets. For low-fidelity training data (incorrect class label) class-agnostic segmentation loss outperforms the state-of-the-art methods on salient object detection datasets by staggering margins of around 50%. For high-fidelity training data (correct class labels) class-agnostic segmentation models perform as good as the state-of-the-art approaches while beating the state-of-the-art methods on most datasets. In order to show the utility of the loss function across different domains we then also test on general segmentation dataset, where class-agnostic segmentation loss outperforms competing losses by huge margins.