5 papers
Le-DETR: Revisiting Real-Time Detection Transformer with Efficient Encoder Design
Jiannan Huang, Aditya Kane, Fengzhe Zhou +2
Real-time object detection is crucial for real-world applications as it requires high accuracy with low latency. While Detection Transformers (DETR) have demonstrated significant p…
Beyond Realism: Learning the Art of Expressive Composition with StickerNet
Haoming Lu, David Kocharian, Humphrey Shi
As a widely used operation in image editing workflows, image composition has traditionally been studied with a focus on achieving visual realism and semantic plausibility. However,…
Distilling Normalizing Flows
Steven Walton, Valeriy Klyukin, Maksim Artemev +3
Explicit density learners are becoming an increasingly popular technique for generative models because of their ability to better model probability distributions. They have advanta…
Combating Label Noise With A General Surrogate Model For Sample Selection
Chao Liang, Linchao Zhu, Humphrey Shi +1
Modern deep learning systems are data-hungry. Learning with web data is one of the feasible solutions, but will introduce label noise inevitably, which can hinder the performance o…
CompactFlowNet: Efficient Real-time Optical Flow Estimation on Mobile Devices
Andrei Znobishchev, Valerii Filev, Oleg Kudashev +2
We present CompactFlowNet, the first real-time mobile neural network for optical flow prediction, which involves determining the displacement of each pixel in an initial frame rela…