arXiv Computer Vision
Continual Visual Learning under Evolving Semantic Concept Shift
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Aug 24
Continual Visual Learning under Evolving Semantic Concept Shift
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...
arXiv Computer Vision
4d ago
Semantic Concept Steering Breaks the Explanation Drift Loop in Continual Learning
arXiv:2610.33877v1 Announce Type: new Abstract: Catastrophic forgetting in continual learning (CL) manifests not only as accuracy degradation but also as \emph{explanation drift}: models maintain pre...
arXiv Machine Learning
Jul 31
Continual Learning with Vision-Language Models via Semantic-Geometry Preservation
arXiv:2603. 12055v3 Announce Type: replace-cross Abstract: Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from pretraining and previous stages, allowing new-task supervision to induce geometric distortion.
arXiv Machine Learning
Oct 21
Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
The paper introduces HASTEN, a hierarchical semantic tree anchoring framework that enhances CLIP-based class‑incremental learning by incorporating external hierarchical knowledge into hyperbolic space. By treating classes as part of a structured hierarchy rather than isolated labels, HASTEN stabilizes visual and textual feature mappings, reduces feature drift, and mitigates catastrophic forgetting across incremental tasks. Experiments on nine benchmarks demonstrate that HASTEN consistently outperforms existing methods.
arXiv Machine Learning
Jul 28
EditCLEVR: A Paired-Scene Intervention Benchmark for Compositional Faithfulness of Object-Centric Representations
arXiv:2607. 22705v1 Announce Type: cross Abstract: Object-centric learning aims to represent scenes as objects whose properties can be reused in new combinations.
arXiv AI
5d ago
Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images
The paper introduces Self-RefineVQA, a training‑free, inference‑time framework that lets a single Vision‑Language Model iteratively generate, critique, and refine its own answers for table visual question answering. By forming a closed self‑feedback loop guided by prompts, the method corrects common reasoning errors such as spatial misalignment and logical hallucinations without requiring additional labeled data or model updates. Experiments on tabular VQA benchmarks show consistent accuracy gains across monolingual and cross‑lingual settings, especially for lightweight models, while keeping inference cost linear and eliminating the need for expensive supervised fine‑tuning.