Pen and Paper Exercises in Machine Learning

michaelgutmann/ml-pen-and-paper-exercises 27 Jun 2022

This is a collection of (mostly) pen-and-paper exercises in machine learning.

Variational Inference

2.96 stars / hour

Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation

Vegetebird/StridedTransformer-Pose3D 26 Mar 2021

The modified VTE is termed as Strided Transformer Encoder (STE), which is built upon the outputs of VTE.

Monocular 3D Human Pose Estimation

0.89 stars / hour

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

lucidrains/parti-pytorch 22 Jun 2022

We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compositions and world knowledge.

Machine Translation Text to image generation +1

0.88 stars / hour

Multi-Graph Fusion Networks for Urban Region Embedding

wushangbin/mgfn 24 Jan 2022

Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks.

Crime Prediction

0.74 stars / hour

EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

tjiiv-cprg/epro-pnp CVPR 2022

The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution.

3D Object Detection 6D Pose Estimation using RGB +1

0.69 stars / hour

Ivy: Templated Deep Learning for Inter-Framework Portability

ivy-dl/ivy 4 Feb 2021

We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks.

0.61 stars / hour

HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction

zhenpeiyang/hm3d-abo 24 Jun 2022

Reconstructing 3D objects is an important computer vision task that has wide application in AR/VR.

3D Reconstruction Novel View Synthesis +1

0.59 stars / hour

OmniXAI: A Library for Explainable AI

salesforce/omnixai 1 Jun 2022

We introduce OmniXAI (short for Omni eXplainable AI), an open-source Python library of eXplainable AI (XAI), which offers omni-way explainable AI capabilities and various interpretable machine learning techniques to address the pain points of understanding and interpreting the decisions made by machine learning (ML) in practice.

Counterfactual Explanation Decision Making +3

0.53 stars / hour

Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning

tianyu0207/RTFM ICCV 2021

To address this issue, we introduce a novel and theoretically sound method, named Robust Temporal Feature Magnitude learning (RTFM), which trains a feature magnitude learning function to effectively recognise the positive instances, substantially improving the robustness of the MIL approach to the negative instances from abnormal videos.

Anomaly Detection In Surveillance Videos Contrastive Learning +1

0.49 stars / hour

Matryoshka Representations for Adaptive Deployment

raivnlab/mrl 26 May 2022

The flexibility within the learned Matryoshka Representations offer: (a) up to 14x smaller embedding size for ImageNet-1K classification at the same level of accuracy; (b) up to 14x real-world speed-ups for large-scale retrieval on ImageNet-1K and 4K; and (c) up to 2% accuracy improvements for long-tail few-shot classification, all while being as robust as the original representations.

Representation Learning

0.49 stars / hour