# IKKA: Inversion Classification via Critical Anomalies for Robust Visual Servoing

Source: [IKKA: Inversion Classification via Critical Anomalies for Robust Visual Servoing](<https://www.sota2.com/research/paper/69dc78937d0172140ec78b47>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-14T05:00:04.234Z

Authors: Darya Pavlenko

Published: 2026-04-09T20:37:27.000Z

## Abstract

We introduce IKKA (Inversion Classification via Critical Anomalies), a topologically motivated weighting framework for robust visual servoing under distribution shift. Unlike conventional outlier handling, IKKA treats maverick points as structurally informative observations: points where small perturbations can induce qualitatively different control responses or class assignments. The method combines local extremality, boundary transversality, and multi-scale persistence into a single anomaly weight, W(x) = E(x) x T(x) x M(x), which modulates control updates near ambiguous decision regions. We instantiate IKKA in a CPU-only embedded visual-servoing pipeline on Raspberry Pi 4 and evaluate it across 230 reproducible runs under nominal and stress conditions. In stress scenarios involving dim illumination and transient occlusion, IKKA reduces the 95th-percentile lateral error by 24% relative to a hybrid baseline (0.124 to 0.094) while increasing throughput from 20.0 to 24.8 Hz. Non-parametric analysis confirms a large effect size (Cliff's delta = 0.79).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Tracking Recovery on 30 occlusion obstacle runs](<https://www.sota2.com/research/sota/object-tracking-recovery-on-30-occlusion-obstacle-runs.md>): Object Tracking Recovery; 30 occlusion obstacle runs; Median Recovery Time (s): 0.38.

- [Visual Servoing on Visual Servoing Benchmark Nominal](<https://www.sota2.com/research/sota/visual-servoing-on-visual-servoing-benchmark-nominal.md>): Visual Servoing; Visual Servoing Benchmark Nominal; FPS: 24.8.

- [Visual Servoing on Visual Servoing Benchmark (Stress)](<https://www.sota2.com/research/sota/visual-servoing-on-visual-servoing-benchmark-stress.md>): Visual Servoing; Visual Servoing Benchmark (Stress); FPS: 24.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.08754>)

[PDF](<https://arxiv.org/pdf/2604.08754.pdf>)
