YOLOX: Exceeding YOLO Series in 2021

Megvii-BaseDetection/YOLOX 18 Jul 2021

In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX.

2D Object Detection Autonomous Driving

2,848
1.74 stars / hour

U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection

nadermx/backgroundremover 18 May 2020

In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD).

Image Classification RGB Salient Object Detection +2

246
1.35 stars / hour

Contextual Transformer Networks for Visual Recognition

JDAI-CV/CoTNet 26 Jul 2021

Such design fully capitalizes on the contextual information among input keys to guide the learning of dynamic attention matrix and thus strengthens the capacity of visual representation.

Instance Segmentation Object Detection +1

126
1.10 stars / hour

Open-World Entity Segmentation

dvlab-research/Entity 29 Jul 2021

We introduce a new image segmentation task, termed Entity Segmentation (ES) with the aim to segment all visual entities in an image without considering semantic category labels.

Image Manipulation Semantic Segmentation

70
1.05 stars / hour

Zero-Shot Text-to-Image Generation

borisdayma/dalle-mini 24 Feb 2021

Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset.

Zero-Shot Text-to-Image Generation

136
0.71 stars / hour

Epistemic Neural Networks

deepmind/enn 19 Jul 2021

All existing approaches to uncertainty modeling can be expressed as ENNs, and any ENN can be identified with a Bayesian neural network.

82
0.66 stars / hour

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

xinntao/Real-ESRGAN 22 Jul 2021

Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images.

Super-Resolution

245
0.55 stars / hour

Human Pose Regression with Residual Log-likelihood Estimation

Jeff-sjtu/res-loglikelihood-regression 23 Jul 2021

In light of this, we propose a novel regression paradigm with Residual Log-likelihood Estimation (RLE) to capture the underlying output distribution.

Multi-Person Pose Estimation

107
0.54 stars / hour

Rank & Sort Loss for Object Detection and Instance Segmentation

kemaloksuz/RankSortLoss 24 Jul 2021

RS Loss supervises the classifier, a sub-network of these methods, to rank each positive above all negatives as well as to sort positives among themselves with respect to (wrt.)

Instance Segmentation Object Detection +1

57
0.52 stars / hour

Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP

warmspringwinds/segmentation_in_style 26 Jul 2021

Derived regions are consistent across different images and coincide with human-defined semantic classes on some datasets.

Semantic Segmentation

51
0.47 stars / hour