AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning

• URL: http://arxiv.org/abs/2605.28809v1
• Date: Wed, 27 May 2026 17:58:16 GMT
• Title: AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
• Abstract summary: Class-Incremental Learning (CIL) is important in building real-world learning systems.<n>We propose AREA for attribute extraction and aggregation in CLIP-based CIL.<n> Experiments show that AREA consistently outperforms SOTA methods.
• Score: 17.715024506546957
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLIP-based CIL, the model performs classification by comparing similarity between visual and textual embeddings obtained from template prompts, e.g., ``a photo of a [CLASS]''. This seemingly monolithic matching process can be decomposed into two conceptually distinct stages: attribute extraction and attribute aggregation. For example, a model may recognize cat using attributes such as fur texture and whiskers. When learning a new class like car, the model must extract additional attributes like wheels and adjust how they are aggregated in the shared representation space. However, since only data from the current task is available, incremental updates can bias both attribute extraction and aggregation toward new classes, leading to catastrophic forgetting. Therefore, we propose AREA for attribute extraction and aggregation in CLIP-based CIL. To stabilize extraction, we anchor class-level visual and textual attributes on the hyperspherical embedding space via principal geodesic analysis. To stabilize aggregation, we learn lightweight task-specific experts with scoring and residual refinement, regularized by a variational information bottleneck objective. During inference, we perform routing over task attribute manifolds via optimal transport for more concise prediction. Experiments show that AREA consistently outperforms SOTA methods. Code is available at https://github.com/LAMDA-CL/ICML2026-AREA.

Related papers

• Learning Unified Distance Metric for Heterogeneous Attribute Data Clustering [60.05209293008078]
  Heterogeneous Attribute Reconstruction and Representation (HARR) learning paradigm for cluster analysis.<n>HarR is parameter-free, convergence-guaranteed, and can more effectively self-adapt to different sought number of clusters $k$.
  arXiv  Detail & Related papers  (2026-03-03T08:13:16Z)
• Hierarchical Representation Matching for CLIP-based Class-Incremental Learning [80.2317078787969]
  Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams.<n>Recent advances in pre-trained vision-language models (e.g., CLIP) provide a powerful foundation for this task.<n>We introduce HiErarchical Representation MAtchiNg (HERMAN) for CLIP-based CIL.
  arXiv  Detail & Related papers  (2025-09-26T17:59:51Z)
• CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection [30.286598189230396]
  Class-Agnostic Shared Attribute Base encourages the model to learn category-agnostic attributes shared across incremental classes.<n>For subsequent tasks, the retained attributes are frozen, and new attributes are selected from the remaining candidates.<n>Experiments on the COCO dataset demonstrate the state-of-the-art performance of our method.
  arXiv  Detail & Related papers  (2024-10-08T08:36:12Z)
• Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss [20.10399273585125]
  Long-tailed (LT) classification is an unavoidable and challenging problem in the real world. We propose a novel long-tailed classification framework, aiming to build a multi-granularity classification model by means of invariant feature learning. Our approach achieves state-of-the-art performance on both existing benchmarks ImageNet-GLT and MSCOCO-GLT.
  arXiv  Detail & Related papers  (2023-10-12T10:51:23Z)
• Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning [52.506434446439776]
  Compositional zero-shot learning (CZSL) aims to recognize compositions with prior knowledge of known primitives (attribute and object) We propose a simple and scalable framework called Composition Transformer (CoT) to address these issues. Our method achieves SoTA performance on several benchmarks, including MIT-States, C-GQA, and VAW-CZSL.
  arXiv  Detail & Related papers  (2023-08-08T03:24:21Z)
• AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning [53.32576252950481]
  Continual learning aims to enable a model to incrementally learn knowledge from sequentially arrived data. In this paper, we propose a non-incremental learner, named AttriCLIP, to incrementally extract knowledge of new classes or tasks.
  arXiv  Detail & Related papers  (2023-05-19T07:39:17Z)
• Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation [21.72622601533585]
  We propose a novel framework to boost Zero-Shot Learning (ZSL) by synthesizing diverse features. This method uses augmented semantic attributes to train the generative model, so as to simulate the real distribution of visual features. We evaluate the proposed model on four benchmark datasets, observing significant performance improvement against the state-of-the-art.
  arXiv  Detail & Related papers  (2021-12-23T14:32:51Z)
• Attribute Propagation Network for Graph Zero-shot Learning [57.68486382473194]
  We introduce the attribute propagation network (APNet), which is composed of 1) a graph propagation model generating attribute vector for each class and 2) a parameterized nearest neighbor (NN) classifier. APNet achieves either compelling performance or new state-of-the-art results in experiments with two zero-shot learning settings and five benchmark datasets.
  arXiv  Detail & Related papers  (2020-09-24T16:53:40Z)
• Learning Class Regularized Features for Action Recognition [68.90994813947405]
  We introduce a novel method named Class Regularization that performs class-based regularization of layer activations. We show that using Class Regularization blocks in state-of-the-art CNN architectures for action recognition leads to systematic improvement gains of 1.8%, 1.2% and 1.4% on the Kinetics, UCF-101 and HMDB-51 datasets, respectively.
  arXiv  Detail & Related papers  (2020-02-07T07:27:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.