Is Continual Learning Ready for Real-world Challenges?
Despite continual learning's long and well-established academic history, its application in real-world scenarios remains rather limited. This paper contends that this gap is attributable to a misalignment between the actual challenges of continual learning and the evaluation protocols in use, rendering proposed solutions ineffective for addressing the complexities of real-world setups. We validate our hypothesis and assess progress to date, using a new 3D semantic segmentation benchmark, OCL-3DSS. We investigate various continual learning schemes from the literature by utilizing more realistic protocols that necessitate online and continual learning for dynamic, real-world scenarios (eg., in robotics and 3D vision applications). The outcomes are sobering: all considered methods perform poorly, significantly deviating from the upper bound of joint offline training. This raises questions about the applicability of existing methods in realistic settings. Our paper aims to initiate a paradigm shift, advocating for the adoption of continual learning methods through new experimental protocols that better emulate real-world conditions to facilitate breakthroughs in the field.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Semantic SegmentationContinual LearningSemantic SegmentationSimilar Papers 제목 키워드 기반
Learn it or Leave it: Module Composition and Pruning for Continual Learning
In real-world environments, continual learning is essential for machine learning models, as they need to acquire new knowledge incrementally without forgetting what they have already learned. While pretrained language mo…
Continual LearningTransfer LearningLong-Tailed Continual Learning For Visual Food Recognition
Deep learning based food recognition has achieved remarkable progress in predicting food types given an eating occasion image. However, there are two major obstacles that hinder deployment in real world scenario. First, …
Continual LearningData AugmentationFood RecognitionKnowledge DistillationIs Class-Incremental Enough for Continual Learning?
The ability of a model to learn continually can be empirically assessed in different continual learning scenarios. Each scenario defines the constraints and the opportunities of the learning environment. Here, we challen…
Computational EfficiencyContinual LearningContinual Learning for Predictive Maintenance: Overview and Challenges
Deep learning techniques have become one of the main propellers for solving engineering problems effectively and efficiently. For instance, Predictive Maintenance methods have been used to improve predictions of when mai…
Continual LearningCLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion
To teach robots complex manipulation tasks, a common approach is to fine-tune a pre-trained vision-language-action model (VLA) on task-specific data. However, since this recipe updates existing representations, it is uns…
Continual Learning