Incremental Learning

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

22 leaderboard tables shown for this task, 22 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 22 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

8 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 542 papers with code (1,371 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Overcoming catastrophic forgetting in neural networks
  2 Dec 2016 29 repositories listed Syntology ran 14 of 22 samples · 8 unverified · 4 pointer-only (licence)
  The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence.
• Learning without Forgetting
  29 Jun 2016 12 repositories listed Syntology ran 9 of 15 samples · 6 unverified · 1 pointer-only (licence)
  We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities.
• iCaRL: Incremental Classifier and Representation Learning
  23 Nov 2016 10 repositories listed Syntology ran 3 of 14 samples · 11 unverified · 3 pointer-only (licence)
  A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data.
• Three scenarios for continual learning
  15 Apr 2019 8 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning difficult for machine learning.
• Gradient Episodic Memory for Continual Learning
  26 Jun 2017 7 repositories listed
  One major obstacle towards AI is the poor ability of models to solve new problems quicker, and without forgetting previously acquired knowledge.
• End-to-End Incremental Learning
  25 Jul 2018 6 repositories listed Syntology ran 0 of 9 samples · 9 unverified
  Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with…
• Large Scale Incremental Learning
  30 May 2019 5 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  We believe this is because of the combination of two factors: (a) the data imbalance between the old and new classes, and (b) the increasing number of visually similar classes.
• RMM: Reinforced Memory Management for Class-Incremental Learning
  14 Jan 2023 4 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
  Class-Incremental Learning (CIL) [40] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free space for the next phase.
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
  10 Jul 2018 4 repositories listed Syntology ran 9 of 13 samples · 4 unverified · 12 pointer-only (licence)
  Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning…
• Cost-Effective Active Learning for Deep Image Classification
  13 Jan 2017 4 repositories listed Syntology ran 2 of 13 samples · 11 unverified · 2 pointer-only (licence)
  In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental…
• External Knowledge Injection for CLIP-Based Class-Incremental Learning
  11 Mar 2025 3 repositories listed
  In this paper, we introduce ExterNal knowledGe INjEction (ENGINE) for CLIP-based CIL.
• FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
  25 Sep 2023 3 repositories listed Syntology ran 11 of 21 samples · 10 unverified
  However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous.
• Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need
  13 Mar 2023 3 repositories listed
  In this work, we revisit CIL with PTMs and argue that the core factors in CIL are adaptivity for model updating and generalizability for knowledge transferring.
• Class-Incremental Learning: A Survey
  7 Feb 2023 3 repositories listed
  Deep models, e.
• Latent Spectral Regularization for Continual Learning
  9 Jan 2023 3 repositories listed
  While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget catastrophically whenever they face a changing training data distribution.
• A Multi-Head Model for Continual Learning via Out-of-Distribution Replay
  20 Aug 2022 3 repositories listed
  Instead of using the saved samples in memory to update the network for previous tasks/classes in the existing approach, MORE leverages the saved samples to build a task specific classifier (adding a new classification…
• Visual Memorability for Robotic Interestingness via Unsupervised Online Learning
  18 May 2020 3 repositories listed
  In this paper, we explore the problem of interesting scene prediction for mobile robots.
• Learning a Unified Classifier Incrementally via Rebalancing
  1 Jun 2019 3 repositories listed
  However, it has been observed that incremental learning is subject to a fundamental difficulty -- catastrophic forgetting, namely adapting a model to new data often results in severe performance degradation on previous…
• Incremental Learning of Object Detectors without Catastrophic Forgetting
  23 Aug 2017 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Despite their success for object detection, convolutional neural networks are ill-equipped for incremental learning, i.
• Continuous Knowledge-Preserving Decomposition for Few-Shot Continual Learning
  9 Jan 2025 2 repositories listed
  To this end, we propose Continuous Knowledge-Preserving Decomposition for FSCIL (CKPD-FSCIL), a framework that decomposes a model's weights into two parts: one that compacts existing knowledge (knowledge-sensitive…
• MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning
  12 Dec 2024 2 repositories listed Syntology ran 6 of 17 samples · 11 unverified · 12 pointer-only (licence)
  Class-Incremental Learning (CIL) requires models to continually acquire knowledge of new classes without forgetting old ones.
• AIR: Analytic Imbalance Rectifier for Continual Learning
  19 Aug 2024 2 repositories listed
  To solve this problem, we propose an analytic imbalance rectifier algorithm (AIR), a novel online exemplar-free continual learning method with an analytic (i.
• Data-Free Generative Replay for Class-Incremental Learning on Imbalanced Data
  7 Jun 2024 2 repositories listed
  One method for incremental class learning, addressing dataset imbalance, is rehearsal using previously stored data.
• GACL: Exemplar-Free Generalized Analytic Continual Learning
  23 Mar 2024 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  The GACL adopts analytic learning (a gradient-free training technique) and delivers an analytical (i.
• Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters
  18 Mar 2024 2 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
  Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset.
• A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets
  10 Mar 2024 2 repositories listed
  Few-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting.
• Incremental Sequence Labeling: A Tale of Two Shifts
  16 Feb 2024 2 repositories listed
  As for the E2O problem, we use knowledge distillation to maintain the model's discriminative ability for old entities.
• Can LLMs Learn New Concepts Incrementally without Forgetting?
  13 Feb 2024 2 repositories listed
  The concepts in Concept-1K are discrete, interpretable units of knowledge that allow for fine-grained analysis of learning and forgetting processes.
• Class incremental learning with probability dampening and cascaded gated classifier
  2 Feb 2024 2 repositories listed
  The latter is a gated incremental classifier, helping the model modify past predictions without directly interfering with them.
• Federated Class-Incremental Learning with New-Class Augmented Self-Distillation
  1 Jan 2024 2 repositories listed
  Federated Learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data.

Syntology lines on 14 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.