10-shot image generation on COCO 2014 val

Metric: mIoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	mIoU▼	Extra Data	Paper	Date↕	Code
1	DHR (Swin-L, Mask2Former)	56.8	No	DHR: Dual Features-Driven Hierarchical Rebalanci...	2024-03-30	Code
2	SemPLeS (Swin-L)	56.1	No	Semantic Prompt Learning for Weakly-Supervised S...	2024-01-22	Code
3	WSSS-SAM(DeepLabV2-ResNet101)	55.6	Yes	An Alternative to WSSS? An Empirical Study of th...	2023-05-02	Code
4	FMA-WSSS (Swin-L)	55.4	No	Foundation Model Assisted Weakly Supervised Sema...	2023-12-06	Code
5	CoSA (SWIN-B, multi-stage)	53.7	No	Weakly Supervised Co-training with Swapping Assi...	2024-02-27	Code
6	CoSA (ViT-B, single-stage)	51.1	No	Weakly Supervised Co-training with Swapping Assi...	2024-02-27	Code
7	WeakTr (ViT-S, multi-stage)	50.3	No	WeakTr: Exploring Plain Vision Transformer for W...	2023-04-03	Code
8	MARS (ResNet-101, multi-stage)	49.4	No	MARS: Model-agnostic Biased Object Removal witho...	2023-04-19	Code
9	WeakTr (DeiT-S, multi-stage)	46.9	No	WeakTr: Exploring Plain Vision Transformer for W...	2023-04-03	Code
10	RS+EPM (ResNet-101, multi-stage)	46.4	No	RecurSeed and EdgePredictMix: Pseudo-Label Refin...	2022-04-14	Code
11	T2MDiffusion(DeepLabV2-ResNet101)	45.7	Yes	From Text to Mask: Localizing Entities Using the...	2023-09-08	Code
12	FBR	45.6	No	Fine-grained Background Representation for Weakl...	2024-06-22	Code
13	CLIP-ES(DeepLabV2-ResNet101)	45.4	No	CLIP is Also an Efficient Segmenter: A Text-Driv...	2022-12-16	Code
14	ACR(DeeplabV1-ResNet38)	45.3	No	-	-	Code
15	BECO(DeepLabV3Plus+R101)	45.1	No	-	-	Code
16	ViT-PCM	45	No	Max Pooling with Vision Transformers reconciles ...	2022-10-31	Code
17	ACR-WSSS(DeepLabV2-ResNet101)	45	No	All-pairs Consistency Learning for Weakly Superv...	2023-08-08	Code
18	AMN (DeepLabV2-ResNet101)	44.7	No	Threshold Matters in WSSS: Manipulating the Acti...	2022-03-30	Code
19	L2G (DeepLabV2-ResNet101)	44.2	No	L2G: A Simple Local-to-Global Knowledge Transfer...	2022-04-07	Code
20	RIB (DeepLabV2-ResNet101, No Saliency)	43.8	No	Reducing Information Bottleneck for Weakly Super...	2021-10-13	Code
21	SIPE(ResNet-38, no saliency, no RW)	43.6	No	Self-supervised Image-specific Prototype Explora...	2022-03-06	Code
22	RS+EPM (ResNet-50, single-stage)	42.2	No	RecurSeed and EdgePredictMix: Pseudo-Label Refin...	2022-04-14	Code
23	ClusterCAM	41.8	No	-	-	Code
24	URN(Res2Net-101, no saliency, no RW)	41.5	No	Uncertainty Estimation via Response Scaling for ...	2021-12-14	Code
25	URN(ScaleNet-101, no saliency, no RW)	40.8	No	Uncertainty Estimation via Response Scaling for ...	2021-12-14	Code
26	URN(ResNet-101, no saliency, no RW)	40.7	No	Uncertainty Estimation via Response Scaling for ...	2021-12-14	Code
27	URN(ResNet-38, no saliency, no RW)	40.5	No	Uncertainty Estimation via Response Scaling for ...	2021-12-14	Code
28	PMM(ScaleNet101, no saliency, no RW)	40.2	No	Pseudo-mask Matters in Weakly-supervised Semanti...	2021-08-30	Code
29	AFA	38.9	No	Learning Affinity from Attention: End-to-End Wea...	2022-03-05	Code
30	PMM(ResNet38, no saliency, no RW)	36.7	No	Pseudo-mask Matters in Weakly-supervised Semanti...	2021-08-30	Code
31	OC-CSE(ResNet38, no saliency, no RW)	36.4	No	-	-	Code
32	VWL-L	36.2	No	Weakly-Supervised Semantic Segmentation with Vis...	2022-02-10	Code
33	VWL-M	36.1	No	Weakly-Supervised Semantic Segmentation with Vis...	2022-02-10	Code
34	EPS	35.7	Yes	Railroad is not a Train: Saliency as Pseudo-pixe...	2021-05-19	Code
35	SLRNet	35	No	Learning Self-Supervised Low-Rank Network for Si...	2022-03-19	Code
36	SGAN	33.6	Yes	Saliency Guided Self-attention Network for Weakl...	2019-10-12	Code
37	IRNet+CONTA	33.4	No	Causal Intervention for Weakly-Supervised Semant...	2020-09-26	-
38	GroupWSSS	28.4	Yes	Group-Wise Semantic Mining for Weakly Supervised...	2020-12-09	Code
39	DSRG	26	Yes	-	-	Code

#1DHR (Swin-L, Mask2Former)SOTA
56.8
mIoU· 2024-03-30
DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation Code
#2SemPLeS (Swin-L)SOTA
56.1
mIoU· 2024-01-22
Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation Code
#3WSSS-SAM(DeepLabV2-ResNet101)SOTA
55.6
mIoU· Extra Data· 2023-05-02
An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems Code
#4FMA-WSSS (Swin-L)
55.4
mIoU· 2023-12-06
Foundation Model Assisted Weakly Supervised Semantic Segmentation Code
#5CoSA (SWIN-B, multi-stage)
53.7
mIoU· 2024-02-27
Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation Code
#6CoSA (ViT-B, single-stage)
51.1
mIoU· 2024-02-27
Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation Code
#7WeakTr (ViT-S, multi-stage)SOTA
50.3
mIoU· 2023-04-03
WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation Code
#8MARS (ResNet-101, multi-stage)
49.4
mIoU· 2023-04-19
MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation Code
#9WeakTr (DeiT-S, multi-stage)
46.9
mIoU· 2023-04-03
WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation Code
#10RS+EPM (ResNet-101, multi-stage)SOTA
46.4
mIoU· 2022-04-14
RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks Code
#11T2MDiffusion(DeepLabV2-ResNet101)
45.7
mIoU· Extra Data· 2023-09-08
From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models Code
#12FBR
45.6
mIoU· 2024-06-22
Fine-grained Background Representation for Weakly Supervised Semantic Segmentation Code
#13CLIP-ES(DeepLabV2-ResNet101)
45.4
mIoU· 2022-12-16
CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation Code
#14ACR(DeeplabV1-ResNet38)
45.3
mIoU
No paperCode
#15BECO(DeepLabV3Plus+R101)
45.1
mIoU
No paperCode
#16ViT-PCM
45
mIoU· 2022-10-31
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation Code
#17ACR-WSSS(DeepLabV2-ResNet101)
45
mIoU· 2023-08-08
All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation Code
#18AMN (DeepLabV2-ResNet101)SOTA
44.7
mIoU· 2022-03-30
Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds Code
#19L2G (DeepLabV2-ResNet101)
44.2
mIoU· 2022-04-07
L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation Code
#20RIB (DeepLabV2-ResNet101, No Saliency)SOTA
43.8
mIoU· 2021-10-13
Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation Code
#21SIPE(ResNet-38, no saliency, no RW)
43.6
mIoU· 2022-03-06
Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation Code
#22RS+EPM (ResNet-50, single-stage)
42.2
mIoU· 2022-04-14
RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks Code
#23ClusterCAM
41.8
mIoU
No paperCode
#24URN(Res2Net-101, no saliency, no RW)
41.5
mIoU· 2021-12-14
Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation Code
#25URN(ScaleNet-101, no saliency, no RW)
40.8
mIoU· 2021-12-14
Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation Code
#26URN(ResNet-101, no saliency, no RW)
40.7
mIoU· 2021-12-14
Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation Code
#27URN(ResNet-38, no saliency, no RW)
40.5
mIoU· 2021-12-14
Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation Code
#28PMM(ScaleNet101, no saliency, no RW)SOTA
40.2
mIoU· 2021-08-30
Pseudo-mask Matters in Weakly-supervised Semantic Segmentation Code
#29AFA
38.9
mIoU· 2022-03-05
Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers Code
#30PMM(ResNet38, no saliency, no RW)
36.7
mIoU· 2021-08-30
Pseudo-mask Matters in Weakly-supervised Semantic Segmentation Code
#31OC-CSE(ResNet38, no saliency, no RW)
36.4
mIoU
No paperCode
#32VWL-L
36.2
mIoU· 2022-02-10
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling Code
#33VWL-M
36.1
mIoU· 2022-02-10
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling Code
#34EPSSOTA
35.7
mIoU· Extra Data· 2021-05-19
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation Code
#35SLRNet
35
mIoU· 2022-03-19
Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation Code
#36SGANSOTA
33.6
mIoU· Extra Data· 2019-10-12
Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation Code
#37IRNet+CONTA
33.4
mIoU· 2020-09-26
Causal Intervention for Weakly-Supervised Semantic Segmentation
#38GroupWSSS
28.4
mIoU· Extra Data· 2020-12-09
Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation Code
#39DSRG
26
mIoU· Extra Data
No paperCode