Weakly-Supervised Semantic Segmentation

142 papers with code • 6 benchmarks • 7 datasets

The semantic segmentation task is to assign a label from a label set to each pixel in an image. In the case of fully supervised setting, the dataset consists of images and their corresponding pixel-level class-specific annotations (expensive pixel-level annotations). However, in the weakly-supervised setting, the dataset consists of images and corresponding annotations that are relatively easy to obtain, such as tags/labels of objects present in the image.

( Image credit: Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing )

Libraries

Use these libraries to find Weakly-Supervised Semantic Segmentation models and implementations

Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation

cvi-szu/qa-clims 18 Jan 2024

Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation (WSSS), allowing the localization of object regions in an image using only image-level labels.

6
18 Jan 2024

Clustering-Guided Class Activation for Weakly Supervised Semantic Segmentation

DCVL-WSSS/ClusterCAM Access 2024

In this paper, we propose a novel class activation scheme that is able to uniformly highlight the whole object region.

8
05 Jan 2024

PointCT: Point Central Transformer Network for Weakly-supervised Point Cloud Semantic Segmentation

anhthuan1999/PointCT Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023

Although point cloud segmentation has a principal role in 3D understanding, annotating fully large-scale scenes for this task can be costly and time-consuming.

4
24 Dec 2023

Weakly Supervised Semantic Segmentation for Driving Scenes

k0u-id/carb 21 Dec 2023

Notably, the proposed method achieves 51. 8\% mIoU on the Cityscapes test dataset, showcasing its potential as a strong WSSS baseline on driving scene datasets.

11
21 Dec 2023

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training

linyq2117/tagclip 20 Dec 2023

As a result, we dissect the preservation of patch-wise spatial information in CLIP and proposed a local-to-global framework to obtain image tags.

32
20 Dec 2023

Progressive Feature Self-reinforcement for Weakly Supervised Semantic Segmentation

jessie459/feature-self-reinforcement 14 Dec 2023

Building upon this, we introduce a complementary self-enhancement method that constrains the semantic consistency between these confident regions and an augmented image with the same class labels.

6
14 Dec 2023

Foundation Model Assisted Weakly Supervised Semantic Segmentation

HAL-42/FMA-WSSS 6 Dec 2023

This work aims to leverage pre-trained foundation models, such as contrastive language-image pre-training (CLIP) and segment anything model (SAM), to address weakly supervised semantic segmentation (WSSS) using image-level labels.

25
06 Dec 2023

Weakly Supervised Semantic Segmentation by Knowledge Graph Inference

jia-zhang666/grm_layer 25 Sep 2023

Extensive experimentation on both the multi-label classification and segmentation network stages underscores the effectiveness of the proposed graph reasoning approach for advancing WSSS.

5
25 Sep 2023

Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation

wpy1999/bas 22 Sep 2023

In addition, our method also achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets.

42
22 Sep 2023

BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications

linjiatai/broadcam 7 Sep 2023

Class activation mapping~(CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation~(WSSS) and object localization~(WSOL).

2
07 Sep 2023