Although deep salient object detection (SOD) has achieved remarkable progress, deep SOD models are extremely data-hungry, requiring large-scale pixel-wise annotations to deliver such promising results. In this paper, we propose a novel yet effective method for SOD, coined SODGAN, which can generate infinite high-quality image-mask pairs requiring only a few labeled data, and these synthesized pairs can replace the human-labeled DUTS-TR to train any off-the-shelf SOD model. Its contribution is three-fold. 1) Our proposed diffusion embedding network can address the manifold mismatch and is tractable for the latent code generation, better matching with the ImageNet latent space. 2) For the first time, our proposed few-shot saliency mask generator can synthesize infinite accurate image synchronized saliency masks with a few labeled data. 3) Our proposed quality-aware discriminator can select highquality synthesized image-mask pairs from noisy synthetic data pool, improving the quality of synthetic data. For the first time, our SODGAN tackles SOD with synthetic data directly generated from the generative model, which opens up a new research paradigm for SOD. Extensive experimental results show that the saliency model trained on synthetic data can achieve $98.4\%$ F-measure of the saliency model trained on the DUTS-TR. Moreover, our approach achieves a new SOTA performance in semi/weakly-supervised methods, and even outperforms several fully-supervised SOTA methods. Code is available at https://github.com/wuzhenyubuaa/SODGAN
翻译:虽然深显性物体探测(SOD)取得了显著进展,但深重的SOD模型却极缺乏数据,需要大规模像素说明来提供这种有希望的结果。在本文中,我们为SOD提出了一种创新的、但有效的方法,创建了SODAN,它能够产生无限的高质量图像标模配对,只需要贴上标签的数据,而这些合成的配对可以取代人类标签的DUTS-TR,以训练任何现成的SOD模型。它的贡献是三倍的。 1 我们提议的传播嵌入网络可以解决多重错配,并且对于潜在代码的生成来说,可以拉动,更好地与图像网络潜在的空间相匹配。 2 首先,我们提议的微小的显性遮罩可以合成无限准确的图像显性遮罩,只需要几个贴标签的数据。 3 我们拟议的质量识别师可以选择高品质的DUTS-TR-TR-MS, 提高合成数据的质量。第一次,我们的SODADAN多处理SOD 和直接生成的合成数据模型的合成数据模型,在经过训练的S-RODS-G-G-G-S-RODB-S-S-G-S-S-S-G-GI-GI-S-SDB-S-S-SB-G-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-SB-S-S-SB-S-S-S-SBAR-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-