CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions
Vincenzo Lomonaco,Lorenzo Pellegrini,Pau Rodríguez,Massimo Caccia,Qi She,Yu Chen,Quentin Jodelet,Quentin Jodelet,Ruiping Wang,Zheda Mai,David Vazquez,German Ignacio Parisi,Nikhil Churamani,Marc Pickett,Issam H. Laradji,Davide Maltoni +15 more
TLDR
The first Continual Learning in Computer Vision Challenge (CLCVC) as discussed by the authors was held in 2019, which was one of the first opportunities to evaluate different continual learning algorithms on a common hardware with a large set of shared evaluation metrics and 3 different settings based on the realistic CORe50 video benchmark.About:
This article is published in Artificial Intelligence.The article was published on 2022-02-01 and is currently open access. It has received 10 citations till now. The article focuses on the topics: Benchmarking & Computer science.read more
Citations
More filters
Book ChapterDOI
Practical Recommendations for Replay-based Continual Learning Methods
TL;DR: In this paper , the authors compare and analyze replay-based strategies and provide practical recommendations on developing efficient, effective and generally applicable replaybased strategies, and investigate the role of the memory size value, different weighting policies and discuss about the impact of data augmentation.
Journal ArticleDOI
Fault Diagnosis of Wind Turbine Bearings Based on CNN and SSA–ELM
Proceedings ArticleDOI
Unsupervised Continual Learning for Gradually Varying Domains
TL;DR: In this article , a source free method based on episodic memory replay with buffer management is proposed to address a gradually evolving target domain fragmented into multiple sequential batches where the model continually adapts to the gradually varying stream of data in an unsupervised manner.
Journal ArticleDOI
AI Autonomy: Self‐initiated Open‐world Continual Learning and Adaptation
TL;DR: In this article , the authors propose a framework (called SOLA) for autonomous and continual learning enabled AI agents, which aims to make these agents self-motivated and self-initiated, rather than being retrained offline periodically on the initiation of human engineers.
Journal ArticleDOI
Balanced softmax cross-entropy for incremental learning with and without memory
TL;DR: In this article , the authors proposed to use the Balanced Softmax Cross-Entropy (BSCE) for class-incremental learning in order to improve their accuracy while also potentially decreasing the computational cost of the training procedure.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Dissertation
Learning Multiple Layers of Features from Tiny Images
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.
Journal ArticleDOI
Continual lifelong learning with neural networks: A review.
TL;DR: This review critically summarize the main challenges linked to lifelong learning for artificial learning systems and compare existing neural network approaches that alleviate, to different extents, catastrophic forgetting.