Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation

06/20/2022
by   Tao Chen, et al.
5

Weakly supervised semantic segmentation with only image-level labels aims to reduce annotation costs for the segmentation task. Existing approaches generally leverage class activation maps (CAMs) to locate the object regions for pseudo label generation. However, CAMs can only discover the most discriminative parts of objects, thus leading to inferior pixel-level pseudo labels. To address this issue, we propose a saliency guided Inter- and Intra-Class Relation Constrained (I^2CRC) framework to assist the expansion of the activated object regions in CAMs. Specifically, we propose a saliency guided class-agnostic distance module to pull the intra-category features closer by aligning features to their class prototypes. Further, we propose a class-specific distance module to push the inter-class features apart and encourage the object region to have a higher activation than the background. Besides strengthening the capability of the classification network to activate more integral object regions in CAMs, we also introduce an object guided label refinement module to take a full use of both the segmentation prediction and the initial labels for obtaining superior pseudo-labels. Extensive experiments on PASCAL VOC 2012 and COCO datasets demonstrate well the effectiveness of I^2CRC over other state-of-the-art counterparts. The source codes, models, and data have been made available at <https://github.com/NUST-Machine-Intelligence-Laboratory/I2CRC>.

READ FULL TEXT

page 1

page 4

page 6

page 7

page 9

research
03/12/2021

Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation

Weakly-supervised semantic segmentation (WSSS) using image-level labels ...
research
05/09/2023

Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation (WSSS) models relying on class a...
research
03/26/2021

Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation

Semantic segmentation aims to classify every pixel of an input image. Co...
research
11/17/2019

Weakly Supervised Object Localization with Inter-Intra Regulated CAMs

Weakly supervised object localization (WSOL) aims to locate objects in i...
research
04/15/2021

Learning structure-aware semantic segmentation with image-level supervision

Compared with expensive pixel-wise annotations, image-level labels make ...
research
08/21/2023

Beyond Discriminative Regions: Saliency Maps as Alternatives to CAMs for Weakly Supervised Semantic Segmentation

In recent years, several Weakly Supervised Semantic Segmentation (WS3) m...
research
12/16/2021

Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation

Image-level weakly supervised semantic segmentation (WSSS) is a fundamen...

Please sign up or login with your details

Forgot password? Click here to reset