SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization (Paper Explained)

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization (Paper Explained)
Share:

Download MP3


Similar Tracks

NVAE: A Deep Hierarchical Variational Autoencoder (Paper Explained) Yannic Kilcher
SupSup: Supermasks in Superposition (Paper Explained) Yannic Kilcher
RepNet: Counting Out Time - Class Agnostic Video Repetition Counting in the Wild (Paper Explained) Yannic Kilcher
Visualizing transformers and attention | Talk for TNG Big Tech Day '24 Grant Sanderson
Neural Architecture Search without Training (Paper Explained) Yannic Kilcher
Object-Centric Learning with Slot Attention (Paper Explained) Yannic Kilcher
Deep Ensembles: A Loss Landscape Perspective (Paper Explained) Yannic Kilcher
Math's Fundamental Flaw Veritasium
Transformers (how LLMs work) explained visually | DL5 3Blue1Brown
FHI-aims Webinar: Heat and Charge Transport in Solids, Talk by Christian Carbogno MS1P e.V.
LambdaNetworks: Modeling long-range Interactions without Attention (Paper Explained) Yannic Kilcher
How I Read a Paper: Facebook's DETR (Video Tutorial) Yannic Kilcher
SynFlow: Pruning neural networks without any data by iteratively conserving synaptic flow Yannic Kilcher
Discovering Symbolic Models from Deep Learning with Inductive Biases (Paper Explained) Yannic Kilcher
DETR: End-to-End Object Detection with Transformers (Paper Explained) Yannic Kilcher
Robot Framework Tutorial For Beginners | Robot Framework With Python | Intellipaat Intellipaat
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation (Paper Explained) Yannic Kilcher
Big Self-Supervised Models are Strong Semi-Supervised Learners (Paper Explained) Yannic Kilcher
How do Graphics Cards Work? Exploring GPU Architecture Branch Education
Linformer: Self-Attention with Linear Complexity (Paper Explained) Yannic Kilcher