I have read the paper about the soft-NMS and the problem that tries to solve. Does it make sense to use this algorithm during inference apart from training? It smooths the predictions on the bounding boxes, but I am not sure if this makes sense during the inference process or if it can change the results.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.