Papers › Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights
Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights
Arun Mallya, Dillon Davis, Svetlana Lazebnik
This work presents a method for adapting a single, fixed deep neural network to multiple tasks without affecting performance on already learned tasks. By building upon ideas from network quantization and pruning, we learn binary masks that piggyback on an existing network, or are applied to unmodified weights of that network to provide good performance on a new task. These masks are learned in an end-to-end differentiable fashion, and incur a low overhead of 1 bit per network parameter, per task. Even though the underlying network is fixed, the ability to mask individual weights allows for the learning of a large number of filters. We show performance comparable to dedicated fine-tuned networks for a variety of classification tasks, including those with large domain shifts from the initial task (ImageNet), and a variety of network architectures. Unlike prior work, we do not suffer from catastrophic forgetting or competition between tasks, and our performance is agnostic to task ordering. Code available at https://github.com/arunmallya/piggyback.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Continual Learning | CUBS (Fine-grained 6 Tasks) | Piggyback | Accuracy | 80.5 | #4 of 6 | Archive leaderboard | report |
| Continual Learning | Flowers (Fine-grained 6 Tasks) | Piggyback | Accuracy | 94.77 | #4 of 6 | Archive leaderboard | report |
| Continual Learning | ImageNet (Fine-grained 6 Tasks) | Piggyback | Accuracy | 76.16 | #2 of 6 | Archive leaderboard | report |
| Continual Learning | Sketch (Fine-grained 6 Tasks) | Piggyback | Accuracy | 79.91 | #3 of 6 | Archive leaderboard | report |
| Continual Learning | Stanford Cars (Fine-grained 6 Tasks) | Piggyback | Accuracy | 89.62 | #4 of 6 | Archive leaderboard | report |
| Continual Learning | Wikiart (Fine-grained 6 Tasks) | Piggyback | Accuracy | 71.33 | #5 of 6 | Archive leaderboard | report |
| Continual Learning | visual domain decathlon (10 tasks) | Piggyback | Avg. Accuracy | 76.60 | #8 of 14 | Archive leaderboard | report |
| Continual Learning | visual domain decathlon (10 tasks) | Piggyback | decathlon discipline (Score) | 2838 | #8 of 14 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections