AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Image Compression for Machine and Human Vision With Spatial-Frequency Adaptation

Han Li, Shaohui Li, Shuangrui Ding, Wenrui Dai, Maida Cao, Chenglin Li, Junni Zou, Hongkai Xiong

ECCV 2024 · Architectures and efficiency › Pruning and efficient tuning · approach: Efficient ViT adaptation · 36 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
add the frequency modulation adapter alongside the spatial modulation adapter (ablation)SFMA on mbt2018-mean · ImageNet-val classificationBD-acc: 16.30 -> 18.71Improved
add the spatial modulation adapter alongside the frequency modulation adapter (ablation)SFMA on mbt2018-mean · ImageNet-val classificationBD-acc: 17.29 -> 18.71Improved
use FMA in parallel with SMA instead of a second parallel SMA (ablation)SFMA on mbt2018-mean · ImageNet-val classificationBD-acc: 17.59 -> 18.71Improved
parallel rather than sequential arrangement of FMA and SMA (ablation)SFMA on mbt2018-mean · Classification, detection, segmentationBD-rate/BD-acc: classification BD-acc 18.67 and 18.50 (sequential) vs 18.71Mixed
place SFMA at shallow stage 1 rather than stage 3 (ablation)SFMA on mbt2018-mean · ImageNet-val classificationBD-rate: -64.76% -> -69.54%Improved
plug SFMA into all three stages rather than one (ablation)SFMA on mbt2018-mean · ImageNet-val classificationBD-rate: -69.54% -> -82.00%Improved
add SFMA to the decoder as well as the encoder (ablation)SFMA on mbt2018-mean · ImageNet-val classificationBD-acc: 13.28 -> 18.71Improved
add SFMA to the encoder as well as the decoder (ablation)SFMA on mbt2018-mean · ImageNet-val classificationBD-acc: 12.40 -> 18.71Improved
increase middle dimension from 64 to 128 (ablation)SFMA on mbt2018-mean · Detection COCO2017-valBD-mAP: 3.84 -> 4.11 (params 0.28M -> 0.62M)Improved
increase middle dimension from 1 to 64 (ablation)SFMA on mbt2018-mean · ImageNet-val classificationBD-acc: 12.58 -> 18.71Improved
use SFMA adapters instead of full fine-tuningLu2022-TIC base codec · Classification, detection, segmentationBD-acc / BD-mAP: classification 17.68 -> 16.90; detection 4.51 -> 3.55 with 0.28M vs 7.51M paramsMixed
use SFMA instead of channel selectionLu2022-TIC base codec · Detection COCO2017-valBD-mAP: -0.55 -> 3.55Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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