Papers › WaveMix-Lite: A Resource-efficient Neural Network for Image Analysis
WaveMix-Lite: A Resource-efficient Neural Network for Image Analysis
Jeevan, Pranav; Sethi, Amit
Gains in the ability to generalize on image analysis tasks for neural networks have come at the cost of increased number of parameters and layers, dataset sizes, training and test computations, and GPU RAM. We introduce a new architecture -- WaveMix-Lite -- that can generalize on par with contemporary transformers and convolutional neural networks (CNNs) while needing fewer resources. WaveMix-Lite uses 2D-discrete wavelet transform to efficiently mix spatial information from pixels. WaveMix-Lite seems to be a versatile and scalable architectural framework that can be used for multiple vision tasks, such as image classification and semantic segmentation, without requiring significant architectural changes, unlike transformers and CNNs. It is able to meet or exceed several accuracy benchmarks while training on a single GPU. For instance, it achieves state-of-the-art accuracy on five EMNIST datasets, outperforms CNNs and transformers in ImageNet-1K and Places-365, and achieves an mIoU of 77\% on Cityscapes validation set, while using less than one-fifth the number parameters and half the GPU RAM of comparable CNNs or transformers. Our experiments show that while the convolutional elements of neural architectures exploit the shift-invariance property of images, new types of layers (e.g., wavelet transform) can exploit additional properties of images, such as scale-invariance and finite spatial extents of objects.
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
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | ImageNet | WaveMixLite-256/24 | Number of params | 32.4M | #1039 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | WaveMixLite-256/24 | Top 1 Accuracy | 67.7% | #1039 of 1060 | Archive leaderboard | report |
| Image Classification | SVHN | WaveMixLite | Percentage error | 1.58 | #14 of 62 | Archive leaderboard | report |
| Image Classification | Tiny ImageNet Classification | WaveMixLite-160/13 | Validation Acc | 54.76 | #22 of 23 | Archive leaderboard | report |
| Semantic Segmentation | Cityscapes val | WaveMixLite-256/16 | mIoU | 76.79 | #67 of 99 | 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.
Methods
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