0 参考资料

• https://course.zhidx.com/c/MjUxYzUxODYzMDkwYWViNjBjZjM=
• https://zhuanlan.zhihu.com/p/42058498
• https://www.bilibili.com/video/BV1S5411w7Yo?p=5
• https://github.com/gyguo/awesome-weakly-supervised-semantic-segmentation-image

1.1. Results on PASCAL VOC 2012 dataset

• For each method, I will provide the name of baseline in brackets if it has.
• Sup.:
  • I-image-level class label
  • B-bounding box label
  • S-scribble label
  • P-point label
• Bac. C: Method for generating pseudo label, or backbone of the classification network.
• Arc. S: backbone and method of the segmentation network.
• Pre.s : The dataset used to pre-train the segmentation network,
  • "I" denotes ImageNet,
  • "C" denotes COCO.
  • Note that many works use COCO pre-trained DeepLab model but not mentioned in the paper.
• For methods that use multiple backbones, I only reports the results of ResNet101.
• "-" indicates no fully-supervised model is utilized, "?" indicates the corresponding item is not mentioned in the paper.

Method	Pub.	Bac. C	Arc. S	Sup.	Extra data	Pre.S	val	test	Code	Paper	Note
AffinityNet	CVPR18	ResNet38	ResNet38	I	-	?	61.7	63.7	code (opens new window)	paper (opens new window)
ICD	CVPR20	VGG16	ResNet101 DeepLabv1	I	-	?	64.1	64.3	code (opens new window)	paper (opens new window)
IRN	CVPR19	ResNet50	ResNet50 DeepLabv2	I	-	I	63.5	64.8	code (opens new window)	paper (opens new window)
IAL	IJCV20	ResNet?	ResNet?	I	-	I	64.3	65.4	-	paper (opens new window)
SSDD (PSA)	ICCV19	ResNet38	ResNet38	I	-	I	64.9	65.5	code (opens new window)	paper (opens new window)
SEAM	CVPR20	ResNet38	ResNet38 DeepLabv2	I	-	I	64.5	65.7	code (opens new window)	paper (opens new window)
SC-CAM	CVPR20	ResNet38	ResNet101 DeepLabv2	I	-	?	66.1	65.9	code (opens new window)	paper (opens new window)
RRM	AAAI20	ResNet38	ResNet101 DeepLabv2	I	-	?	66.3	66.5	code (opens new window)	paper (opens new window)
BES	ECCV20	ResNet50	ResNet101 DeepLabv2	I	-	?	65.7	66.6	code (opens new window)	paper (opens new window)
CONTA (+SEAM)	NeurIPS20	ResNet38	ResNet101 DeepLabv2	I	-	?	66.1	66.7	code (opens new window)	paper (opens new window)
Puzzle-CAM	ICIP21	ResNeSt-101	ResNeSt-101 DeepLabv3+	I	-	?	66.9	67.7	code (opens new window)	paper (opens new window)	Note (opens new window)
VWE	IJCAI21	ResNet101	ResNet101 DeepLabv2	I	-	?	67.2	67.3	code (opens new window)	paper (opens new window)	Note (opens new window)
WSGCN (IRN)	ICME21	ResNet50	ResNet101 DeepLabv2	I	-	I	66.7	68.8	code (opens new window)	paper (opens new window)	Note (opens new window)
CPN	ICCV21	ResNet38	ResNet38 DeepLabv1	I	-	?	67.8	68.5	code (opens new window)	paper (opens new window)
RPNet	arxiv21	ResNet101	ResNet50 DeepLabv2	I	-	I	68.0	68.2	code (opens new window)	paper (opens new window)
AdvCAM	CVPR21	ResNet50	ResNet101 DeepLabv2	I	-	I	68.1	68.0	code (opens new window)	paper (opens new window)
WSGCN (IRN)	ICME21	ResNet50	ResNet101 DeepLabv2	I	-	I+C	68.7	69.3	code (opens new window)	paper (opens new window)	Note (opens new window)
Puzzle-CAM	ICIP21	ResNeSt-101	ResNeSt-269 DeepLabv3+	I	-	?	71.9	72.2	code (opens new window)	paper (opens new window)	Note (opens new window)
CDA									code (opens new window)	paper (opens new window)

2.1. Supervised by image tags without extra data.(such as saliency)

2021

• AdvCAM: " Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation" CVPR2021
• WSGCN: "Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks" ICME2021
• PuzzleCAM: "Puzzle-CAM Improved localization via matching partial and full features" ICIP2021
• CDA: "Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation" 2021arXiv
• VWE: "Learning Visual Words for Weakly-Supervised Semantic Segmentation" IJCAI2021
• CPN: "Complementary Patch for Weakly Supervised Semantic Segmentation" ICCV2021
• RPNet: "Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation" arxiv2021
• Method: "" 2021

2020

• RRM: "Reliability Does Matter An End-to-End Weakly Supervised Semantic Segmentation Approach" AAAI2020
• IAL: "Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning" IJCV2020
• SEAM: "Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation" CVPR2020
• SC-CAM: "Weakly-Supervised Semantic Segmentation via Sub-category Exploration" CVPR2020
• ICD: "Learning Integral Objects with Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation" CVPR2020
• Fan et al.: "Employing multi-estimations for weakly-supervised semantic segmentation" ECCV2020
• MCIS: "Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation" 2020
• BES: "Weakly Supervised Semantic Segmentation with Boundary Exploration" ECCV2020
• CONTA: "Causal intervention for weakly-supervised semantic segmentation" NeurIPS2020
• Method: "Find it if You Can: End-to-End Adversarial Erasing for Weakly-Supervised Semantic Segmentation" 2020arXiv
• Zhang et al.: "Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation" ECCV2020

2019

• IRN: "Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations" CVPR2019
• Ficklenet: " Ficklenet: Weakly and semi-supervised semantic image segmentation using stochastic inference" CVPR2019
• Lee *et al.*: "Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation" ICCV2019
• OAA: "Integral Object Mining via Online Attention Accumulation" ICCV2019
• SSDD: "Self-supervised difference detection for weakly-supervised semantic segmentation" ICCV2019

2018

• DSRG: "Weakly-supervised semantic segmentation network with deep seeded region growing" CVPR2018
• AffinityNet: "Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation" CVPR2018
• GAIN: " Tell me where to look: Guided attention inference network" CVPR2018
• AISI: "Associating inter-image salient instances for weakly supervised semantic segmentation" ECCV2018
• SeeNet: "Self-Erasing Network for Integral Object Attention" NeurIPS2018
• Method: "" 2018

2017

• CrawlSeg: "Weakly Supervised Semantic Segmentation using Web-Crawled Videos" CVPR2017
• WebS-i2: "Webly supervised semantic segmentation" CVPR2017
• Oh *et al*.: "Exploiting saliency for object segmentation from image level labels" CVPR2017
• TPL: "Two-phase learning for weakly supervised object localization" ICCV2017

2016

• SEC: "Seed, expand and constrain: Three principles for weakly-supervised image segmentation" ECCV2016
• AF-SS: "Augmented Feedback in Semantic Segmentation under Image Level Supervision" 2016

2.2. Supervised by image tags with extra data.(such as saliency)

2021

• SPML: "Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning" ICLR2021

• Li et al.: "Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation" AAAI2021

• DRS: "Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation" AAAI2021

• **Yao et al. **: "Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation" CVPR2021

• EDAM: "Embedded Discriminative Attention Mechanism for Weakly Supervised Semantic Segmentation" CVPR2021

• AuxSegNet: "Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation" ICCV2021