Rainforest Wang

Reducing spatial redundancy in video recognition. SOTA computational efficiency.

blackfeather-wang

Accelerating T2t-ViT by 1.6-3.6x.

blackfeather-wang

blackfeather-wang

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.

blackfeather-wang

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

blackfeather-wang

An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.

blackfeather-wang