A Research, Taco Cohen, Davide Abati, Amirhossein Habibian, Babak Ehteshami, Bejnordi Qualcomm
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose Skip-Convolutions to leverage the large amount of redundancies in video streams and save computations. Each video is represented as a series of changes across frames and network activations, denoted as residuals. We reformulate standard convolution to be efficiently computed on residual frames: each layer is coupled with a binary gate deciding whether a residual is important to the model prediction, e.g. foreground regions, or it can be safely skipped, e.g. background regions. These gates can either be implemented as an efficient network trained jointly with convolution kernels, or can simply skip the residuals based on their magnitude. Gating functions can also incorporate block-wise sparsity structures, as required for efficient implementation on hardware platforms. By replacing all convolutions with Skip-Convolutions in two state-ofthe-art architectures, namely EfficientDet and HRNet, we reduce their computational cost consistently by a factor of 3 ∼ 4× for two different tasks, without any accuracy drop. Extensive comparisons with existing model compression, as well as image and video efficiency methods demonstrate that Skip-Convolutions set a new state-of-the-art by effectively exploiting the temporal redundancies in videos.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.11487")
get_code_for_paper("2104.11487")
have("2104.11487")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.11487.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.11487)
Connect an agent — have() is free.