Despite its success, the said paradigm is still constrained by several factors, such as (i) low-quality region proposals for novel classes and (ii) negligence of the inter-class correlation among different classes.
The first is scene-level swapping which exchanges point cloud sectors of two LiDAR scans that are cut along the azimuth axis.
The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection.
Extensive experiments over multiple conditional image generation tasks show that our method achieves superior diverse image generation performance qualitatively and quantitatively as compared with the state-of-the-art.
First, it projects object queries into the same embedding space as encoded image features, where the matching can be accomplished efficiently with aligned semantics.
Specifically, we design GenCo, a Generative Co-training network that mitigates the discriminator over-fitting issue by introducing multiple complementary discriminators that provide diverse supervision from multiple distinctive views in training.
This paper presents a versatile image translation and manipulation framework that achieves accurate semantic and style guidance in image generation by explicitly building a correspondence.
Generative Adversarial Networks (GANs) have become the de-facto standard in image synthesis.
In addition, we design a semantic-activation normalization scheme that injects style features of exemplars into the image translation process successfully.
With image-level attention, transformers enable to model long-range dependencies and generate diverse contents with autoregressive modeling of pixel-sequence distributions.
In addition, the synthesized defect samples demonstrate their effectiveness in training better defect inspection networks.
Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks.
Ranked #4 on Few-Shot Object Detection on MS-COCO (30-shot)