To leverage video streams, PatchDriveNet reuses patch embeddings from the previous frame using a lightweight optical flow predictor. Only patches with significant motion (displacement >3 pixels) are recomputed – reducing redundant computation by up to 65%.
: Similar to "PatchCore" algorithms, patch-based networks can detect anomalies by comparing individual test patches against a memory bank of "normal" image features. Significant deviations in a single patch can signal a fault even if the overall image appears standard.
: Researchers have found that while a normal DriveNet model focuses on curbs and lane lines to steer, an adversarial patch can distract it .