AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Cross-Modal Knowledge Transfer without Task-Relevant Source Data

Sk Miraj Ahmed, Suhas Lohit, Kuan-Chuan Peng, Michael J. Jones, Amit K. Roy-Chowdhury

ECCV 2022 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 18 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 modality-specific losses (L_d and L_TI) to SOCKET over SHOTSHOT · SUN RGB-D single source, Kinect v1 targetaccuracy (%): 11.7 -> 18.4Improved
add modality-specific losses to DECISION for two sourcesDECISION · SUN RGB-D two sources, Kinect v2 targetaccuracy (%): 26.7 -> 31.4Improved
use SOCKET instead of SHOT on RGB to NIRSHOT · RGB-NIR Scene RGB to NIRaccuracy (%): 86.7 -> 90.2Improved
use SOCKET instead of SHOT on NIR to RGBSHOT · RGB-NIR Scene NIR to RGBaccuracy (%): 92.2 -> 92.7Improved
use TI data from a different dataset (SUN RGB-D) rather than DIMLSOCKET · DIML RGB+D RGB to depthaccuracy (%): 46.1 -> 53.2Improved
add discrepancy loss L_d to L_ma (ablation)SOCKET · SUN RGB-D (a) single source RGB to Kinect v2 depthaccuracy (%): 30.0 -> 31.6Improved
add TI-data loss L_TI to L_ma (ablation)SOCKET · SUN RGB-D (a) single source RGB to Kinect v2 depthaccuracy (%): 30.0 -> 34.9Improved
add both L_d and L_TI to L_ma (ablation)SOCKET · SUN RGB-D (a) single source RGB to Kinect v2 depthaccuracy (%): 30.0 -> 36.3Improved
add both L_d and L_TI to L_ma (ablation)SOCKET · SUN RGB-D (b) two sources kv1+xtion to Kinect v1 depthaccuracy (%): 11.7 -> 23.9Improved
increase TI images per class from 0 to 60 (ablation)SOCKET · SUN RGB-D Kinect v1 RGB to depth, six TI classesaccuracy (%): 16.7 -> 25.0Improved
raise regularization lambda from 0 to 0.5 (ablation)SOCKET · Kinect v1 RGB to Kinect v1 depthaccuracy (%): 16.1 -> 23.4Improved
raise regularization lambda from 0.5 to 1.0 (ablation)SOCKET · Kinect v2 RGB to Kinect v1 depthaccuracy (%): 36.7 -> 16.3Hurt

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