Log In Sign Up

Towards Single Stage Weakly Supervised Semantic Segmentation

by   Peri Akiva, et al.

The costly process of obtaining semantic segmentation labels has driven research towards weakly supervised semantic segmentation (WSSS) methods, using only image-level, point, or box labels. The lack of dense scene representation requires methods to increase complexity to obtain additional semantic information about the scene, often done through multiple stages of training and refinement. Current state-of-the-art (SOTA) models leverage image-level labels to produce class activation maps (CAMs) which go through multiple stages of refinement before they are thresholded to make pseudo-masks for supervision. The multi-stage approach is computationally expensive, and dependency on image-level labels for CAMs generation lacks generalizability to more complex scenes. In contrary, our method offers a single-stage approach generalizable to arbitrary dataset, that is trainable from scratch, without any dependency on pre-trained backbones, classification, or separate refinement tasks. We utilize point annotations to generate reliable, on-the-fly pseudo-masks through refined and filtered features. While our method requires point annotations that are only slightly more expensive than image-level annotations, we are to demonstrate SOTA performance on benchmark datasets (PascalVOC 2012), as well as significantly outperform other SOTA WSSS methods on recent real-world datasets (CRAID, CityPersons, IAD).


page 4

page 5

page 6

page 8


PCAMs: Weakly Supervised Semantic Segmentation Using Point Supervision

Current state of the art methods for generating semantic segmentation re...

Single-Stage Semantic Segmentation from Image Labels

Recent years have seen a rapid growth in new approaches improving the ac...

Exploiting Shape Cues for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation (WSSS) aims to produce pixel-wis...

Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class

Semantic segmentation tasks based on weakly supervised condition have be...

Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation

Semantic segmentation has been continuously investigated in the last ten...

Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation

Weakly Supervised Semantic Segmentation (WSSS) research has explored man...

Movable-Object-Aware Visual SLAM via Weakly Supervised Semantic Segmentation

Moving objects can greatly jeopardize the performance of a visual simult...