Generative Transformer for Accurate and Reliable Salient Object Detection

TL;DR

This paper explores the use of transformers for salient object detection, demonstrating improved accuracy and reliability by addressing over-confidence issues with a novel uncertainty estimation method called iGAN, which leverages MCMC for input-dependent latent variables.

Contribution

The paper introduces a transformer-based framework for salient object detection and proposes iGAN, a novel uncertainty estimation model using MCMC, to improve reliability of predictions.

Findings

Transformers outperform CNNs in salient object detection.

iGAN effectively estimates predictive uncertainty.

Transformer + iGAN achieves accurate and reliable detection.

Abstract

Transformer, which originates from machine translation, is particularly powerful at modeling long-range dependencies. Currently, the transformer is making revolutionary progress in various vision tasks, leading to significant performance improvements compared with the convolutional neural network (CNN) based frameworks. In this paper, we conduct extensive research on exploiting the contributions of transformers for accurate and reliable salient object detection. For the former, we apply transformer to a deterministic model, and explain that the effective structure modeling and global context modeling abilities lead to its superior performance compared with the CNN based frameworks. For the latter, we observe that both CNN and transformer based frameworks suffer greatly from the over-confidence issue, where the models tend to generate wrong predictions with high confidence. To estimate the reliability degree of both CNN- and transformer-based frameworks, we further present a latent variable model, namely inferential generative adversarial network (iGAN), based on the generative adversarial network (GAN). The stochastic attribute of the latent variable makes it convenient to estimate the predictive uncertainty, serving as an auxiliary output to evaluate the reliability of model prediction. Different from the conventional GAN, which defines the distribution of the latent variable as fixed standard normal distribution $\mathcal{N}(0,\mathbf{I})$, 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 both fully and weakly supervised salient object detection, and explain that iGAN within the transformer framework leads to both accurate and reliable salient object detection.