All you need is a good init
Paper
•
1511.06422
•
Published
•
1
Papers - Image - Datasets - ImageNet
-
-
Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
Paper • 2404.14507 • Published • 21 -
Efficient Transformer Encoders for Mask2Former-style models
Paper • 2404.15244 • Published • 1 -
Deep Residual Learning for Image Recognition
Paper • 1512.03385 • Published • 6 -
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 26 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 12 -
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
Paper • 2406.06525 • Published • 64 -
Diffusion Models Beat GANs on Image Synthesis
Paper • 2105.05233 • Published • 2 -
Classifier-Free Diffusion Guidance
Paper • 2207.12598 • Published • 2 -
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Paper • 1809.11096 • Published • 1 -
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
Paper • 1707.02968 • Published • 1 -
Data curation via joint example selection further accelerates multimodal learning
Paper • 2406.17711 • Published • 3 -
Fixup Initialization: Residual Learning Without Normalization
Paper • 1901.09321 • Published • 1 -
RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness
Paper • 2206.14502 • Published • 1 -
Randomized Autoregressive Visual Generation
Paper • 2411.00776 • Published • 17 -
SLIP: Self-supervision meets Language-Image Pre-training
Paper • 2112.12750 • Published • 1