{"slug": "egrnet-a-lightweight-semantic-segmentation-network-with-edge-gated-refinement", "title": "EGRNet: A Lightweight Semantic Segmentation Network with Edge-Gated Refinement and Adversarial Sensing", "summary": "Researchers have developed EGRNet, a lightweight semantic segmentation network with only 0.46 million parameters that achieves 65.28% mean Intersection over Union on the Cityscapes dataset, designed for real-time urban scene understanding in autonomous systems. The model introduces an Edge-Gated Refinement module and a lightweight adversarial attack detection strategy to balance accuracy, efficiency, and robustness for edge-device deployment.", "body_md": "arXiv:2607.19617v1 Announce Type: new\nAbstract: As autonomous systems and smart cities continue to evolve, the demand for efficient and robust scene understanding becomes increasingly critical. Semantic segmentation plays a key role in enabling autonomous vehicles to comprehend complex urban environments. However, achieving high accuracy with minimal computational cost remains a significant challenge. In this paper, we present Edge-Gated Refinement Network (EGRNet), a lightweight and efficient deep learning model designed for real-time semantic segmentation in urban scenarios. The model incorporates depthwise separable convolutions to reduce computational complexity and dilated residual blocks for capturing rich multi-scale contextual information. Additionally, we introduce a novel Edge-Gated Refinement (EGR) module, which adaptively fuses original and refined features through a learnable gating mechanism, enhancing boundary preservation and edge-sensitive regions. To further improve feature representation, Squeeze-and-Excitation (SE) attention is applied across the network. With only 0.46M parameters, EGRNet achieves state-of-the-art performance while maintaining low computational overhead. When evaluated on the Cityscapes dataset, the model attains a mean Intersection over Union (mIoU) of 65.28%, demonstrating strong accuracy with minimal resource consumption. Moreover, we introduce a lightweight adversarial attack detection strategy, ensuring robustness against adversarial inputs without compromising real-time performance. By combining efficiency, accuracy, and resilience, EGRNet is well-suited for deployment on edge devices in safety-critical real-time applications.", "url": "https://wpnews.pro/news/egrnet-a-lightweight-semantic-segmentation-network-with-edge-gated-refinement", "canonical_source": "https://arxiv.org/abs/2607.19617", "published_at": "2026-07-23 04:00:00+00:00", "updated_at": "2026-07-23 04:25:53.851981+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "autonomous-vehicles", "ai-research", "ai-infrastructure"], "entities": ["EGRNet", "Cityscapes dataset", "Edge-Gated Refinement module", "Squeeze-and-Excitation"], "alternates": {"html": "https://wpnews.pro/news/egrnet-a-lightweight-semantic-segmentation-network-with-edge-gated-refinement", "markdown": "https://wpnews.pro/news/egrnet-a-lightweight-semantic-segmentation-network-with-edge-gated-refinement.md", "text": "https://wpnews.pro/news/egrnet-a-lightweight-semantic-segmentation-network-with-edge-gated-refinement.txt", "jsonld": "https://wpnews.pro/news/egrnet-a-lightweight-semantic-segmentation-network-with-edge-gated-refinement.jsonld"}}