Language as an Anchor: Preserving Relative Visual Geometry for Domain Incremental Learning

• URL: http://arxiv.org/abs/2511.14401v1
• Date: Tue, 18 Nov 2025 12:06:55 GMT
• Title: Language as an Anchor: Preserving Relative Visual Geometry for Domain Incremental Learning
• Authors: Shuyi Geng, Tao Zhou, Yi Zhou,
• Abstract summary: Key challenge in Domain Incremental Learning is to continually learn under shifting distributions.<n>We propose LAVA, a novel DIL framework that replaces direct feature alignment with relative alignment driven by a text-based reference anchor.<n> experiments on standard DIL benchmarks demonstrate that LAVA achieves significant performance improvements over state-of-the-arts.
• Score: 8.952803050083203
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A key challenge in Domain Incremental Learning (DIL) is to continually learn under shifting distributions while preserving knowledge from previous domains. Existing methods face a fundamental dilemma. On one hand, projecting all domains into a single unified visual space leads to inter-domain interference and semantic distortion, as large shifts may vary with not only visual appearance but also underlying semantics. On the other hand, isolating domain-specific parameters causes knowledge fragmentation, creating "knowledge islands" that hamper knowledge reuse and exacerbate forgetting. To address this issue, we propose LAVA (Language-Anchored Visual Alignment), a novel DIL framework that replaces direct feature alignment with relative alignment driven by a text-based reference anchor. LAVA guides the visual representations of each incoming domain to preserve a consistent relative geometry, which is defined by mirroring the pairwise semantic similarities between the class names. This anchored geometric structure acts as a bridge across domains, enabling the retrieval of class-aware prior knowledge and facilitating robust feature aggregation. Extensive experiments on standard DIL benchmarks demonstrate that LAVA achieves significant performance improvements over state-of-the-arts. Code is available at https://github.com/ShuyiGeng/LAVA.

Related papers

• Learn Before Represent: Bridging Generative and Contrastive Learning for Domain-Specific LLM Embeddings [14.859728745469354]
  Large Language Models (LLMs) adapted via contrastive learning excel in general representation learning but struggle in vertical domains like chemistry and law.<n>This work identifies a core bottleneck: the prevailing LLM+CL'' paradigm focuses on semantic alignment but cannot perform knowledge acquisition.<n>We propose Learn Before Represent, a novel two-stage framework for building accurate and robust representations in vertical domains.
  arXiv  Detail & Related papers  (2026-01-16T09:35:29Z)
• Exploiting Domain Properties in Language-Driven Domain Generalization for Semantic Segmentation [16.081767698947186]
  We present a novel domain generalization framework for semantic segmentation, namely Domain-aware Prompt-driven Masked Transformer (DPMFormer)<n> Firstly, we introduce domain-aware prompt learning to facilitate semantic alignment between visual and textual cues.<n>To capture various domain-specific properties with a single source dataset, we propose domain-aware contrastive learning along with the texture perturbation that diversifies the observable domains.
  arXiv  Detail & Related papers  (2025-12-03T06:58:38Z)
• Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learning [20.048013939398484]
  Cross-Domain Few-Shot Learning endeavors to transfer generalized knowledge from the source domain to target domains.<n>We make novel attempts to construct Intermediate Domain Proxies (IDP) with source feature embeddings as the codebook.<n>We develop a fast domain alignment method to use these proxies as learning guidance for target domain feature transformation.
  arXiv  Detail & Related papers  (2025-11-18T09:14:06Z)
• Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation [27.40776917141145]
  Class-Incremental Unsupervised Domain Adaptation (CI-UDA) aims to adapt a model from a labeled source domain to an unlabeled target domain.<n>The key to solving this problem lies in avoiding catastrophic forgetting of knowledge about previous target classes.<n>We propose to mine and preserve domain-invariant and class-agnostic knowledge to facilitate the CI-UDA task.
  arXiv  Detail & Related papers  (2025-09-14T13:27:46Z)
• Prompt-based Visual Alignment for Zero-shot Policy Transfer [35.784936617675896]
  Overfitting in reinforcement learning has become one of the main obstacles to applications in reinforcement learning. We propose prompt-based visual alignment (PVA) to mitigate the detrimental domain bias in the image for zero-shot policy transfer. We verify PVA on a vision-based autonomous driving task with CARLA simulator.
  arXiv  Detail & Related papers  (2024-06-05T13:26:30Z)
• Unsupervised Domain Adaptation via Style-Aware Self-intermediate Domain [52.783709712318405]
  Unsupervised domain adaptation (UDA) has attracted considerable attention, which transfers knowledge from a label-rich source domain to a related but unlabeled target domain.<n>We propose a novel style-aware feature fusion method (SAFF) to bridge the large domain gap and transfer knowledge while alleviating the loss of class-discnative information.
  arXiv  Detail & Related papers  (2022-09-05T10:06:03Z)
• SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning [6.705297811617307]
  Domain adaptation can help in transferring knowledge from a labeled source domain to an unlabeled target domain. We propose a novel semantic prototype-based contrastive learning framework for fine-grained class alignment. Our method is easy to implement and attains superior results compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-11-24T09:26:07Z)
• HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning [74.76431541169342]
  Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. We propose a novel hierarchical semantic-visual adaptation (HSVA) framework to align semantic and visual domains. Experiments on four benchmark datasets demonstrate HSVA achieves superior performance on both conventional and generalized ZSL.
  arXiv  Detail & Related papers  (2021-09-30T14:27:50Z)
• Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains [108.11746235308046]
  We propose a novel approach that learns domain-agnostic structured latent embeddings by projecting images from different domains. Our experiments on the challenging DomainNet and DomainNet-LS benchmarks show the superiority of our approach over existing methods.
  arXiv  Detail & Related papers  (2021-07-12T17:57:46Z)
• Cross-domain Contrastive Learning for Unsupervised Domain Adaptation [108.63914324182984]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. We build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets.
  arXiv  Detail & Related papers  (2021-06-10T06:32:30Z)
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection [90.18752912204778]
  Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
  arXiv  Detail & Related papers  (2021-06-10T05:01:20Z)
• Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation [56.694330303488435]
  We propose a Learning to Combine for Multi-Source Domain Adaptation (LtC-MSDA) framework. In the nutshell, a knowledge graph is constructed on the prototypes of various domains to realize the information propagation among semantically adjacent representations. Our approach outperforms existing methods with a remarkable margin.
  arXiv  Detail & Related papers  (2020-07-17T07:52:44Z)
• Learning Cross-domain Semantic-Visual Relationships for Transductive Zero-Shot Learning [29.498249893085287]
  This work proposes the Transferrable Semantic-Visual Relation (TSVR) approach towards transductive Zero-Shot Learning (ZSL) TSVR redefines image recognition as predicting the similarity/dissimilarity labels for semantic-visual fusions consisting of class attributes and visual features. For the problem, the number of similar semantic-visual pairs is significantly smaller than that of dissimilar ones.
  arXiv  Detail & Related papers  (2020-03-31T11:26:49Z)

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.