Saliency-driven Experience Replay for Continual Learning
Authors: Giovanni Bellitto, Federica Proietto Salanitri, Matteo Pennisi, Matteo Boschini, Lorenzo Bonicelli, Angelo Porrello, SIMONE CALDERARA, Simone Palazzo, Concetto Spampinato
NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results confirm that SER effectively enhances the performance (in some cases up to about twenty percent points) of state-of-the-art continual learning methods, both in class-incremental and task-incremental settings. |
| Researcher Affiliation | Academia | Giovanni Bellitto University of Catania giovanni.bellitto@unict.it Federica Proietto Salanitri University of Catania federica.proiettosalanitri@unict.it Matteo Pennisi University of Catania matteo.pennisi@phd.unict.it Matteo Boschini University of Modena and Reggio Emilia matteo.boschini@unimore.it Lorenzo Bonicelli University of Modena and Reggio Emilia lorenzo.bonicelli@unimore.it Angelo Porrello University of Modena and Reggio Emilia angelo.porrello@unimore.it Simone Calderara University of Modena and Reggio Emilia simone.calderara@unimore.it Simone Palazzo University of Catania simone.palazzo@unict.it Concetto Spampinato University of Catania concetto.spampinato@unict.it |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code is available at: https: //github.com/perceivelab/SER. |
| Open Datasets | Yes | Split Mini-Image Net [66, 13, 21, 17] that includes 100 classes from Image Net, allowing for a longer task sequence. For each class, 500 images are used for training and 100 for evaluation. Split FG-Image Net1 [58] is a benchmark for fine-grained image classification that we use to test CL methods on a more challenging task than traditional ones. |
| Dataset Splits | Yes | For both datasets, images are resized to 288 384 pixels and split into twenty 5-way tasks. |
| Hardware Specification | Yes | All experiments were conducted on a workstation with an 24-core CPU, 500GB RAM, and an NVIDIA A100 GPU (40GB VRAM). |
| Software Dependencies | No | The paper mentions 'Mammoth framework [9]' and 'UNISAL[20]' but does not provide specific version numbers for these or other software components. |
| Experiment Setup | Yes | In compliance with online learning, all models are trained for a single epoch, using SGD as optimizer, with a fixed batch size of 8 both for the input stream and the replay buffer. Rehearsal methods are evaluated with three different sizes of the memory buffer (1000, 2000 and 5000). |