AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Ultrafast Video Attention Prediction with Coupled Knowledge Distillation

Kui Fu, Peipei Shi, Yafei Song, Shiming Ge, Xiangju Lu, Jia Li

AAAI 2020 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
reduce input resolution from 256x256 to 64x64 (ablation)UVA-Net (DVA teacher) · AVS1KNSS: 1.447 -> 1.981Improved
reduce input resolution further from 64x64 to 32x32 (ablation)UVA-Net (DVA teacher) · AVS1KNSS: 1.981 -> 1.905Hurt
use DVA instead of SalNet as spatial teacher (ablation)UVA-Net 64x64 · AVS1KNSS: 1.955 -> 1.981Improved
add coupled knowledge distillation (MobileNetV2 blocks) (ablation)UVA-Net MB · AVS1KNSS: 1.906 -> 1.943Improved
add coupled knowledge distillation (CA-Res blocks) (ablation)UVA-Net CA-Res · AVS1KNSS: 1.921 -> 1.981Improved
replace MobileNetV2 block with CA-Res channel attention block (with distillation) (ablation)UVA-Net · AVS1KNSS: 1.943 -> 1.981Improved
replace SE block with CA-Res channel attention (avg+max pooling) (ablation)UVA-Net with distillation · AVS1KNSS: 1.943 -> 1.981Improved
add spatiotemporal joint optimization fusing temporal branch (vs spatial branch alone) (ablation)UVA-Net CA-Res+dis · AVS1KNSS: 1.864 -> 1.981Improved
add spatiotemporal joint optimization fusing spatial branch (vs temporal branch alone) (ablation)UVA-Net CA-Res+dis · AVS1KNSS: 1.783 -> 1.981Improved
distill from DVA into 64x64 student vs using DVA directlyUVA-DVA-64 vs DVA · AVS1KNSS: 2.044 -> 1.981Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy