Pyramidal Attention for Saliency Detection

TL;DR

This paper introduces a pyramidal attention approach that enhances saliency detection using only RGB images by estimating depth features, achieving superior results without requiring depth data during training or testing.

Contribution

It proposes a novel pyramidal attention structure that leverages intermediate depth features estimated from RGB images to improve saliency detection performance.

Findings

Outperforms 21 and 40 state-of-the-art methods on multiple datasets.

Achieves significant performance improvements without using actual depth data.

Provides a new perspective on RGB-D saliency detection using estimated depth features.

Abstract

Salient object detection (SOD) extracts meaningful contents from an input image. RGB-based SOD methods lack the complementary depth clues; hence, providing limited performance for complex scenarios. Similarly, RGB-D models process RGB and depth inputs, but the depth data availability during testing may hinder the model's practical applicability. This paper exploits only RGB images, estimates depth from RGB, and leverages the intermediate depth features. We employ a pyramidal attention structure to extract multi-level convolutional-transformer features to process initial stage representations and further enhance the subsequent ones. At each stage, the backbone transformer model produces global receptive fields and computing in parallel to attain fine-grained global predictions refined by our residual convolutional attention decoder for optimal saliency prediction. We report significantly improved performance against 21 and 40 state-of-the-art SOD methods on eight RGB and RGB-D datasets, respectively. Consequently, we present a new SOD perspective of generating RGB-D SOD without acquiring depth data during training and testing and assist RGB methods with depth clues for improved performance. The code and trained models are available at https://github.com/tanveer-hussain/EfficientSOD2