AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation

Chang Liu, Giulia Rizzoli, Pietro Zanuttigh, Fu Li, Yi Niu

ECCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: CAM refinement and prototypes · 4 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 Fourier-amplitude domain filtering of web images (ablation)WILSON with web data · PASCAL-VOC 10-10 overlappedmIoU (all): 62.1 -> 63.1Improved
add caption labeling for multi-label image-level supervision (ablation)WILSON with web data · PASCAL-VOC 10-10 overlappedmIoU (all): 62.1 -> 63.6Improved
combine domain filtering and caption labeling (ablation)WILSON with web data · PASCAL-VOC 10-10 overlappedmIoU (all): 62.1 -> 65.0Improved
query rehearsal images by caption instead of class name (ablation)web rehearsal · PASCAL-VOC 10-10 overlappedmIoU (all): 63.6 -> 64.9Improved
add caption-based filtering of rehearsal images (ablation)web rehearsal · PASCAL-VOC 10-10 overlappedmIoU (all): 63.6 -> 63.5No clear effect
combine caption query and caption filtering (ablation)web rehearsal · PASCAL-VOC 15-5 overlappedmIoU (all): 69.8 -> 73.4Improved
Fourier amplitude discriminator instead of pixel-domain discriminator (ablation)web image selection · PASCAL-VOC 10-10 overlappedmIoU (all): 61.9 -> 63.1Improved
use 500 instead of 100 web images for rehearsal or new-class training (ablation)web-learning pipeline · PASCAL-VOC 10-10 overlappedmIoU (all): 65.7 (M=100) vs 65.3 (M=500)Mixed
replace OpenFlamingo with BLIP captioner (ablation)Ours · PASCAL-VOC 10-10 and 15-5 overlappedmIoU (all): 65.7 -> 65.9 (10-10); 73.3 -> 73.0 (15-5)No clear effect
vary caption-filter threshold T from 0.5 to 0.7 (ablation)caption filtering · PASCAL-VOC 10-10 and 15-5 overlappedmIoU (all): T=0.6 gives 65.7 and 73.3No clear effect
use web rehearsal data for multi-step single-class incremental learningWILSON · PASCAL-VOC 10-1 overlappedmIoU (all): 0.1 -> 54.4Improved

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