SOURCE-LINKED INTELLIGENCE

Reading Decoder Trajectories: Training-Free Counterfactual Query-Trajectory Reliability for Small-Object Detection

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Small-object detection remains challenging because limited pixels cause information loss and suppress the scale knowledge encoded in pretrained detectors. Existing approaches mainly improve representations through multiscale training, architecture redesign, or parameter adaptation, implicitly assuming that frozen models lack the required capability. We challenge this assumption and hypothesize that small-object knowledge already exists in frozen detectors but remains underactivated and unstable during query evolution. To test this hypothesis, we propose Counterfactual Query-Trajectory Reliabil

Read original source ↗ Open in workspace

recordType

paper

region

Global