[1] A BEARMAN, O RUSSAKOVSKY, V FERRARI et al. What’s the point: semantic segmentation with point supervision, 549-565(2016).

[2] S LEE, M LEE, J LEE et al. Railroad is not a train: saliency as pseudo-pixel supervision for weakly supervised semantic segmentation, 5495-5505(2021).

[3] J FAN, Z ZHANG, T TAN et al. Cian: cross-image affinity net for weakly supervised semantic segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 10762-10769(2020).

[4] Y YAO, T CHEN, G S XIE et al. Non-salient region object mining for weakly supervised semantic segmentation, 2623-2632(2021).

[5] T ZHOU, M ZHANG, F ZHAO et al. Regional semantic contrast and aggregation for weakly supervised semantic segmentation, 4299-4309(2022).

[6] P T JIANG, Y YANG, Q HOU et al. L2g: a simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation, 16886-16896(2022).

[7] J AHN, S KWAK. Learning pixel-level semantic affinity with image-level supervision for weakly supervised SEMANTIC segmentation, 4981-4990(2018).

[8] R R SELVARAJU, M COGSWELL, A DAS et al. Grad-cam: visual explanations from deep networks via gradient-based localization, 618-626(2017).

[9] Y WANG, J ZHANG, M KAN et al. Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation, 12275-12284(2020).

[10] S H JO, I J YU, K S KIM. RecurSeed and CertainMix for weakly supervised semantic segmentation. arXiv preprint arXiv, 1, 2204.06754(2022).

[11] A DOSOVITSKIY, L BEYER, A KOLESNIKOV et al. An image is worth 16x16 words: transformers for image recognition at scale. https://www.xueshufan.com/publication/3119786062

[12] A VASWANI, N SHAZEER, N PARMAR et al. Attention is all you need, 6000-6010(2017).

[13] W GAO, F WAN, X PAN et al. Ts-cam: token semantic coupled attention map for weakly supervised object localization, 2886-2895(2021).

[14] L XU, W OUYANG, M BENNAMOUN et al. Multi-class token transformer for weakly supervised semantic segmentation, 4310-4319(2022).

[15] K HE, X CHEN, S XIE et al. Masked autoencoders are scalable vision learners, 16000-16009(2022).

[16] L HOYER, D DAI, H WANG et al. MIC: masked image consistency for context-enhanced domain adaptation, 11721-11732(2023).

[17] Yi WANG, Xiaojie GONG, Hao SU. Image segmentation method of surface defects for metal workpieces based on improved U-net. Journal of Applied Optics, 44, 86-92(2023).

[18] Yanchen YANG, Lijun YUN, Jianhua MEI et al. Gait recognition method of infrared human body images based on improved ViT. Journal of Applied Optics, 44, 71-78(2023).

[19] Jiaying LI, Wenting JIANG, Lin YANG et al. Fine-grained visual classification based on vision transformer. Computer Engineering and Design, 44, 916-921(2023).

[20] Zonghan SHI, Haitao ZHAO. Hyperspectral target tracking based on attention mechanism and additive angular margin loss. Journal of Applied Optics, 43, 893-903(2022).

[21] J LEE, E KIM, S YOON. Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation, 4071-4080(2021).

[22] J LEE, J CHOI, J MOK et al. Reducing information bottleneck for weakly supervised semantic segmentation. Advances in Neural Information Processing Systems, 34, 27408-27421(2021).

[23] J FAN, Z ZHANG, C SONG et al. Learning integral objects with intra-class discriminator for weakly-supervised semantic segmentation, 4283-4292(2020).

[24] T WU, J HUANG, G GAO et al. Embedded discriminative attention mechanism for weakly supervised semantic segmentation, 16765-16774(2021).

[25] L XU, W OUYANG, M BENNAMOUN et al. Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation, 6984-6993(2021).

[26] L CHEN, W WU, C FU et al. Weakly supervised semantic segmentation with boundary exploration, 347-362(2020).

[27] D ZHANG, H ZHANG, J TANG et al. Causal intervention for weakly-supervised semantic segmentation. Advances in Neural Information Processing Systems, 33, 655-666(2020).

[28] K SUN, H SHI, Z ZHANG et al. Ecs-net: improving weakly supervised semantic segmentation by using connections between class activation maps, 7283-7292(2021).

[29] Y SU, R SUN, G LIN et al. Context decoupling augmentation for weakly supervised semantic segmentation, 7004-7014(2021).

[30] Y LI, Z KUANG, L LIU et al. Pseudo-mask matters in weakly-supervised semantic segmentation, 6964-6973(2021).

[31] Y LI, Y DUAN, Z KUANG et al. Uncertainty estimation via response scaling for pseudo-mask noise mitigation in weakly-supervised semantic segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 36, 1447-1455(2022).

[32] M LEE, D KIM, H SHIM. Threshold matters in WSSS: manipulating the activation for the robust and accurate segmentation model against thresholds, 4330-4339(2022).