Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CORe50: a New Dataset and Benchmark for Continuous Object Recognition

About

Continuous/Lifelong learning of high-dimensional data streams is a challenging research problem. In fact, fully retraining models each time new data become available is infeasible, due to computational and storage issues, while na\"ive incremental strategies have been shown to suffer from catastrophic forgetting. In the context of real-world object recognition applications (e.g., robotic vision), where continuous learning is crucial, very few datasets and benchmarks are available to evaluate and compare emerging techniques. In this work we propose a new dataset and benchmark CORe50, specifically designed for continuous object recognition, and introduce baseline approaches for different continuous learning scenarios.

Vincenzo Lomonaco, Davide Maltoni• 2017

Related benchmarks

TaskDatasetResultRank
Link PredictionGraphHigher last snapshot (test)
MRR20.3
12
Link PredictionGraphEqual last snapshot (test)
MRR12.2
12
Link PredictionGraphLower last snapshot (test)
MRR3.2
12
Link PredictionDB-CKGE last snapshot (test)
MRR0.026
12
Link PredictionENTITY (test)
MRR8.8
12
Link PredictionRELATION (test)
MRR2.1
12
Link PredictionHybrid (test)
MRR0.037
12
Link PredictionFB-CKGE (test)
MRR7.5
12
Object ClassificationCORe-50 (test)
Increments21
10
Class-incremental learningImageNet first 10 classes 1.0 (test)
Accuracy (Task 1)83.2
4
Showing 10 of 10 rows

Other info

Follow for update