Research map / Continual learning / Class-incremental
Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning
Jun-Yeong Moon, Keon-Hee Park, Jung Uk Kim, Gyeong-Moon Park
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add instance-wise logit masking to DualPrompt baseline (ablation) | DualPrompt · Si-Blurry CIFAR-100 (buffer 0) | A_Last: 56.82 -> 58.52 | Improved |
| add contrastive visual prompt tuning loss to DualPrompt baseline (ablation) | DualPrompt · Si-Blurry CIFAR-100 (buffer 0) | A_AUC: 67.07 -> 66.37 (A_AUC); 56.82 -> 58.63 (A_Last) | Mixed |
| combine logit masking and contrastive loss (ablation) | MVP · Si-Blurry CIFAR-100 (buffer 0) | A_Last: 58.52 -> 60.20 | Improved |
| add GSF loss alone (ablation) | DualPrompt · Si-Blurry CIFAR-100 (buffer 0) | A_Last: 56.82 -> 56.11 | Hurt |
| add adaptive feature scaling alone (ablation) | DualPrompt · Si-Blurry CIFAR-100 (buffer 2000) | A_Last: 80.72 -> 84.31 | Improved |
| add all four components (Mask, Cont, GSF, AFS) (ablation) | DualPrompt · Si-Blurry CIFAR-100 (buffer 0) | A_Last: 56.82 -> 62.59 | Improved |
| add replay buffer of 2,000 samples (MVP-R vs MVP) | MVP · Si-Blurry CIFAR-100 | A_Last: 62.59 -> 84.42 | Improved |
| gamma in GSF loss set to 2.0 versus 0.5 (ablation) | MVP · Si-Blurry CIFAR-100 | A_Last: 60.39 -> 62.59 | Improved |
| MVP versus DualPrompt when only disjoint classes present | MVP · Si-Blurry CIFAR-100 (disjoint ratio 0) | A_AUC: 68.85 -> 67.86 | Hurt |
| raise blurry sample ratio to 50 | MVP · Si-Blurry CIFAR-100 | A_Last: 49.93 -> 59.47 | Improved |
| Si-Blurry versus i-Blurry for MVP-R | MVP-R (2,000) · CIFAR-100 | A_Last: 84.44 vs 84.42 | No clear effect |
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.
- DualPrompt — DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning (ECCV 2022) · better on 5 of 5 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
- Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (ICLR 2022 · similarity 0.91)
- Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning (CVPR 2024 · similarity 0.87)
- Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models (NeurIPS 2024 · similarity 0.87)
- Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection (AAAI 2024 · similarity 0.87)
- Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning (NeurIPS 2024 · similarity 0.87)
- Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning (NeurIPS 2024 · similarity 0.86)
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.
