AI Paper Atlas

Research map / Continual learning / Class-incremental

Language-Inspired Relation Transfer for Few-Shot Class-Incremental Learning

Yifan Zhao, Jia Li, Zeyin Song, Yonghong Tian

TPAMI 2024 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 22 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 text-vision prototypical fusion with fixed prompt to visual finetuning (ablation)LRT base (CLIP ResNet-50) · miniImageNet FSCIL (5-way 5-shot)average accuracy (%): 57.16 -> 64.98Improved
replace fixed handcrafted prompt with learnable context prompt (PT) (ablation)LRT with M_fuse · miniImageNet FSCIL (5-way 5-shot)average accuracy (%): 64.98 -> 67.01Improved
add imagined contrastive loss (ablation)LRT with PT+FT+M_fuse · miniImageNet FSCIL (5-way 5-shot)average accuracy (%): 67.01 -> 67.88Improved
add graph relation transformation module M_graph (ablation)LRT with PT+FT+M_fuse · miniImageNet FSCIL (5-way 5-shot)average accuracy (%): 67.88 -> 75.94Improved
use text prompt tuning only with fixed vision encoder instead of visual finetuning (ablation)LRT base · miniImageNet FSCIL (5-way 5-shot)average accuracy (%): 57.16 -> 52.87Hurt
fuse prototypes by simple averaging (Proto Add.) instead of learnable tau (ablation)M_graph+M_fuse · miniImageNet FSCIL (5-way 5-shot)average accuracy (%): 75.94 -> 51.25Hurt
fix tau = 1 (Static) instead of learnable (ablation)M_graph+M_fuse · miniImageNet FSCIL (5-way 5-shot)average accuracy (%): 75.94 -> 51.10Hurt
add M_fuse to M_graph only (ablation)LRT · miniImageNet FSCIL (5-way 5-shot)average accuracy (%): 72.61 -> 75.94Improved
increase incremental shots from 1 to 5 (ablation)LRT · miniImageNet FSCIL (5-way 5-shot)incremental-class accuracy (%): 17.12 -> 39.32Improved
increase incremental shots from 1 to 5 (ablation)LRT · miniImageNet FSCIL (5-way 5-shot)base-class accuracy (%): 86.40 -> 82.68Mixed
scale loss weights lambda_im or lambda_m by 0.1x or 10x (ablation)LRT · miniImageNet FSCIL (5-way 5-shot)average accuracy (%): 75.94 -> 71.89Hurt
increase prompt length from 2 to 4 (ablation)LRT · miniImageNet FSCIL (5-way 5-shot)base/incremental accuracy (%): 82.68 vs 84.28 base, 35.42 -> 39.32 incrementalMixed

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