AI Paper Atlas

Research map / Video / Video segmentation and tracking

Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders

Alexandre Eymaël, Renaud Vandeghen, Anthony Cioppa, Silvio Giancola, Bernard Ghanem, Marc Van Droogenbroeck

ECCV 2024 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 10 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 two different crops (global-to-local) instead of the same view for both inputs (ablation)CropMAE · DAVIS-2017 (IN Subset)J&F_m: 36.6 -> 60.4Improved
global-to-local crops instead of local-to-global (ablation)CropMAE · DAVIS-2017 (IN Subset)J&F_m: 55.9 -> 60.4Improved
global-to-local crops instead of independent random crops (ablation)CropMAE · DAVIS-2017 (IN Subset)J&F_m: 60.0 -> 60.4No clear effect
raise masking ratio from 0.75 to 0.985 (ablation)CropMAE · DAVIS-2017 (IN Subset)J&F_m: 45.3 -> 60.4Improved
raise masking ratio from 0.985 to 0.99 (one visible patch) (ablation)CropMAE · DAVIS-2017 (IN Subset)J&F_m: 60.4 -> 58.6Hurt
deeper decoder (8 blocks vs 4) (ablation)CropMAE · DAVIS-2017 (IN Subset)J&F_m: 60.4 -> 57.0Hurt
add color jitter augmentation (ablation)CropMAE · DAVIS-2017 (IN Subset)J&F_m: 60.3 -> 56.2Hurt
add random horizontal flip (ablation)CropMAE · DAVIS-2017 (IN Subset)J&F_m: 60.3 -> 60.4No clear effect
pre-train on ImageNet subset images instead of K400 video framesCropMAE · DAVIS-2017J&F_m: 58.6 -> 60.4Improved
CropMAE image-based pretext vs SiamMAE video frames, 400 epochsCropMAE · JHMDBPCK@0.1: 46.1 -> 43.6Hurt
CropMAE on images vs SiamMAE on K400, training timeCropMAE · pre-training speedupspeedup: x1.0 -> x23.8Improved

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