Abstract
Recent semantic segmentation research has increasingly moved toward stronger context modeling, dense attention, and transformer-based architectures. Although these models achieve impressive performance, classical CNN-based segmentation pipelines remain attractive because of their simplicity, efficiency, and ease of implementation. This paper revisits a practical question: how far can a ResNet-based segmentation model be improved by only modifying the segmentation head? We propose ATV-Net, an Adaptive Triple-View Network that strengthens a ResNet-101 backbone using three simple but complementary receptive-field views. The micro view captures point-wise semantic responses, the local view models neighborhood structures and object boundaries, and the scout view provides enlarged contextual cues. Instead of fusing these views with fixed weights, ATV-Net introduces an Adaptive Decision Gate that dynamically selects receptive-field responses according to input scene characteristics. A compact global coordination layer is further applied to improve spatial and semantic consistency. Experiments on the Cityscapes validation set show that ATV-Net achieves 80.31\% mIoU. This result suggests that classical CNN-based segmentation is still far from obsolete: with simple receptive-field views and adaptive fusion, a ResNet-based pipeline can reach a competitive accuracy level without relying on transformer-style global attention or overly complex context modules.
Abstract (translated)
URL
https://arxiv.org/abs/2605.25803
