{"ID":2837412,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18865","arxiv_id":"2511.18865","title":"DualGazeNet: A Biologically Inspired Dual-Gaze Query Network for Salient Object Detection","abstract":"Recent salient object detection (SOD) methods aim to improve performance in four key directions: semantic enhancement, boundary refinement, auxiliary task supervision, and multi-modal fusion. In pursuit of continuous gains, these approaches have evolved toward increasingly sophisticated architectures with multi-stage pipelines, specialized fusion modules, edge-guided learning, and elaborate attention mechanisms. However, this complexity paradoxically introduces feature redundancy and cross-component interference that obscure salient cues, ultimately reaching performance bottlenecks. In contrast, human vision achieves efficient salient object identification without such architectural complexity. This contrast raises a fundamental question: can we design a biologically grounded yet architecturally simple SOD framework that dispenses with most of this engineering complexity, while achieving state-of-the-art accuracy, computational efficiency, and interpretability? In this work, we answer this question affirmatively by introducing DualGazeNet, a biologically inspired pure Transformer framework that models the dual biological principles of robust representation learning and magnocellular-parvocellular dual-pathway processing with cortical attention modulation in the human visual system. Extensive experiments on five RGB SOD benchmarks show that DualGazeNet consistently surpasses 25 state-of-the-art CNN- and Transformer-based methods. On average, DualGazeNet achieves about 60\\% higher inference speed and 53.4\\% fewer FLOPs than four Transformer-based baselines of similar capacity (VST++, MDSAM, Sam2unet, and BiRefNet). Moreover, DualGazeNet exhibits strong cross-domain generalization, achieving leading or highly competitive performance on camouflaged and underwater SOD benchmarks without relying on additional modalities.","short_abstract":"Recent salient object detection (SOD) methods aim to improve performance in four key directions: semantic enhancement, boundary refinement, auxiliary task supervision, and multi-modal fusion. In pursuit of continuous gains, these approaches have evolved toward increasingly sophisticated architectures with multi-stage p...","url_abs":"https://arxiv.org/abs/2511.18865","url_pdf":"https://arxiv.org/pdf/2511.18865v1","authors":"[\"Yu Zhang\",\"Haoan Ping\",\"Yuchen Li\",\"Zhenshan Bing\",\"Fuchun Sun\",\"Alois Knoll\"]","published":"2025-11-24T08:08:22Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\",\"Convolutional Neural Network\"]","has_code":false}