AI Paper Atlas

Research map / Continual learning / Class-incremental

Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition

Yukun Zuo, Hantao Yao, Liansheng Zhuang, Changsheng Xu

TPAMI 2024 · Continual learning › Class-incremental · approach: Incremental object detection with replay · 11 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 hierarchical augmentation module (HAM) (ablation)baseline · HAD on AVE 3 phasesAIA: 74.8 -> 87.6Improved
add hierarchical logical distillation (HLD) (ablation)baseline · HAD on AVE 3 phasesAIA: 74.8 -> 80.5Improved
add hierarchical correlative distillation (HCD) (ablation)baseline · HAD on AVE 3 phasesAIA: 74.8 -> 78.2Improved
combine HLD and HCD into HDM (ablation)HLD or HCD alone · HAD on AVE 3 phasesAIA: 80.5 -> 82.2Improved
add HDM to HAM (ablation)HAM · HAD on AVE 3 phasesAIA: 87.6 -> 88.9Improved
add low-level modal augmentation (LMA) only (ablation)baseline · HAD on AVE 3 phasesAIA: 74.8 -> 86.4Improved
add high-level video augmentation (HVA) only (ablation)baseline · HAD on AVE 3 phasesAIA: 74.8 -> 87.0Improved
combine LMA and HVA (ablation)LMA or HVA alone · HAD on AVE 3 phasesAIA: 87.0 -> 87.6Improved
add video-level and distribution-level logical distillation together (ablation)SLD alone · HAD on AVE 3 phasesAIA: 80.3 -> 80.5Improved
add snippet-level and video-level correlative distillation together (ablation)VCD alone · HAD on AVE 3 phasesAIA: 77.9 -> 78.2Improved
add audio to visual modality (HAD vs HAD-V) (ablation)HAD · AVK-400 fully supervisedaccuracy: 76.1 -> 84.8Improved
increase Gaussian augmentation lambda from 0 to 0.05 (ablation)HAD · HAD on AVE 3 phasesAIA: 88.2 -> 88.9Improved

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