Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark

roboflow-ai/roboflow-100-benchmark 24 Nov 2022

The evaluation of object detection models is usually performed by optimizing a single metric, e. g. mAP, on a fixed set of datasets, e. g. Microsoft COCO and Pascal VOC.

2D object detection Image Retrieval +13

24
0.51 stars / hour
159
0.49 stars / hour

DiffusionDet: Diffusion Model for Object Detection

shoufachen/diffusiondet 17 Nov 2022

In inference, the model refines a set of randomly generated boxes to the output results in a progressive way.

Denoising object-detection +1

1,311
0.48 stars / hour

Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces

dome272/paella 14 Nov 2022

Conditional text-to-image generation has seen countless recent improvements in terms of quality, diversity and fidelity.

Conditional Image Generation Denoising +2

288
0.47 stars / hour

A Time Series is Worth 64 Words: Long-term Forecasting with Transformers

yuqinie98/patchtst 27 Nov 2022

Our channel-independent patch time series Transformer (PatchTST) can improve the long-term forecasting accuracy significantly when compared with that of SOTA Transformer-based models.

Multivariate Time Series Forecasting Representation Learning

13
0.46 stars / hour

Medical Image Segmentation Review: The success of U-Net

nitr098/awesome-u-net 27 Nov 2022

U-Net is the most widespread image segmentation architecture due to its flexibility, optimized modular design, and success in all medical image modalities.

Image Segmentation Medical Image Segmentation +1

16
0.46 stars / hour

SinDiffusion: Learning a Diffusion Model from a Single Natural Image

weilunwang/sindiffusion 22 Nov 2022

We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image.

Denoising Image Generation +1

107
0.45 stars / hour

VeLO: Training Versatile Learned Optimizers by Scaling Up

google/learned_optimization 17 Nov 2022

While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers.

447
0.45 stars / hour

A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases

google/learned_optimization 22 Sep 2022

We apply the resulting learned optimizer to a variety of neural network training tasks, where it outperforms the current state of the art learned optimizer -- at matched optimizer computational overhead -- with regard to optimization performance and meta-training speed, and is capable of generalization to tasks far different from those it was meta-trained on.

Inductive Bias

447
0.44 stars / hour

DeepPrivacy2: Towards Realistic Full-Body Anonymization

hukkelas/deep_privacy2 17 Nov 2022

Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures.

Face Anonymization

61
0.43 stars / hour