Continual Visual Learning under Evolving Semantic Concept Shift

• URL: http://arxiv.org/abs/2608.23903v1
• Date: Mon, 24 Aug 2026 23:14:46 GMT
• Title: Continual Visual Learning under Evolving Semantic Concept Shift
• Abstract summary: SemReWrite is a framework for selectively updating obsolete visual-semantic mappings while preserving knowledge that remains valid.<n>We also introduce EvoShift-Bench, spanning ImageNet, iNaturalist, CUB-200-2011, and DomainNet, with semantic transitions including class split, merge, boundary revision, insertion, partial redefinition, recurrence, and mixed semantic-appearance shift.
• Score: 1.565870461096057
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual foundation models are commonly adapted under the assumption that the appearance of incoming data may change while the semantic meaning of the prediction task remains fixed. In long-lived visual systems, however, taxonomies, policies, and concept definitions can themselves evolve, causing the same visual evidence to require a different interpretation. We study this setting as evolving semantic concept shift and introduce SemReWrite, a framework for selectively updating obsolete visual--semantic mappings while preserving knowledge that remains valid. SemReWrite represents changes between old and revised semantic specifications, combines semantic discrepancy with sparse revised supervision to localize affected visual regions, and uses an input-dependent low-rank rewriting mechanism together with structured semantic memory, preservation, and obsolete-decision suppression. We further introduce EvoShift-Bench, spanning ImageNet, iNaturalist, CUB-200-2011, and DomainNet, with semantic transitions including class split, merge, boundary revision, insertion, partial redefinition, recurrence, and mixed semantic--appearance shift. To explicitly evaluate selective semantic revision, we introduce Rewrite Accuracy (RA) and Preservation Accuracy (PA) for affected and unaffected regions, respectively, Obsolete Retention (OR) for measuring residual outdated semantic associations, and the Selective Revision Score (SRS), which jointly summarizes rewriting and preservation performance. Experiments show that SemReWrite achieves a stronger balance between learning revised semantics and retaining unaffected knowledge than prompt replacement, conventional fine-tuning, parameter-efficient adaptation, and continual-learning strategies.

Related papers

• Provenance Guided Incremental Learning Under Evolving Concept Definitions [0.0]
  This paper studies rule-induced concept shift, where the target-defining concept is revised directly.<n>We introduce a provenance-guided incremental learning framework that compiles consecutive concept definitions into a structured rule delta.<n>We also introduce RuleShift-Bench, spanning financial, demographic, cybersecurity, and graph-structured data with threshold, predicate, logical, relational, recurring, and mixed concept revisions.
  arXiv  Detail & Related papers  (2026-08-24T23:03:10Z)
• Structured-Condensed Prompt Tuning in Vision-Language Models for Fine-grained Image Recognition [38.294322671641545]
  Fine-grained image recognition is a significant challenge due to the substantial expertise and effort required for manual annotation.<n>Current methods treat class labels as isolated, discrete entities, overlooking the rich semantic relationships between them.<n>We propose Structured-Condensed Prompt Tuning ( SCPT), which enhances semantic structure modeling in prompt learning.
  arXiv  Detail & Related papers  (2026-07-07T12:09:49Z)
• Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification [60.02530716177415]
  Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data.<n> Existing exemplar-free approaches largely rely on visual-only distillation or parameter regularization.<n>We propose Prompt-Anchored vision-text Distillation (PAD), an asymmetric vision-text framework for semantic alignment and cross-domain generalization.
  arXiv  Detail & Related papers  (2026-05-06T15:23:13Z)
• SemCovNet: Towards Fair and Semantic Coverage-Aware Learning for Underrepresented Visual Concepts [11.181779608395184]
  Existing datasets exhibit Semantic Coverage Imbalance (SCI)<n>SCI occurs at the semantic level, affecting how models learn and reason about rare yet meaningful semantics.<n>We propose Semantic Coverage-Aware Network (SemCovNet), a novel model that explicitly learns to correct SCI.
  arXiv  Detail & Related papers  (2026-02-18T22:18:29Z)
• TaCo: Capturing Spatio-Temporal Semantic Consistency in Remote Sensing Change Detection [54.22717266034045]
  Ta-Co is a consistent semantic network for temporal semantic transitions.<n>We show that Ta-Co consistently achieves SOTA performance on remote sensing detection tasks.<n>This design can yield substantial gains without any additional computational overhead during inference.
  arXiv  Detail & Related papers  (2025-11-25T13:44:29Z)
• Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selection [50.68751788132789]
  This study introduces an innovative methodology named as Weighted Semantic Map with Auto-adaptive Candidate Editing Network (WSAE-Net)<n>The generation of the weighted semantic map is designed to maximize the reduction of non-semantic feature units that need to be computed.<n>The auto-adaptive candidate editing sequences are designed to determine the optimal computational order among the feature units to be processed.
  arXiv  Detail & Related papers  (2025-11-17T05:34:10Z)
• Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning [47.56496248878093]
  Continual learning aims to equip models with the ability to learn from a stream of tasks without forgetting previous knowledge.<n>We propose a unified framework that harnesses the anti-forgetting and structured nature of textual priors to guide semantic-aware knowledge transfer.
  arXiv  Detail & Related papers  (2025-08-03T04:09:00Z)
• PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings [55.55445978692678]
  PseudoNeg-MAE enhances global feature representation of point cloud masked autoencoders by making them both discriminative and sensitive to transformations.<n>We propose a novel loss that explicitly penalizes invariant collapse, enabling the network to capture richer transformation cues while preserving discriminative representations.
  arXiv  Detail & Related papers  (2024-09-24T07:57:21Z)
• Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning [74.48337375174297]
  Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge transferred from the seen domain. We deploy the dual semantic-visual transformer module (DSVTM) to progressively model the correspondences between prototypes and visual features. DSVTM devises an instance-motivated semantic encoder that learns instance-centric prototypes to adapt to different images, enabling the recast of the unmatched semantic-visual pair into the matched one.
  arXiv  Detail & Related papers  (2023-03-27T15:21:43Z)
• Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation [56.830395467247016]
  We propose a model of semantic memory for WSD in a meta-learning setting. Our model is based on hierarchical variational inference and incorporates an adaptive memory update rule via a hypernetwork. We show our model advances the state of the art in few-shot WSD, supports effective learning in extremely data scarce scenarios.
  arXiv  Detail & Related papers  (2021-06-05T20:40:01Z)

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.