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

by   Angira Sharma, et al.

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 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 (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 also test on general segmentation dataset, where class-agnostic segmentation loss outperforms cross-entropy based loss by huge margins on both region and edge metrics.



There are no comments yet.


page 2

page 6

page 11

page 12

page 18

page 20

page 21

page 22


Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses

Object detection is an important task in computer vision which serves a ...

Optimizing the F-measure for Threshold-free Salient Object Detection

Current CNN-based solutions to salient object detection (SOD) mainly rel...

CAGNet: Content-Aware Guidance for Salient Object Detection

Beneficial from Fully Convolutional Neural Networks (FCNs), saliency det...

Marginal loss and exclusion loss for partially supervised multi-organ segmentation

Annotating multiple organs in medical images is both costly and time-con...

Gated CRF Loss for Weakly Supervised Semantic Image Segmentation

State-of-the-art approaches for semantic segmentation rely on deep convo...

Automated Focal Loss for Image based Object Detection

Current state-of-the-art object detection algorithms still suffer the pr...

Class Anchor Clustering: a Distance-based Loss for Training Open Set Classifiers

Existing open set classifiers distinguish between known and unknown inpu...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.