Continually Learning Structured Visual Representations via Network Refinement with Rerelation
Current machine learning paradigm relies on continuous representations like neural networks, which iteratively adjust parameters to approximate outcomes rather than directly learning the structure of problem. This spreads information across the network, causing issues like information loss and incomprehensibility Building on prior work in environment dynamics modeling, we propose a method that learns visual space in a structured, continual manner. Our approach refines networks to capture the core structure of objects while representing significant subvariants in structure efficiently. We demonstrate this with 2D shape detection, showing incremental learning on MNIST without overwriting knowledge and creating compact, comprehensible representations. These results offer a promising step toward a transparent, continually learning alternative to traditional neural networks for visual processing.
Code (0)
등록된 구현이 없습니다.
Tasks
Incremental LearningSimilar Papers 제목 키워드 기반
Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments
Learning continually from a stream of non-i.i.d. data is an open challenge in deep learning, even more so when working in resource-constrained environments such as embedded devices. Visual models that are continually upd…
Continual LearningLanguage ModelingLanguage ModellingLarge Language ModelLearning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement
We present MACLA, a framework that decouples reasoning from learning by maintaining a frozen large language model while performing all adaptation in an external hierarchical procedural memory. MACLA extracts reusable pro…
Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers
Parameter-efficient fine-tuning (PEFT) has become a practical solution for adapting large pretrained vision transformers (ViTs) to downstream tasks while updating only a small subset of parameters. However, existing adap…
parameter-efficient fine-tuningComposition-Incremental Learning for Compositional Generalization
Compositional generalization has achieved substantial progress in computer vision on pre-collected training data. Nonetheless, real-world data continually emerges, with possible compositions being nearly infinite, long-t…
Compositional Zero-Shot LearningIncremental LearningFine-Grained Action Recognition with Cross-Attentive Latent Sparse Experts
Fine-grained human action recognition (FHAR) must distinguish visually similar actions that differ mainly in body configuration, timing, or local appearance. RGB representations retain visual context but often suppress j…
Action Recognition