Generative Transformer for Accurate and Reliable Salient Object Detection
Yuxin Mao, Jing Zhang, Zhexiong Wan, Xinyu Tian, Aixuan Li, Yunqiu Lv, Yuchao Dai
Abstract
We explore the impact of transformers on accurate and reliable salient object detection. For accuracy, we integrate the transformer with a deterministic model and delineate its advantages in structural modeling. Regarding reliability, we address the transformer’s tendency to produce overly confident, incorrect predictions. To gauge reliability implicitly, we introduce a latent variable model within the transformer framework, termed the inferential generative adversarial network (iGAN). The stochastic nature of the latent variable facilitates the estimation of predictive uncertainty, which serves as an auxiliary measure of the model’s prediction reliability. Different from the conventional GAN, which defines the distribution of the latent variable as fixed standard normal distribution <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {N}(0,\mathbf {I})$ </tex-math></inline-formula>. The proposed iGAN infers the latent variable by gradient-based Markov Chain Monte Carlo (MCMC), namely Langevin dynamics, leading to an input-dependent latent variable model. We apply our proposed iGAN to fully supervised salient object detection, explaining that iGAN within the transformer framework leads to both accurate and reliable salient object detection. The source code and experimental results are publicly available via our project page: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://npucvr.github.io/TransformerSOD</uri>.