Few-Shot Class-Incremental Learning

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 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.

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

3 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.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 55 papers with code (118 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.

• 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…
• 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.
• FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models
  28 Dec 2023 2 repositories listed
  To address the above challenges, we introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for…
• Continual Learning: Forget-free Winning Subnetworks for Video Representations
  19 Dec 2023 2 repositories listed Syntology ran 7 of 15 samples · 8 unverified
  Inspired by the Lottery Ticket Hypothesis (LTH), which highlights the existence of efficient subnetworks within larger, dense networks, a high-performing Winning Subnetwork (WSN) in terms of task performance under…
• Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants
  3 Aug 2023 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Beyond the normal case, long-tail class incremental learning and few-shot class incremental learning are also proposed to consider the data imbalance and data scarcity, respectively, which are common in real-world…
• On the Soft-Subnetwork for Few-shot Class Incremental Learning
  15 Sep 2022 2 repositories listed Syntology ran 7 of 10 samples · 3 unverified · 2 pointer-only (licence)
  Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which hypothesizes that there exist smooth (non-binary) subnetworks within a dense network that achieve the competitive performance of the dense network, we…
• Constrained Few-shot Class-incremental Learning
  30 Mar 2022 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified
  Moreover, it is imperative that such learning must respect certain memory and computational constraints such as (i) training samples are limited to only a few per class, (ii) the computational cost of learning a novel…
• Adaptive Decision Boundary for Few-Shot Class-Incremental Learning
  15 Apr 2025 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  However, current strategies primarily focus on preventing catastrophic forgetting, considering only the relationship between novel and base classes, without paying attention to the specific decision spaces of each class.
• Enhancing Few-Shot Class-Incremental Learning via Training-Free Bi-Level Modality Calibration
  1 Jan 2025 1 repository listed
  Few-shot Class-Incremental Learning (FSCIL) challenges models to adapt to new classes with limited samples, presenting greater difficulties than traditional classincremental learning.
• Class Balance Matters to Active Class-Incremental Learning
  9 Dec 2024 1 repository listed
  Then for each cluster, we employ greedy selection strategy to ensure that the Gaussian distribution of the sampled features closely matches the Gaussian distribution of all unlabeled features within the cluster.
• An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
  11 Nov 2024 1 repository listed
  Knowledge is then distilled back into the GNN through a Graph Knowledge Distillation Module, preserving the model's memory.
• Covariance-based Space Regularization for Few-shot Class Incremental Learning
  2 Nov 2024 1 repository listed
  In this paper, we aim to mitigate these issues by directly constraining the span of each class distribution from a covariance perspective.
• Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor
  11 Oct 2024 1 repository listed
  This paper introduces a new method to tackle the Few-Shot Continual Incremental Learning (FSCIL) problem in 3D point cloud environments.
• CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning
  8 Oct 2024 1 repository listed
  Building upon the recent efforts for enhancing transferability, such as promoting the spread of features, we find that trying to secure the spread of features within a more confined feature space enables the learned…
• Rethinking Few-shot Class-incremental Learning: Learning from Yourself
  10 Jul 2024 1 repository listed
  In this work, as a complement to existing metrics, we offer a new metric called generalized average accuracy (gAcc) which is designed to provide an extra equitable evaluation by incorporating different perspectives of…
• Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
  8 Jul 2024 1 repository listed Syntology ran 2 of 8 samples · 6 unverified · 8 pointer-only (licence)
  The dual design enables the model to maintain the robust features of base classes, while adaptively learning distinctive feature shifts for novel classes.
• Compositional Few-Shot Class-Incremental Learning
  27 May 2024 1 repository listed Syntology ran 9 of 15 samples · 6 unverified
  Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data.
• Few-shot Tuning of Foundation Models for Class-incremental Learning
  26 May 2024 1 repository listed Syntology ran 6 of 10 samples · 4 unverified
  For the first time, we explore few-shot tuning of vision foundation models for class-incremental learning.
• Few-Shot Class Incremental Learning via Robust Transformer Approach
  8 May 2024 1 repository listed
  This problem remains an open problem because all recent works are built upon the convolutional neural networks performing sub-optimally compared to the transformer approaches.
• Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
  9 Apr 2024 1 repository listed Syntology ran 6 of 15 samples · 9 unverified
  FSCIL methods start with a many-shot first task to learn a very good feature extractor and then move to the few-shot setting from the second task onwards.
• Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners
  2 Apr 2024 1 repository listed Syntology ran 12 of 14 samples · 2 unverified
  In this paper, we argue that large models such as vision and language transformers pre-trained on large datasets can be excellent few-shot incremental learners.
• OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning
  27 Mar 2024 1 repository listed Syntology ran 6 of 8 samples · 2 unverified · 8 pointer-only (licence)
  To address these challenges, we propose the OrCo framework built on two core principles: features' orthogonality in the representation space, and contrastive learning.
• NTK-Guided Few-Shot Class Incremental Learning
  19 Mar 2024 1 repository listed
  Through the combined effects of these measures, our network acquires robust NTK properties, ensuring optimal convergence and stability of the NTK matrix and minimizing the NTK-related generalization loss, significantly…
• Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt
  14 Mar 2024 1 repository listed
  Few-Shot Class-Incremental Learning (FSCIL) models aim to incrementally learn new classes with scarce samples while preserving knowledge of old ones.
• 12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning
  12 Mar 2024 1 repository listed
  In this work, we introduce Online Few-Shot Class-Incremental Learning (O-FSCIL), based on a lightweight model consisting of a pretrained and metalearned feature extractor and an expandable explicit memory storing the…
• PL-FSCIL: Harnessing the Power of Prompts for Few-Shot Class-Incremental Learning
  26 Jan 2024 1 repository listed
  In this paper, we propose a novel approach called Prompt Learning for FSCIL (PL-FSCIL), which harnesses the power of prompts in conjunction with a pre-trained Vision Transformer (ViT) model to address the challenges of…
• Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning
  3 Jan 2024 1 repository listed
  When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt, thus enabling the model to learn new knowledge…
• Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
  8 Dec 2023 1 repository listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  In this Few-Shot Class-Incremental Learning (FSCIL) scenario, existing methods either introduce extra learnable components or rely on a frozen feature extractor to mitigate catastrophic forgetting and overfitting…
• Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning
  31 Oct 2023 1 repository listed
  Moreover, we design a multi-stage strategy for training S2C model, which mitigates the training challenges posed by limited data in the incremental process.
• CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics
  31 Jul 2023 1 repository listed
  For most real-world applications, robots need to adapt and learn continually with limited data in their environments.

Syntology lines on 12 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.