Sneaky Machine Learning Reading Group
He Wang, Tom Kelly, and their PGR students meet every Friday afternoon for the Machine Learning in 3D reading group. In each meeting, one person presents a cutting edge machine learning paper from any field. It is an opportunity to share knowledge and practice academic communication skills.
This page contains the contents of the past meetings (links to slides and meeting notes) and information of the upcoming meetings.
Time and Place
Upcoming meeting
2020 Meetings
31st Jan: Progressive Growing of GANs for Improved Quality, Stability, and Variation
Presenter: Jialin
Date: 31st Jan
Minutes:
He: original GAN can hardly learn the mixture of 2 distributions well.
Jialin: U-net concatenates left to the right at the same layer.
Tom: these connections maintain spatial resolution.
He: why weight of two ways is not a learnable parameter?
Jialin: Always fix the earlier layers when train the new layers.
He: Now that use means why calculate stand deviation?
Tom: Low resolution determines features.
7th Feb: Efficient N-Dimensional Convolutions via Higher-Order Factorization
Presenter: Zheyan
Date 7th Feb
Contents:
1 How to do convolution for dimension 0-3 tensors.
2 The overall convolution filter for a rank n tensor is a rank 2n tensor and why decompose it.
3 Some methods to decompose filters for n dimensions tensors.
15th Feb: TempoGAN
Presenter: Dody
Date 15th Feb
After the presentation please try to give your opinion on the paper!Contents:
TempoGAN projects the low resolution simulation result to high resolution result. Compared with past CNN, this module take 3 frames in time series as input.
Discussion:
Why there is dimension inconsistency?
Some region of TempoGAN result is worse than baseline. It is hard to say which result is better.
It is better to present one paper with more details than 2 papers.
21st Feb: Talking Face Generation by Adversarially Disentangled Audio-Visual Representation
Presenter: Feixiang
Discussion:
The words are embedded into ID format.
What is the training time?
The encoder and classifier are trained individually.
How to separate speech information and left words information.
Is there evidence that shows disentangle really works?
In the video there is minor change other than the mouse and bleezing eyes.
28st Feb: Generating Adversarial Examples By Makeup Attacks on Face Recognition
Presenter: Baiyi
Discussion:
This is CycleGAN, networks used for creating dataset.
Constraint GAN means difficulty in training.
Possible build two datasets, with and without makeup.
The purpose of attack: avoid recognition, update defense system.
6th Mar: Yarn-Level Simulation of Woven Cloth
Presenter: Deshan
Main content:
The difference of knit and woven and the reason to do yarn level simulation.
What are the Lagrangian and Euler DoFs.
The contact plane is used to compute contact force.
What is visco-elastic property.
13th March: Adversarial Examples Are Not Bugs, They Are Features
After presentation everyone please try to give some opinion on the paper.
Presenter: Yunfeng
27th March: Proximal Policy Optimization
Presenter: Xue
3th April: GAN Compression -Efficient Architectures for interactive Conditional GANs
Paper: GAN Compression -Efficient Architectures for interactive Conditional GANs.
Presenter: Jialin
Contents:
Traditional GAN conditional GAN and Pix2Pix GAN.
Previous methods to reduce calculation
Validation to choose proper student NN.
Decouple training and search.
10th April: Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control
Presentor: Zheyan
Contents:
Flow control and active control background, it is hard to design active control.
experiment setting.
Reinforcement algorithms. The output of ANN is the distribution of control strategy. Optimization loss is the long term performance. The samplle strategy number increase over time and seems training expense continues to grow.
24th April: Latent-space Dynamics for Reduced Deformable Simulation
Presenter : Dody
Contents:
Can we use ML to accelerate hypeelastic simulation?
Traditional Reduce order method use PCA.
How to integrate autoencoder.
Questions:
Why do not use autoencoder alone but with PCA?
What does J means?
1st May: TransMoMo
Presentor: Feixiang
8th May: Differentiable Cloth Simulation for Inverse Problems
Presenter: Deshan
Contents:
Concepts of discretization, implicit Euler , collision detection and responce
It usually need labor work to adjust the simulation parameters. The work aims automatically adjust parameters.
Dynamic and Continuous collision dectection, QR decomposion
Derivatives of the physics solve. Constrains, KKT condition.
Experiments
15th May: Deep Blending for Free-Viewpoint Image-Based-Rendering
Presenter: Jialin
Contents:
After the presentation please try to give your opinion on the paper!Traditional image blending.
Combine MVS and IBR.
Deep Blending, 4 challenges in old methods.
Two offline pipeline, one online.
3D geometry reconstruction.
DNN architecture.
Rendering algorithm.
Two novel training loss.
Limitation.
22nd May: Accelerated design and characterization of non-uniform cellular materials via a machine-learning based framework
After the presentation please try to give your opinion on the paper!
Presenter: Zheyan
29th May: MeshingNet
MeshingNet by Zheyan
The question asked in the presentation:
- How is the algorithm of the solution?
- How does the network connect to the mesh?
- When it breaks the triangle?
- Does it resize the triangle?
- Is the magic generator differentiable/ inside or outside the neural network?
- How do you make the particular neural network design?
- Why do you show training loss, rather than testing loss?
- If you don’t show the testing with training, it’s hard to tell.
The comments on every slide:
2nd slide: To make the figures with less information/To make it a bit simpler.
3rd slides: What data are you actually training on? Use a real mesh instead of simplified mesh.
4th slide: what does 3000 mean?
6th slide: It needs motivation: how should it affect the mesh? Need examples.
7th slide: what’s the baseline?
10th slide: make it look 3d.
