Knot-10:A Tightness-Stratified Benchmark for Real-World Knot Classification with Topological Difficulty Analysis
This work addresses a fine-grained visual classification problem for real-world applications like robotics or rescue operations, but it is incremental as it builds on existing methods with a new benchmark and analysis.
The paper tackles physical knot classification by introducing the Knots-10 benchmark with a deployment-oriented split, where models like Swin-T and TransFG achieve 97.2% accuracy on tightly dressed knots, but cross-domain tests with phone photographs show a 58-69 percentage-point drop in accuracy due to rope appearance bias.
Physical knot classification is a fine-grained visual classification (FGVC) scenario in which appearance cues are deliberately suppressed: different classes share the same rope material, color, and background, and class identity resides primarily in crossing structure. We introduce the Knots-10 benchmark, comprising 1,440 images with a deployment-oriented split that trains on loosely tied knots and tests on tightly dressed ones. Swin-T and TransFG both average 97.2% accuracy; PMG scores 94.5%, consistent with the hypothesis that jigsaw shuffling disrupts crossing continuity. McNemar tests cannot separate four of the five general-purpose backbones, so small ranking margins should be interpreted with caution. A Mantel permutation test shows that topological distance significantly correlates with confusion patterns in three of the five models (p < 0.01). We propose TACA regularization, which improves embedding-topology alignment from rho=0.46 to rho=0.65 without improving classification accuracy; a random-distance ablation yields comparable alignment, indicating the benefit is likely driven by generic regularization. A pilot cross-domain test with 100 phone photographs reveals a 58-69 percentage-point accuracy drop, exposing rope appearance bias as the dominant failure mode.