Exemplar-Free

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

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

No dataset record in the archive lists this task.

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 39 papers with code (72 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.

• 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.
• 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.
• 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.
• FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning
  23 Nov 2022 2 repositories listed
  Actual features of new classes and pseudo-features of past classes are fed into a linear classifier which is trained incrementally to discriminate between all classes.
• S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning
  26 Jul 2022 2 repositories listed Syntology ran 3 of 8 samples · 5 unverified
  In this paper, we propose one simple paradigm (named as S-Prompting) and two concrete approaches to highly reduce the forgetting degree in one of the most typical continual learning scenarios, i.
• Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
  5 Jul 2025 1 repository listed
  We show that STP attacks are able to strongly disrupt the whole continual training process: decreasing both the stability (its performance on past tasks) and plasticity (capacity to adapt to new tasks) of the algorithm.
• Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification
  21 Apr 2025 1 repository listed
  To solve these issues, we propose a novel Distribution-aware Forgetting Compensation (DAFC) model that explores cross-domain shared representation learning and domain-specific distribution integration without using old…
• Boosting the Class-Incremental Learning in 3D Point Clouds via Zero-Collection-Cost Basic Shape Pre-Training
  11 Apr 2025 1 repository listed
  Based on this, we propose a framework embedded with 3D geometry knowledge for incremental learning in point clouds, compatible with exemplar-free (-based) settings.
• LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning
  23 Mar 2025 1 repository listed
  However, they rely on static features or outdated statistics stored from old tasks, which prevents them from capturing the dynamic evolution of the feature space in CL, leading to performance degradation over time.
• EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning
  13 Mar 2025 1 repository listed
  In this paper, we consider the challenging Cold Start scenario in which insufficient data is available in the first task to learn a high-quality backbone.
• Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning
  7 Mar 2025 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Specifically, the embeddings of old tasks shift in the embedding space after learning new tasks, and the classifier becomes biased towards new tasks due to training solely with new data, hindering the balance between…
• Incremental Learning with Repetition via Pseudo-Feature Projection
  27 Feb 2025 1 repository listed
  Incremental Learning scenarios do not always represent real-world inference use-cases, which tend to have less strict task boundaries, and exhibit repetition of common classes and concepts in their continual data stream.
• ConSense: Continually Sensing Human Activity with WiFi via Growing and Picking
  18 Feb 2025 1 repository listed
  The framework leverages the transformer architecture and involves dynamic model expansion and selective retraining to preserve previously learned knowledge while integrating new information.
• CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning
  13 Jan 2025 1 repository listed
  While separate adapters are proven to mitigate forgetting and fit unique requirements, naively applying them hinders the intrinsic connection between spatial and temporal information increments, affecting the efficiency…
• Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning
  24 Dec 2024 1 repository listed
  We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and scalability.
• DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification
  12 Dec 2024 1 repository listed Syntology ran 0 of 3 samples · 3 unverified · 3 pointer-only (licence)
  To overcome these challenges, we propose a novel paradigm that models and rehearses the distribution of the old domains to enhance knowledge consolidation during the new data learning, possessing a strong…
• Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
  26 Sep 2024 1 repository listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  In this work, we propose AdaGauss -- a novel method that adapts covariance matrices from task to task and mitigates the task-recency bias owing to the additional anti-collapse loss function.
• Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning
  11 Sep 2024 1 repository listed Syntology ran 7 of 14 samples · 7 unverified
  In this paper, we harness the potent representation capabilities of pre-trained models and introduce AdaPtive Adapter RouTing (APART) as an exemplar-free solution for LTCIL.
• Exemplar-free Continual Representation Learning via Learnable Drift Compensation
  11 Jul 2024 1 repository listed Syntology ran 8 of 16 samples · 8 unverified · 16 pointer-only (licence)
  Prototype-based approaches, when continually updated, face the critical issue of semantic drift due to which the old class prototypes drift to different positions in the new feature space.
• TACLE: Task and Class-aware Exemplar-free Semi-supervised Class Incremental Learning
  10 Jul 2024 1 repository listed
  We propose a novel TACLE (TAsk and CLass-awarE) framework to address the relatively unexplored and challenging problem of exemplar-free semi-supervised class incremental learning.
• Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning
  29 May 2024 1 repository listed Syntology ran 4 of 9 samples · 5 unverified
  We then estimate the drift in the embedding space from the old to the new model using the perturbed images and compensate the prototypes accordingly.
• Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Task
  28 May 2024 1 repository listed
  One of these scenarios can be formulated as an online continual learning (OCL) problem.
• DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning
  26 Mar 2024 1 repository listed Syntology ran 3 of 5 samples · 2 unverified
  The compensation stream is governed by a Dual-Activation Compensation (DAC) module.
• Every Shot Counts: Using Exemplars for Repetition Counting in Videos
  26 Mar 2024 1 repository listed
  We propose an exemplar-based approach that discovers visual correspondence of video exemplars across repetitions within target videos.
• F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning
  23 Mar 2024 1 repository listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  In this paper, we propose an exemplar-free approach--Forward-only Online Analytic Learning (F-OAL).
• LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery
  26 Feb 2024 1 repository listed
  We further design an adaptive weight assignment approach that balances the generalization ability of the LLM and the domain expertise of the old CL model.
• Random Representations Outperform Online Continually Learned Representations
  13 Feb 2024 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  However, little attention has been paid to the efficacy of continually learned representations, as representations are learned alongside classifiers throughout the learning process.
• Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning
  6 Feb 2024 1 repository listed Syntology ran 3 of 13 samples · 10 unverified
  Experimental results on CIFAR-100, Tiny-ImageNet, ImageNet-Subset and ImageNet-1K demonstrate that Elastic Feature Consolidation is better able to learn new tasks by maintaining model plasticity and significantly…
• Divide and not forget: Ensemble of selectively trained experts in Continual Learning
  18 Jan 2024 1 repository listed Syntology ran 9 of 10 samples · 1 unverified
  Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know.
• Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning
  12 Sep 2023 1 repository listed Syntology ran 5 of 5 samples · 0 unverified · 5 pointer-only (licence)
  In the second phase, we combine this new knowledge with the previous network in an adaptation-retrospection phase to avoid forgetting and initialize a new expert with the knowledge of the old network.

Syntology lines on 15 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.