Rainforest Wang

ISDA-for-Deep-Networks. An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.

Dynamic-Vision-Transformer. Accelerating T2t-ViT by 1.6-3.6x.

GFNet-Pytorch. A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 1.3x on an iPhone XS Max without sacrificing accuracy.

AdaFocus. Reducing spatial redundancy in video recognition. SOTA computational efficiency.

InfoPro-Pytorch. Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better performance.

Dynamic-Vision-Transformer-MindSpore. Jinja

blackfeather-wang.github.io. HTML