AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval

Giorgos Kordopatis-Zilos, Christos Tzelepis, Symeon Papadopoulos, Ioannis Yiannis Kompatsiaris, Ioannis Patras

IJCV 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 41 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
use h-attention (with fully-connected layer) instead of l2-attention (ablation)fine-grained attention student · FIVR-5K ISVRmAP: 0.787 -> 0.803Improved
use the differentiable E[sgn(x)] (erf) activation instead of sgn (ablation)fine-grained binarization student · FIVR-5K ISVRmAP: 0.776 -> 0.788Improved
use E[sgn(x)] activation instead of tanh(beta x) (ablation)fine-grained binarization student · FIVR-5K DSVRmAP: 0.875 -> 0.879Improved
increase bits per region vector from 64 to 512 (ablation)fine-grained binarization student · FIVR-5K DSVRmAP: 0.845 -> 0.879Improved
distill from teacher on unlabelled data instead of supervised training on VCDB (ablation)fine-grained attention student · FIVR-5K DSVRmAP: 0.821 -> 0.873Improved
distill on DnS-100K instead of VCDB (ablation)coarse-grained student · FIVR-5K DSVRmAP: 0.510 -> 0.634Improved
increase training data from 25% to 100% of DnS-100K (ablation)coarse-grained student · FIVR-5K DSVRmAP: 0.573 -> 0.634Improved
increase training data from 25% to 100% of DnS-100K (ablation)fine-grained attention student · FIVR-5K DSVRmAP: 0.888 -> 0.893No clear effect
distill from a better teacher (S^f_A(2) instead of T) (ablation)fine-grained binarization student · FIVR-5K DSVRmAP: 0.879 -> 0.895Improved
distill from a better teacher (S^f_A(2) instead of T) (ablation)coarse-grained student · FIVR-5K DSVRmAP: 0.634 -> 0.632No clear effect
binarize region features (32 times smaller) instead of float featuresfine-grained binarization student vs teacher · FIVR-5K DSVRmAP and storage: 0.882 -> 0.879 mAP; 15124 KB -> 63 KBImproved
replace fine-grained teacher by the coarse-grained studentS^c vs T · FIVR-5K DSVRmAP and time: 0.882 -> 0.634 mAP; 10.10 -> 0.018 s per queryMixed

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