CloudObjectDetectorAdaptationbyIntegrating DifferentSourceKnowledge

Despite with powerful generalization capability, the cloud model still cannot achieve error-free detection in a specific target domain. In this work, we present a novel Cloud Object detector adaptation method byIntegrating different source kNowledge (COIN).Thekey idea is to incorporate a public vision-language model (CLIP) to distill positive knowledge while refining negative knowledge for adaptation by self-promotion gradient direction alignment.