Pyramidal Attention for Saliency Detection
This work addresses the limitation of RGB-based SOD methods that lack depth clues and RGB-D models that require depth data, offering a practical solution for complex scenarios without needing depth data during training or testing.
The paper tackles the problem of salient object detection (SOD) by proposing a method that uses only RGB images to estimate depth and leverage depth features, achieving significantly improved performance against 21 and 40 state-of-the-art methods on eight datasets.
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