AgMIC: Agricultural Masked Image Consistency for Cross-Domain Segmentation

Muhib Ullah, Nisar Ali, Numair Nadeem, Abdul Bais; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025, pp. 7139-7149

Canola crop segmentation is critical for monitoring crop coverage and health, and identifying growth variability. It allows farmers to implement variable rate applications based on localized crop conditions. Recent advances in deep learning (DL) have shown promising results for crop segmentation using high-resolution imagery. Although DL-based models perform well on their source domain (ground vehicle imagery), they exhibit significant performance drops when applied to the target domain (unmanned aerial vehicles). This degradation occurs due to substantial differences in viewing perspective, image resolution, object appearance scale, and spatial context between the two domains. To bridge this domain gap, this paper presents agricultural masked image consistency (AgMIC), an enhanced unsupervised domain adaptation (UDA) framework for cross-domain canola crop segmentation. Unlike existing MIC method that employs random masking strategies, AgMIC introduces agricultural pattern-aware masking, which leverages crop density patterns to preserve structural field information for enhanced cross-domain contextual understanding. Additionally, it incorporates confidence-aware pseudo-label enhancement with adaptive thresholding to filter unreliable predictions. Experimental results demonstrate that AgMIC achieves superior performance with a mean intersection over union of 0.7603, outperforming state-of-the-art UDA methods, including MIC (0.7436), RUDA (0.7326), and HRDA (0.7248).