Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.14401 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908662302244864 |
|---|---|
| author | Geng, Shuyi Zhou, Tao Zhou, Yi |
| author_facet | Geng, Shuyi Zhou, Tao Zhou, Yi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14401 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Language as an Anchor: Preserving Relative Visual Geometry for Domain Incremental Learning Geng, Shuyi Zhou, Tao Zhou, Yi Computer Vision and Pattern Recognition 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. |
| title | Language as an Anchor: Preserving Relative Visual Geometry for Domain Incremental Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.14401 |