349 citations · 463 across the 11 of their papers we have counts for
15 papers
Revisiting Training-free NAS Metrics: An Efficient Training-based Method
Taojiannan Yang, Linjie Yang, Xiaojie Jin +1
Recent neural architecture search (NAS) works proposed training-free metrics to rank networks which largely reduced the search cost in NAS. In this paper, we revisit these training…
Robust High-Resolution Video Matting with Temporal Guidance
Shanchuan Lin, Linjie Yang, Imran Saleemi +1
We introduce a robust, real-time, high-resolution human video matting method that achieves new state-of-the-art performance. Our method is much lighter than previous approaches and…
HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
Mingyu Ding, Xiaochen Lian, Linjie Yang +4
High-resolution representations (HR) are essential for dense prediction tasks such as segmentation, detection, and pose estimation. Learning HR representations is typically ignored…
Is In-Domain Data Really Needed? A Pilot Study on Cross-Domain Calibration for Network Quantization
Haichao Yu, Linjie Yang, Humphrey Shi
Post-training quantization methods use a set of calibration data to compute quantization ranges for network parameters and activations. The calibration data usually comes from the…
DeepViT: Towards Deeper Vision Transformer
Daquan Zhou, Bingyi Kang, Xiaojie Jin +5
Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be…
Progressive Temporal Feature Alignment Network for Video Inpainting
Xueyan Zou, Linjie Yang, Ding Liu +1
Video inpainting aims to fill spatio-temporal "corrupted" regions with plausible content. To achieve this goal, it is necessary to find correspondences from neighbouring frames to…