Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning

• URL: http://arxiv.org/abs/2605.16374v1
• Date: Sun, 10 May 2026 20:07:10 GMT
• Title: Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
• Abstract summary: We propose a framework that decomposes forgetting into apparent concept deletion, recoverability, and decodability.<n>We show that a large portion of seemingly lost concept-level information can often be recovered under linearity assumption.<n>Overall, our findings suggest that a significant part of concept-level forgetting can be attributed to changes in the representational accessibility.
• Score: 12.190665911412466
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly performance-driven, with limited insight into what forgetting actually corresponds to within the vision model's representation space. Prior work has primarily analyzed forgetting through task-level performance or coarse measures of representational drift, without disentangling output-level accessibility from changes in finer-grained internal structure. To this end, we propose a diagnostic framework that leverages Sparse Autoencoders (SAEs) to define a task-anchored latent feature space, enabling analysis of how task-specific information evolves at a finer granularity, where individual SAE latents are treated as concept proxies for recurring and relatively disentangled visual patterns in the model's internal computations. Within this framework, we decompose forgetting into apparent concept deletion, recoverability, and decodability. We show that a large portion of seemingly lost concept-level information can often be recovered under linearity assumption, with concept decodability degrading as more tasks are introduced. Overall, our findings suggest that a significant part of concept-level forgetting can be attributed to changes in the representational accessibility rather than complete information erasure.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Context-Aware Interpretable Representations for Retrieval and Graph Convolutional Network Classification [3.5232028627328895]
  We propose a novel unsupervised framework that integrates Manifold Learning strategies with Rank-based Interpretable Graph Embeddings.<n>Our approach effectively bridges these gaps by first characterizing the contextual information of the dataset through manifold analysis and subsequently generating sparse, self-explainable embeddings.
  arXiv  Detail & Related papers  (2026-08-29T02:29:59Z)
• Multi-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework [0.0]
  We introduce a new visual feature representation that encodes shape structure across multiple scales.<n>We further improve the learning dynamics and the read-out used to predict from the learned model.<n>The study targets two-dimensional shape, with class-incremental MNIST as a controlled, interpretable benchmark.
  arXiv  Detail & Related papers  (2026-07-28T10:17:54Z)
• Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning [0.0]
  Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning.<n>In this work, we investigate an alternative perspective: that forgetting may arise not from complete destruction of task representations but from a loss of accessibility to preserved information.
  arXiv  Detail & Related papers  (2026-06-04T11:25:33Z)
• Large Vision-Language Models Get Lost in Attention [51.851592109135716]
  We propose a unified framework grounded in information theory and geometry to quantify the geometric and entropic nature of residual updates.<n>Applying this unified framework reveals a fundamental functional decoupling: Attention acts as a subspace-language operator focused on reconfiguration, whereas FFNs serve as subspace-language operators driving semantic innovation.
  arXiv  Detail & Related papers  (2026-05-07T04:45:52Z)
• Understanding Degradation with Vision Language Model [56.09241449206817]
  Understanding visual degradations is a critical yet challenging problem in computer vision.<n>We introduce DU-VLM, a multimodal chain-of-thought model trained with supervised fine-tuning and reinforcement learning.<n>We also introduce textbfDU-110k, a large-scale dataset comprising 110,000 clean-degraded pairs with grounded physical annotations.
  arXiv  Detail & Related papers  (2026-02-04T13:51:15Z)
• Provenance Networks: End-to-End Exemplar-Based Explainability [0.0]
  We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability.<n>Provenance networks learn to link each prediction directly to its supporting training examples as part of the model's normal operation.<n>It addresses critical challenges in modern deep learning, including model opaqueness, hallucination, and the assignment of credit to data contributors.
  arXiv  Detail & Related papers  (2025-10-03T01:48:38Z)
• Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models [13.768090541138571]
  Vision Language Models (VLMs) excel at identifying and describing objects but often fail at spatial reasoning.<n>Our analysis reveals a key imbalance: vision token embeddings have much larger norms than text tokens.<n>Tools uncover that vision tokens and system prompts dominate attention.
  arXiv  Detail & Related papers  (2025-03-21T17:51:14Z)
• Oh-A-DINO: Understanding and Enhancing Attribute-Level Information in Self-Supervised Object-Centric Representations [9.949149600332836]
  Self-supervised vision models and slot-based representations excel at identifying edge-derived geometry but fail to preserve non-geometric surface-level cues.<n>We show that learning an auxiliary latent space over segmented patches, where VAE regularisation enforces compact, disentangled object-centric representations, recovers these missing attributes.
  arXiv  Detail & Related papers  (2025-03-12T21:57:41Z)
• Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales [54.78115855552886]
  We show how to construct over-complete invariants with a Convolutional Neural Networks (CNN)-like hierarchical architecture. With the over-completeness, discriminative features w.r.t. the task can be adaptively formed in a Neural Architecture Search (NAS)-like manner. For robust and interpretable vision tasks at larger scales, hierarchical invariant representation can be considered as an effective alternative to traditional CNN and invariants.
  arXiv  Detail & Related papers  (2024-02-23T16:50:07Z)
• Uncovering Unique Concept Vectors through Latent Space Decomposition [0.0]
  Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution estimates. We propose a novel post-hoc unsupervised method that automatically uncovers the concepts learned by deep models during training. Our experiments reveal that the majority of our concepts are readily understandable to humans, exhibit coherency, and bear relevance to the task at hand.
  arXiv  Detail & Related papers  (2023-07-13T17:21:54Z)
• Self-Supervision by Prediction for Object Discovery in Videos [62.87145010885044]
  In this paper, we use the prediction task as self-supervision and build a novel object-centric model for image sequence representation. Our framework can be trained without the help of any manual annotation or pretrained network. Initial experiments confirm that the proposed pipeline is a promising step towards object-centric video prediction.
  arXiv  Detail & Related papers  (2021-03-09T19:14:33Z)
• Progressive Self-Guided Loss for Salient Object Detection [102.35488902433896]
  We present a progressive self-guided loss function to facilitate deep learning-based salient object detection in images. Our framework takes advantage of adaptively aggregated multi-scale features to locate and detect salient objects effectively.
  arXiv  Detail & Related papers  (2021-01-07T07:33:38Z)

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.