AI Paper Atlas

Research map / Detection and segmentation / CNN features

CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection

Shuang Hao, Chunlin Zhong, He Tang

ECCV 2024 · Detection and segmentation › CNN features · approach: RGB-D salient object detection · 7 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 language-driven quality assessment (LQA) to the baseline (ablation)CoLA baseline · VT5000 modality completeF_beta: .801 -> .834Improved
add Conditional Dropout (CD) to the baseline (ablation)CoLA baseline · VT5000 average over three conditionsF_beta: .774 -> .793Improved
combine LQA and CD (ablation)CoLA baseline · VT5000 averageF_beta: .792 -> .813 (over LQA alone)Improved
apply plain modality dropout instead of CD (ablation)CoLA with LQA · VT5000 modality completeF_beta: .834 -> .805Hurt
freeze the original encoder while training the copied encoder (ablation)Conditional Dropout · VT5000 modality completeF_beta: .822 -> .843Improved
copy and freeze encoder without modality dropout (ablation)Conditional Dropout · VT5000 missing RGBF_beta: .754 -> .743No clear effect
extra 60 epochs of training or only copying the encoder (ablation)CoLA · VT821 modality completeF_beta: .839 -> .806 (extra epochs)Hurt
use LQA instead of fixed quality assessors (BRISQUE, GIE, CLIP-IQA) (ablation)dual-modal fusion · VT5000F_beta: .819 (GIE) -> .834 (LQA)Improved
plug Conditional Dropout into LSNet and T-NetLSNet, T-Net · VT5000robustness under missing modalityImproved
use larger backbone (ResNet-50 to Swin-B) (ablation)CoLA · VT5000 modality completeF_beta: 0.843 -> 0.857Improved

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