paper-with-me

홈 › Papers

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

2021-07-16 · Angira Sharma, Naeemullah Khan, Muhammad Mubashar, Ganesh Sundaramoorthi, Philip Torr

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.

📄 PDF Abstract BibTeX arXiv:2108.04226

Code (1)

sofmonk/class_agnostic_loss_saliency 공식 구현 pytorch

Tasks

Objectobject-detectionObject DetectionSalient Object DetectionSegmentation

Similar Papers 제목 키워드 기반

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

2020-10-28 · Angira Sharma, Naeemullah Khan, Ganesh Sundaramoorthi, Philip Torr

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 cla…

Objectobject-detectionObject DetectionSalient Object Detection+1

Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

2021-04-04 · CVPR 2021 1 · Xinggang Wang, Jiapei Feng, Bin Hu, Qi Ding 외

Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based …

Box-supervised Instance SegmentationInstance SegmentationMulti-Task LearningObject+4

A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentation

2022-12-29 · Yuhang Zhang, Shishun Tian, Muxin Liao, Zhengyu Zhang 외

Video semantic segmentation (VSS) is beneficial for dealing with dynamic scenes due to the continuous property of the real-world environment. On the one hand, some methods alleviate the predicted inconsistent problem bet…

Domain GeneralizationSegmentationSemantic SegmentationVideo Semantic Segmentation

Saliency-Aware Class-Agnostic Food Image Segmentation

2021-02-13 · Sri Kalyan Yarlagadda, Daniel Mas Montserrat, David Guerra, Carol J. Boushey 외

Advances in image-based dietary assessment methods have allowed nutrition professionals and researchers to improve the accuracy of dietary assessment, where images of food consumed are captured using smartphones or weara…

Image SegmentationNutritionSemantic Segmentation

Regularized Densely-connected Pyramid Network for Salient Instance Segmentation

2020-08-28 · Yu-Huan Wu, Yun Liu, Le Zhang, Wang Gao 외

Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we propose a new pipeline for end-to-end salie…

DecoderInstance Segmentationobject-detectionObject Detection+3