AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Image Coding for Machines with Omnipotent Feature Learning

Ruoyu Feng, Xin Jin, Zongyu Guo, Runsen Feng, Yixin Gao, Tianyu He, Zhizheng Zhang, Simeng Sun, Zhibo Chen

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 63 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 Information Filtering module with entropy constraint (ablation)Omni-ICM · PASCAL VOC object detectionrate-accuracyImproved
add feature-level distortion loss to feature compression (ablation)Omni-ICM · PASCAL VOC object detectionrate-accuracyImproved
compress omnipotent features instead of task-specific features or reconstructed imagesOmni-ICM vs VVC · Cityscapes semantic segmentationBD-rate: -24.6 -> -72.0Improved
compress omnipotent features instead of task-specific features or reconstructed imagesOmni-ICM vs cheng+Joint · COCO object detectionBD-rate: -3.0 -> -43.9Improved
compress omnipotent features instead of using RoI bit allocationOmni-ICM vs VVC+RoI · PASCAL VOC object detectionBD-rate: -32.9 -> -35.1Improved
use contrastive pretraining instead of supervised ImageNet pretraining for task modelsTask models · multiple taskstask performanceImproved
compress omnipotent features instead of uncompressed contrastive backboneOmni-ICM · uncompressed baselinetask performanceHurt
use Omni-ICM at highest bitrateOmni-ICM · COCO pose estimationAP: more than 2 points gapHurt

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