낡고 지친 회사원

https://arxiv.org/abs/2104.06401 Self-supervised object detection from audio-visual correspondence We tackle the problem of learning object detectors without supervision. Differently from weakly-supervised object detection, we do not assume image-level class labels. Instead, we extract a supervisory signal from audio-visual data, using the audio compone arxiv.org 1. Introduction 목표 : 아무 label이 없..

https://arxiv.org/abs/2208.07576 Object Discovery via Contrastive Learning for Weakly Supervised Object Detection Weakly Supervised Object Detection (WSOD) is a task that detects objects in an image using a model trained only on image-level annotations. Current state-of-the-art models benefit from self-supervised instance-level supervision, but since weak supervision arxiv.org 개요 WSOD(Weakly Sup..