Ross ROSS = Recommend OSS · open-source software intelligence for agents

keyu-tian/SparK

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling" observed · 2026-08-28

github.com/keyu-tian/SparK · homepage · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

22/100

  • Activity 0
  • Release rhythm 8
  • Longevity 95
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 1336
  • days_rel: n/a
  • days_push: 953
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1376 stars · 85 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

SparK is the official PyTorch implementation of an ICLR 2023 Spotlight paper that applies BERT/MAE-style masked image modeling to convolutional networks using sparse convolution and a hierarchical decoder. It can pretrain any CNN (e.g., ResNet, ConvNeXt) in a self-supervised manner without backbone modifications.

Use cases

  • pretrain a ResNet or ConvNeXt with masked image modeling
  • self-supervised pretraining for CNN backbones
  • improve object detection and instance segmentation with pretrained CNN features
  • reproduce BERT-style pretraining on convolutional networks
  • compare sparse masked modeling against contrastive learning baselines
  • fine-tune pretrained CNN weights on ImageNet classification

When to choose

  • you want MAE/BERT-style self-supervised pretraining but must use a CNN backbone
  • you need better transfer features for detection or segmentation with convolutional models
  • you are researching masked image modeling on hierarchical architectures

When to avoid

  • you are pretraining vision transformers, where standard MAE applies directly
  • you need a maintained production library rather than a research codebase
  • you lack GPU resources for large-scale pretraining

Facets

library · maturity stable

machine-learning deep-learning llm-training computer-vision deep-learning image-processing python masked-image-modeling self-supervised-learning sparse-convolution cnn-pretraining bert-style pytorch iclr2023 resnet convnext object-detection gpu linux

6 sources

Member repositories

RepositoryRoleHealth v2
keyu-tian/SparKmain22

For agents

markdown · JSON · MCP: product_card(name="keyu-tian/SparK")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem