Popular GitHub Repositories for Boundary Losses

A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.

:art: Semantic segmentation models, datasets and losses implemented in PyTorch.

Developer friendly Natural Language Processing ?

Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"

A library for solving differential equations using neural networks based on PyTorch, used by multiple research groups around the world, including at Harvard IACS.

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]

A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.

Library for Jacobian descent with PyTorch. It enables optimization of neural networks with multiple losses (e.g. multi-task learning).

Ever wondered how to code your Neural Network using NumPy, with no frameworks involved?

TF2 Deep FloorPlan Recognition using a Multi-task Network with Room-boundary-Guided Attention. Enable tensorboard, quantization, flask, tflite, docker, github actions and google colab.

A TensorFlow implementation of Neural Sequence Labeling model, which is able to tackle sequence labeling tasks such as POS Tagging, Chunking, NER, Punctuation Restoration and etc.

A python package for simulating movement and spatial cell types (e.g. place cells, grid cells) in continuous environments.

RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features (CVPR 2021)

Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation (CVPR 2020)

Improving MMD-GAN training with repulsive loss function

[ECCV 2018] ReenactGAN: Learning to Reenact Faces via Boundary Transfer

[ECCV 2020] Boundary-preserving Mask R-CNN

A pytorch implementation of pix2pix + BEGAN (Boundary Equilibrium Generative Adversarial Networks)

Using Physics-Informed Deep Learning (PIDL) techniques (W-PINNs-DE & W-PINNs) to solve forward and inverse hydrodynamic shock-tube problems and plane stress linear elasticity boundary value problems

ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks, published in ECCV 2018) implemented in Tensorflow 2.0+. This is an unofficial implementation. With Colab.