11th slide: Why do the result by CZ have colour?
by Yunfeng
5th June: Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach
Paper link:
Query-Efficient Hard-label Black-box Attack:An Optimization-based ApproachAfter the presentation please try to give your opinion on the paper!
Presenter: Yunfeng
Minutes:
12th June: Lagrangian fluid simulation with continuous convolutions
19th June: Unpaired Motion Style Transfer from video to animation
26 June: Learning to Measure the Static Friction Coefficient in Cloth Contact
Learning to Measure the Static Friction Coefficient in Cloth Contact
This research proposes a vision-based deep neural network for estimating cloth/substrate dry friction coefficient. It uses synthetic datasets to train the neural network model which, however, is capable of estimating dry friction coefficient of real cloth. This is realised by accurately recover the cloth dynamics related to the dry friction coefficient. Moreover, this research introduces Conditional Friction Model which is optimised for extracting the information related with dry friction coefficient.
3rd July: PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
Jialin presents:
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative ModelsThe back ground is to obtain HD images from low resolution. Pulse ensures the quality of the super resolution image while tradition methods lead to blurring, they only compare HR and LR images. Traditional MSE neglect detail such as texture so that they are smoothed out. To get rid it people increase distance between SR and HR or use perceptual loss.
This paper has new paradigm and use novel method including Gaussian domain search.
PULSE may illuminate some biases inherent in StyleGAN.
CVPR video/paper for discussion:
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
10th July: Dynamic Fluid Surface Reconstruction Using Deep Neural Network
Zheyan present:
Dynamic Fluid Surface Reconstruction Using Deep Neural NetworkCVPR video for discussion:
17th July: BSP-Net: Generating Compact Meshes via Binary Space Partitioning
Dody will present:
BSP-Net: Generating Compact Meshes via Binary Space PartitioningCVPR video/paper for discussion:
Learning Long-term Visual Dynamics, Xiaolong Wang.24th July: Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
Deshan presents:
Use the Force, Luke! Learning to Predict Physical Forces by Simulating EffectsLooking this video:
VIBE: Video Inference for Human Body Pose and Shape Estimation (CVPR 2020)07 August: Skeleton-Aware Networks for Deep Motion Retargeting
Feixiang presents:
Skeleton-Aware Networks for Deep Motion RetargetingLooking this video:
Self-supervised Learning of Interpretable Keypoints from Unlabelled Videos - CVPR 2020 oral
14th August: Contrastive Learning for Unpaired Image-to-Image Translation
21st August: Neural Cages for Detail-Preserving 3D Deformations
Zheyan presents:
Neural Cages for Detail-Preserving 3D Deformations4th September: RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
11th September: Graph Neural Networks in Particle Physics
Dody talked on graph_CNN and how this technique may help our research.
Graph Neural Networks in Particle Physics
18th September: Long-term Human Motion Prediction with Scene Context
Feixiang presents:
25th September: SRFlow: Learning the Super-Resolution Space with Normalizing Flow
9th October: Attention Is All You Need
16th Oct: learning mesh-based simulation with graph convolution
23th Oct : Scalable Graph Networks for Particle Simulations
Presenter: Dody
30th Oct.
Presenter: Feixiang
13th Nov
Ricardo Luna Gutierrez
presents
Information-theoretic Task Selection for Meta-Reinforcement Learning27 Nov
11th Dec Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
2021 meetings
15th January It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
22th January COVID-19 Cough Classification using Machine Learning and Global Smartphone Recordings
29th January Projective Dynamics with Contact
12th February Human Motion Classification Attack
Recent works on human motion classification attack
By He
26th February Lagrangian Neural Networks
By Dody
12th March HouseGAN
19th March GCN Semi-Supervised Classification with Graph Convolutional Networks
26th March Neural Temporal Adaptive Sampling and Denoising
16th April Semantic Photo Manipulation with a Generative Image Prior
Jialin present:
Semantic Photo Manipulation with a Generative Image Prior23th April Deep Learning in Audio Source Separation
Shaun present:
the field of my research with an overview of the problem and the current state of research surrounding it
30th April Efficient Transformers: A Survey
He Wang present:
Efficient Transformers: A Survey14th May Generative Layout Modeling using Constraint Graphs
Tom present:
Generative Layout Modeling using Constraint Graphs21th May Editing in Style: Uncovering the Local Semantics of GANs
Baiyi present:
Editing in Style: Uncovering the Local Semantics of GANs18th June Neural Operator For Parametric PDEs
Maria present:
27th Aug Machine learning–accelerated computational fluid dynamics
Zheyan present:
Machine learning–accelerated computational fluid dynamics3rd Sep Unsupervised Image Generation with Infinite Generative Adversarial Networks
10th Sep OptNet: Differentiable Optimization as a Layer in Neural Networks
12th Nov Neural Animation Layering for Synthesizing Martial Arts Movements
19th Nov Finite element with machine learning
zheyan present:
Finite element with machine learning
26th Nov DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks
3rd Dec Masked Autoencoders Are Scalable Vision Learners
Jiangbei present:
Masked Autoencoders Are Scalable Vision Learners2021 meetings
11th Feb ChoreoMaster: Choreography-Oriented Music-Driven Dance Synthesis
18th Feb Understanding and mitigating gradient pathologies in physics-informed neural networks
4th Mar Spectral images based environmental sound classification using CNN with meaningful data augmentation
11th Mar Analyzing Inverse Problems with Invertible Neural Networks
Mou Li present:
Analyzing Inverse Problems with Invertible Neural Networks27th May Image Classification using Graph Neural Network
Usman present:
17th June Prototypical contrast and reverse prediction: Unsupervised skeleton based action recognition
8th July Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction
Feixiang present:
Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction