attention-map

There are 11 repositories under attention-map topic.

  • rentainhe/visualization

    a collection of visualization function

    Language:Python3792841
  • MaybeShewill-CV/attentive-gan-derainnet

    Unofficial tensorflow implemention of "Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR 2018) " model https://maybeshewill-cv.github.io/attentive-gan-derainnet/

    Language:Python252108283
  • wooyeolBaek/attention-map

    🚀 Cross attention map tools for huggingface/diffusers

    Language:Python68336
  • YeongHyeon/MNIST_AttentionMap

    Attention mechanism with MNIST dataset

    Language:Python1520
  • younghoonNa/ViT_Attention_Map_Visualization

    ViT Attention map visualization (using Custom ViT and Pytorch timm module)

    Language:Jupyter Notebook13300
  • motokimura/attention_branch_network_demo

    Attention Branch Network demonstration

    Language:Jupyter Notebook7301
  • qiaott/HAN

    Exploring Human-like Attention Supervision in Visual Question Answering

  • Simcs/OOD-with-ViT

    [BigComp2023] "Attention Masking for Improved Near Out-of-Distribution Image Detection". Improving OOD detection using attention maps obtained from vision transformer.

    Language:Jupyter Notebook3200
  • KimRass/RotNet

    Pytorch implementation of 'RotNet' (Gidaris et al., 2018).

    Language:Python210
  • Rubo12345/Directed-Research-on-Vehicle-Re-Identification

    In this project, a novel framework is used from the reference mentioned in the README, which successfully encodes both geometric local features and global representations to distinguish vehicle instances, optimized only by the supervision from official ID labels. Specifically, given the insight that objects in ReID share similar geometric characteristics, a self-supervised representation learning technique is used to facilitate geometric features discovery. To condense these features, an interpretable attention module, with the core of local maxima aggregation instead of fully automatic learning, in used, whose mechanism is completely understandable and whose response map is physically reasonable.

    Language:Python0100