Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Designing Concise ConvNets with Columnar Stages
Ashish Kumar, Jaesik Park
In the era of vision Transformers, the recent success of VanillaNet shows the huge potential of simple and concise convolutional neural networks (ConvNets). Where such models mainl…
cs.CV2024
Cross Resolution Encoding-Decoding For Detection Transformers
Ashish Kumar, Jaesik Park
Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we pro…