Salient Object Detection with Dynamic Convolutions

Rohit Venkata Sai Dulam, Chandra Kambhamettu; Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops, 2025, pp. 1692-1702

Convolutional Neural Networks (CNNs) rely on content-independent convolution operations that extract features shared across the entire dataset, limiting their adaptability to individual inputs. In contrast, input-dependent architectures like Vision Transformers (ViTs) can adapt to the specific characteristics of each input. To enhance input adaptability in CNNs, we propose SODDCNet, an encoder-decoder architecture for Salient Object Detection (SOD) that employs large convolutions with dynamically generated weights via the self-attention mechanism. Additionally, unlike other CNN architectures, we utilize multiple large kernels in parallel to segment salient objects of various sizes. To pre-train the proposed model, we combine the COCO and OpenImages semantic segmentation datasets to create a 3.18M image dataset for SOD. Comprehensive quantitative experiments conducted on benchmark datasets demonstrate that SODDCNet performs competitively compared to state-of-the-art methods in SOD and Video SOD.