AI Paper Atlas

Research map / Continual learning / Class-incremental

Data-Free Class-Incremental Hand Gesture Recognition

Shubhra Aich, Jesus Ruiz-Santaquiteria, Zhenyu Lu, Prachi Garg, K J Joseph, Alvaro Fernandez Garcia, Vineeth N Balasubramanian, Kenrick Kin, Chengde Wan, Necati Cihan Camgoz, Shugao Ma, Fernando De la Torre

ICCV 2023 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 13 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
invert boundary-aware prototypical samples plus support vectors instead of using existing DFCIL methodsDG-STA gesture recognizer · SHREC-2017 mean Task 1-6global accuracy G (%): 56.2 -> 70.5 vs ABDImproved
apply BOAT-MI on EgoGesture3DDG-STA gesture recognizer · EgoGesture3D mean Task 1-6global accuracy G (%): 52.6 -> 61.2 vs ABDImproved
invert boundary samples instead of random samples (ablation)synthetic MLP · Synthetic Gaussian blobstotal accuracy (%): 58.6 -> 90.8Improved
sample at a small margin inside boundary instead of exactly on it (ablation)prototypical MI · SHREC-2017IFM (%): 15.1 -> 10.5Improved
sample deep inside class (delta 0.8) rather than near boundary (ablation)prototypical MI · SHREC-2017 Task 6global accuracy G (%): 53.4 -> 50.1 vs near-boundaryHurt
use features at random distances instead of margin-based sampling (ablation)prototypical MI · SHREC-2017global accuracy G (%): 69.5 -> 66.0Hurt
add prototypical boundary samples to standard SVs (ablation)BOAT-MI · SHREC-2017global accuracy G (%): 61.4 -> 70.5Improved
add SVs to prototypical samples (ablation)BOAT-MI · SHREC-2017IFM (%): 10.8 -> 8.8Improved
use data-free inversion methods versus simple feature extraction baselineDFCIL methods ABD, R-DFCIL, DeepInversion · SHREC-2017 mean Task 1-6global accuracy G (%): feature extraction 60.6 vs ABD 56.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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