A Pytorch implementation of "Manifold Matching via Deep Metric Learning for Generative Modeling" (ICCV 2021)

Related tags

Deep Learning pytorch-manifold-matching
Overview

Manifold Matching via Deep Metric Learning for Generative Modeling

A Pytorch implementation of "Manifold Matching via Deep Metric Learning for Generative Modeling" (ICCV 2021).

Paper: https://arxiv.org/abs/2106.10777

Objective functions

Objective for metric learning:

triplet_loss = triplet_(ml_real_out,ml_real_out_shuffle,ml_fake_out_shuffle)

Objective for manifold matching with learned metric:

g_loss = p_dist + c_dist

where

ml_real_out = netML(real_img) # real data
ml_fake_out = netML(fake_img) # generated data 

# shuffle in batch
r1=torch.randperm(batch_size)
r2=torch.randperm(batch_size)
ml_real_out_shuffle = ml_real_out[r1[:, None]].view(ml_real_out.shape[0],ml_real_out.shape[-1])
ml_fake_out_shuffle = ml_fake_out[r2[:, None]].view(ml_fake_out.shape[0],ml_fake_out.shape[-1])

# pairwise distances 
pd_r = pairwise_distances(ml_real_out, ml_real_out) 
pd_f = pairwise_distances(ml_fake_out, ml_fake_out)
 
# matching terms 
p_dist =  torch.dist(pd_r,pd_f,2) # matching 2-diameters             
c_dist = torch.dist(ml_real_out.mean(0),ml_fake_out.mean(0),2) # matching centroids

Dependencies

  • Pytorch 1.0.1

Dataset

Download data to the data path. The sample code uses CelebA dataset.

Training

To train a model for unconditonal generation, run:

python train.py

       

We also tried our objective on generating higher resolution images using a StyleGAN2 data generator and a simple metric generator. Implemenation details can be found here. Below are randomly generated 512x512 samples on FFHQ dataset at ~150K iterations:

Citation

@misc{daiandhang2021manifold,
      title={Manifold Matching via Deep Metric Learning for Generative Modeling}, 
      author={Mengyu Dai and Haibin Hang},
      year={2021},
      eprint={2106.10777},
      archivePrefix={arXiv}
}
You might also like...
This is the official pytorch implementation for our ICCV 2021 paper
This is the official pytorch implementation for our ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering" on VQA Task

🌈 ERASOR (RA-L'21 with ICRA Option) Official page of "ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point C

Hyungtae Lim 225 Dec 29, 2022
PyTorch implementation of our ICCV 2021 paper, Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents.
PyTorch implementation of our ICCV 2021 paper, Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents.

PyTorch implementation of our ICCV 2021 paper, Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents.

Saim Wani 4 May 8, 2022
Official PyTorch implementation of N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras (ICCV 2021)
Official PyTorch implementation of N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras (ICCV 2021)

N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras Official PyTorch implementation of N-ImageNet: Towards Robust, Fine-Gra

null 32 Dec 26, 2022
Official Pytorch implementation of the paper
Official Pytorch implementation of the paper "Action-Conditioned 3D Human Motion Synthesis with Transformer VAE", ICCV 2021

ACTOR Official Pytorch implementation of the paper "Action-Conditioned 3D Human Motion Synthesis with Transformer VAE", ICCV 2021. Please visit our we

Mathis Petrovich 248 Dec 23, 2022
Official PyTorch code of DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization (ICCV 2021 Oral).
Official PyTorch code of DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization (ICCV 2021 Oral).

DeepPanoContext (DPC) [Project Page (with interactive results)][Paper] DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context G

Cheng Zhang 66 Nov 16, 2022
Official pytorch code for SSC-GAN: Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation(ICCV 2021)

SSC-GAN_repo Pytorch implementation for 'Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation'.PDF SSC-GAN:Sem

tyty 4 Aug 28, 2022
Official implementation of NPMs: Neural Parametric Models for 3D Deformable Shapes - ICCV 2021
Official implementation of NPMs: Neural Parametric Models for 3D Deformable Shapes - ICCV 2021

NPMs: Neural Parametric Models Project Page | Paper | ArXiv | Video NPMs: Neural Parametric Models for 3D Deformable Shapes Pablo Palafox, Aljaz Bozic

PabloPalafox 109 Nov 22, 2022
Official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.
Official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.

Vision Transformer with Progressive Sampling This is the official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.

yuexy 123 Jan 1, 2023
Official implementation of the ICCV 2021 paper
Official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence".

The DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a conditional cross-attention mechanism for fast DETR training. Our approach is motivated by that the cross-attention in DETR relies highly on the content embeddings and that the spatial embeddings make minor contributions, increasing the need for high-quality content embeddings and thus increasing the training difficulty.

null 281 Dec 30, 2022
Comments
  • About metric learning output embedding

    About metric learning output embedding

    作者您好，论文中您在Unconditional Image Generation和Single Image Super-Resolution这两个任务上为netML设置了不同的output embedding(分别为10和32)，如何根据自己的任务来选择合适的output embedding呢？比如Image-to-Image translation这样的任务。

    opened by ElegantLee 3
  • Question about Triplet Loss

    Question about Triplet Loss

    Thanks for your fantasy work. I have a question about Triplet Loss.

        def forward(self, anchor, positive, negative, size_average=True):
        distance_positive = (anchor - positive).pow(2).sum(1)  # .pow(.5)
        distance_negative = (anchor - negative).pow(2).sum(1)  # .pow(.5)
        
        cos = nn.CosineSimilarity(dim=1, eps=1e-6)
        cos_reg = cos(negative - anchor, positive - anchor).sum(0) 
        losses = F.relu(distance_positive - distance_negative + self.margin - self.alpha * cos_reg) #2e-2

        return losses.mean()

    When the value of distance_negative is higher than the value of distance_positive, the losses may be zeros. how to avoid it.

    opened by wmpscc 3
  • Question about the picture of image manifold

    Question about the picture of image manifold

    Hello, recently I'm thinking about how to use a graph to represent the image manifold and the process of manifold matching. It's really hard. How to draw the picture and the animation just like yours? I hope you can give me some advice !

    opened by ElegantLee 1
Owner
null
GitHub
An official implementation of "Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation" (ICCV 2021) in PyTorch.

Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation This is an official implementation of the paper "Exploiting a Joint

CV Lab @ Yonsei University 35 Oct 26, 2022
[ICCV 2021] Official Pytorch implementation for Discriminative Region-based Multi-Label Zero-Shot Learning SOTA results on NUS-WIDE and OpenImages

Discriminative Region-based Multi-Label Zero-Shot Learning (ICCV 2021) [arXiv][Project page >> coming soon] Sanath Narayan*, Akshita Gupta*, Salman Kh

Akshita Gupta 54 Nov 21, 2022
[ICCV 2021] Official Pytorch implementation for Discriminative Region-based Multi-Label Zero-Shot Learning SOTA results on NUS-WIDE and OpenImages

Discriminative Region-based Multi-Label Zero-Shot Learning (ICCV 2021) [arXiv][Project page >> coming soon] Sanath Narayan*, Akshita Gupta*, Salman Kh

Akshita Gupta 54 Nov 21, 2022
[ICCV 2021] Official PyTorch implementation for Deep Relational Metric Learning.

Deep Relational Metric Learning This repository is the official PyTorch implementation of Deep Relational Metric Learning. Framework Datasets CUB-200-

Borui Zhang 39 Dec 10, 2022
official Pytorch implementation of ICCV 2021 paper FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting.

FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting By Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi, Lewei Lu, Wenxiu

null 77 Dec 27, 2022
A PyTorch implementation of the baseline method in Panoptic Narrative Grounding (ICCV 2021 Oral)

A PyTorch implementation of the baseline method in Panoptic Narrative Grounding (ICCV 2021 Oral)

Biomedical Computer Vision @ Uniandes 52 Dec 19, 2022
Official pytorch implementation of "Scaling-up Disentanglement for Image Translation", ICCV 2021.

Official pytorch implementation of "Scaling-up Disentanglement for Image Translation", ICCV 2021.

Aviv Gabbay 41 Nov 29, 2022
PyTorch implementation of the WarpedGANSpace: Finding non-linear RBF paths in GAN latent space (ICCV 2021)

Authors official PyTorch implementation of the "WarpedGANSpace: Finding non-linear RBF paths in GAN latent space" [ICCV 2021].

Christos Tzelepis 100 Dec 6, 2022
Official PyTorch Implementation of paper "Deep 3D Mask Volume for View Synthesis of Dynamic Scenes", ICCV 2021.

Deep 3D Mask Volume for View Synthesis of Dynamic Scenes Official PyTorch Implementation of paper "Deep 3D Mask Volume for View Synthesis of Dynamic S

Ken Lin 17 Oct 12, 2022
Pytorch implementation for our ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering".

TRAnsformer Routing Networks (TRAR) This is an official implementation for ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visu

Ren Tianhe 49 Nov 10, 2022