REVIEW 2 cited by
Recent Advances of Continual Learning in Computer Vision: An Overview
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In contrast to batch learning where all training data is available at once, continual learning represents a family of methods that accumulate knowledge and learn continuously with data available in sequential order. Similar to the human learning process with the ability of learning, fusing, and accumulating new knowledge coming at different time steps, continual learning is considered to have high practical significance. Hence, continual learning has been studied in various artificial intelligence tasks. In this paper, we present a comprehensive review of the recent progress of continual learning in computer vision. In particular, the works are grouped by their representative techniques, including regularization, knowledge distillation, memory, generative replay, parameter isolation, and a combination of the above techniques. For each category of these techniques, both its characteristics and applications in computer vision are presented. At the end of this overview, several subareas, where continuous knowledge accumulation is potentially helpful while continual learning has not been well studied, are discussed.
Forward citations
Cited by 2 Pith papers
-
MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Models
A gradient-alignment influence score (GGscore) that selects the highest- and lowest-scoring old interactions for replay improves incremental neural recommendation slightly over random replay, mainly at large replay ratios.
-
Infinite Video Understanding
The paper argues that video understanding research should aim at processing streams of arbitrary, unbounded duration and outlines the challenges, directions, and metrics needed.
Discussion (0). Sign in to comment.