Pith. sign in

REVIEW 5 cited by

PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 1711.05769 v2 pith:QMVPKD55 submitted 2017-11-15 cs.CV

Arun Mallya , Svetlana Lazebnik This is my paper · ORCID
classification cs.CV
keywords networktaskssinglemultiplepruningableaddingcatastrophic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents a method for adding multiple tasks to a single deep neural network while avoiding catastrophic forgetting. Inspired by network pruning techniques, we exploit redundancies in large deep networks to free up parameters that can then be employed to learn new tasks. By performing iterative pruning and network re-training, we are able to sequentially "pack" multiple tasks into a single network while ensuring minimal drop in performance and minimal storage overhead. Unlike prior work that uses proxy losses to maintain accuracy on older tasks, we always optimize for the task at hand. We perform extensive experiments on a variety of network architectures and large-scale datasets, and observe much better robustness against catastrophic forgetting than prior work. In particular, we are able to add three fine-grained classification tasks to a single ImageNet-trained VGG-16 network and achieve accuracies close to those of separately trained networks for each task. Code available at https://github.com/arunmallya/packnet

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays

    cs.RO 2026-06 unverdicted novelty 7.0 of 10

    REGEN uses recurrent generative replays from World Action Models to cut catastrophic forgetting by up to 50% in continual imitation learning compared to sequential fine-tuning.

  2. The impact of allocation strategies in subset learning on the expressive power of neural networks

    cs.LG 2025-02 conditional novelty 7.0 of 10

    In a teacher-student setup, maximal expressive power for a fixed learnable-weight budget is characterized by even row or column distribution in linear RNNs and feedforward networks.

  3. BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    BRAIN uses bias-mitigation continual learning with a new de-bias contrastive loss and angular forgetting mitigation to achieve SOTA performance on vision-brain understanding benchmarks despite brain signal inconsisten...

  4. C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

    cs.CV 2025-08 conditional novelty 5.0 of 10

    C3D-AD enables class-incremental 3D anomaly detection by combining random-feature kernel attention, a learnable advisor memory, and perturbation-based representation consistency.

  5. The Future of Continual Learning in the Era of Foundation Models: Three Key Directions

    cs.LG 2025-06 conditional novelty 4.0 of 10

    Continual learning should pivot from weight-update-based methods to continual compositionality and orchestration of foundation models and agents.

Pith tools