Machine Learning Research Flashcards

Machine Learning Research Flashcards is a collection of flashcards associated with scientific research papers in the field of machine learning. The flashcards are best used with Anki, a spaced repetition system.

53 papers • 252 cards

3D Gaussian Splatting for Real-Time Radiance Field Rendering

A Simple Framework for Contrastive Learning of Visual Representations

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Anchor Pruning for Object Detection

Attention Is All You Need

Auto-Encoding Variational Bayes

AutoSlim: Towards One-Shot Architecture Search for Channel Numbers

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Deep Reinforcement Learning with Double Q-learning

Denoising Diffusion Probabilistic Models

DETR: End-to-End Object Detection with Transformers

Distilling the Knowledge in a Neural Network

DUSt3R: Geometric 3D Vision Made Easy

Extracting and Composing Robust Features with Denoising Autoencoders

FaceNet: A Unified Embedding for Face Recognition and Clustering

Focal Loss for Dense Object Detection

GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

High-Resolution Image Synthesis with Latent Diffusion Models

Instant Neural Graphics Primitives with a Multiresolution Hash Encoding

Learned Thresholds Token Merging and Pruning for Vision Transformers

Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

Learning Transferable Visual Models From Natural Language Supervision

LoRA: Low-Rank Adaptation of Large Language Models

Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

Mixture-of-Experts with Expert Choice Routing

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Multi-Scale Context Aggregation by Dilated Convolutions

Multiple Choice Learning: Learning to Produce Multiple Structured Outputs

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

On Network Design Spaces for Visual Recognition

Once-for-All: Train One Network and Specialize it for Efficient Deployment

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

PaLM-E: An Embodied Multimodal Language Model

Playing Atari with Deep Reinforcement Learning

Proximal Policy Optimization Algorithms

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

RT-1: Robotics Transformer for Real-World Control at Scale

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Segment Anything

Slimmable Neural Networks

Squeeze-and-Excitation Networks

SSD: Single Shot MultiBox Detector

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

Token Merging: Your ViT But Faster

Understanding the Effective Receptive Field in Deep Convolutional Neural Networks

Universally Slimmable Networks and Improved Training Techniques

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation