all AI news
DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection. (arXiv:2304.07082v1 [cs.CV])
cs.CV updates on arXiv.org arxiv.org
This paper presents a DETR-based method for cross-domain weakly supervised
object detection (CDWSOD), aiming at adapting the detector from source to
target domain through weak supervision. We think DETR has strong potential for
CDWSOD due to an insight: the encoder and the decoder in DETR are both based on
the attention mechanism and are thus capable of aggregating semantics across
the entire image. The aggregation results, i.e., image-level predictions, can
naturally exploit the weak supervision for domain alignment. Such motivated, …
aggregation alignment arxiv attention decoder detection encoder exploit global image insight paper predictions semantics supervision think through