Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation

yyliu01/rpl 26 Nov 2022

Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes.

 Ranked #1 on Anomaly Detection on Road Anomaly (using extra training data)

Anomaly Detection Contrastive Learning +3

45
0.24 stars / hour

Tutel: Adaptive Mixture-of-Experts at Scale

microsoft/tutel 7 Jun 2022

On effectiveness, the SwinV2-MoE model achieves superior accuracy in both pre-training and down-stream computer vision tasks such as COCO object detection than the counterpart dense model, indicating the readiness of Tutel for end-to-end real-world model training and inference.

Object Detection

326
0.23 stars / hour

Learning the Beauty in Songs: Neural Singing Voice Beautifier

MoonInTheRiver/DiffSinger ACL 2022

Furthermore, we propose a latent-mapping algorithm in the latent space to convert the amateur vocal tone to the professional one.

Dynamic Time Warping

718
0.22 stars / hour

Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese

ofa-sys/chinese-clip 2 Nov 2022

The tremendous success of CLIP (Radford et al., 2021) has promoted the research and application of contrastive learning for vision-language pretraining.

Contrastive Learning Image Classification +9

356
0.22 stars / hour

MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition

facebookresearch/memvit CVPR 2022

Instead of trying to process more frames at once like most existing methods, we propose to process videos in an online fashion and cache "memory" at each iteration.

Ranked #2 on Action Anticipation on EPIC-KITCHENS-100 (using extra training data)

Action Anticipation Action Classification +2

66
0.22 stars / hour

BotSIM: An End-to-End Bot Simulation Toolkit for Commercial Task-Oriented Dialog Systems

salesforce/botsim 29 Nov 2022

BotSIM adopts a layered design comprising the infrastructure layer, the adaptor layer and the application layer.

64
0.22 stars / hour
41
0.21 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

73
0.21 stars / hour

TorchPRISM: Principal Image Sections Mapping, a novel method for Convolutional Neural Network features visualization

szandala/TorchPRISM 27 Jan 2021

In this paper we introduce a tool called Principal Image Sections Mapping - PRISM, dedicated for PyTorch, but can be easily ported to other deep learning frameworks.

Explainable artificial intelligence Interpretable Machine Learning +1

38
0.21 stars / hour

Fast Sampling of Diffusion Models with Exponential Integrator

shivamshrirao/diffusers 29 Apr 2022

Our goal is to develop a fast sampling method for DMs with a much less number of steps while retaining high sample quality.

1,079
0.20 stars / hour