Rethinking open-world object detection in autonomous driving scenarios
Existing object detection models have been demonstrated to successfully discriminate and
localize the predefined object categories under the seen or similar situations. However, the …
localize the predefined object categories under the seen or similar situations. However, the …
Asynchronous generative adversarial network for asymmetric unpaired image-to-image translation
The unpaired image-to-image translation aims to translate input images from one source
domain to some desired outputs in a target domain by learning from unpaired training data …
domain to some desired outputs in a target domain by learning from unpaired training data …
Pixel bleach network for detecting face forgery under compression
The existing face forgery algorithms have achieved remarkable progress in how to generate
reasonable facial images and can even successfully deceive human beings. Considering …
reasonable facial images and can even successfully deceive human beings. Considering …
Dynamic relevance learning for few-shot object detection
W Liu, C Wang, H Li, S Yu, J Wu - ar** function that aims to convert an image
from a source domain to another target domain. With the proposal and further developments …
from a source domain to another target domain. With the proposal and further developments …
Disentangled representation learning and enhancement network for single image de-raining
In this paper, we present a disentangled representation learning and enhancement network
(DRLE-Net) to address the challenging single image de-raining problems, ie, raindrop and …
(DRLE-Net) to address the challenging single image de-raining problems, ie, raindrop and …
Fully Unsupervised Domain-Agnostic Image Retrieval
Recent research in cross-domain image retrieval has focused on addressing two
challenging issues: handling domain variations in the data and dealing with the lack of …
challenging issues: handling domain variations in the data and dealing with the lack of …