Research map / Architectures and efficiency / Pruning and efficient tuning
Sparse Winning Tickets are Data-Efficient Image Recognizers
Mukund Varma T, Xuxi Chen, Zhenyu Zhang, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace dense network with IMP winning ticket, both with best augmentation | ResNet-18 · CIFAR10 (2%) | accuracy: 55.14% -> 70.05% | Improved |
| replace dense network with IMP winning ticket, both with best augmentation | ResNet-18 · CIFAR10 (1%) | accuracy: 43.8% -> 59.66% | Improved |
| add IMP winning ticket to ImageNet-initialized fine-tuning | ResNet-18 ImageNet init · CIFAR10 (1%) | accuracy: 66.00% -> 69.46% | Improved |
| add IMP winning ticket to SimCLR-initialized fine-tuning | ResNet-18 SimCLR init · CIFAR10 (2%) | accuracy: 52.58% -> 64.09% | Improved |
| add IMP to t-vMF loss | t-vMF loss · CLaMM | accuracy: 24.50% -> 59.67% | Improved |
| add IMP to harmonic nets | Harmonic nets · CIFAR10 (1%) | accuracy: 22.97% -> 49.85% | Improved |
| add IMP to ImageNet-initialized ResNet-18 | ResNet-18 ImageNet init · CLaMM | accuracy: 47.46% -> 55.86% | Improved |
| add IMP winning ticket on small-sample datasets with Basic augmentation | ResNet-18 · EuroSAT | accuracy: 83.44% -> 87.85% | Improved |
| winning ticket on more complex many-class subsets | ResNet-18 · CIFAR100 (2%) | accuracy: 17.21% -> 25.06% | Improved |
| winning ticket on ImageNet subset | ResNet-18 · ImageNet (5%) | accuracy: 28.82% -> 31.04% | Improved |
| winning ticket on long-tailed data | ResNet-18 · Long-tailed CIFAR100 (imbalance 0.01) | accuracy: 45.13 -> 46.73 | Improved |
| winning ticket on mildly imbalanced data | ResNet-18 · Long-tailed CIFAR100 (imbalance 0.10) | accuracy: 64.77 -> 64.92 | No clear effect |
Closest papers by meaning
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (ICLR 2019 · similarity 0.91)
- Winning the Lottery with Continuous Sparsification (NeurIPS 2020 · similarity 0.91)
- Efficient Lottery Ticket Finding: Less Data is More (ICML 2021 · similarity 0.91)
- Plant 'n' Seek: Can You Find the Winning Ticket? (ICLR 2022 · similarity 0.91)
- Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win (ICML 2025 · similarity 0.89)
- Find A Winning Sign: Sign Is All We Need to Win the Lottery (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
