Trending Research

Consistent Instance False Positive Improves Fairness in Face Recognition

Tencent/TFace 10 Jun 2021

Then, an additional penalty term, which is in proportion to the ratio of instance FPR overall FPR, is introduced into the denominator of the softmax-based loss.

Face Recognition Fairness

67
0.50 stars / hour

CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation

microsoft/CoCosNet-v2 3 Dec 2020

We present the full-resolution correspondence learning for cross-domain images, which aids image translation.

Image-to-Image Translation Semantic correspondence

53
0.49 stars / hour

Towards Real-time and Light-weight Line Segment Detection

navervision/mlsd 1 Jun 2021

To maintain competitive performance with such a light-weight network, we present novel training schemes: Segments of Line segment (SoL) augmentation and geometric learning scheme.

Line Segment Detection

169
0.48 stars / hour

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations

wvangansbeke/Revisiting-Contrastive-SSL 10 Jun 2021

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection.

Instance Segmentation Object Detection +3

16
0.46 stars / hour

ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

yym6472/ConSERT 25 May 2021

Learning high-quality sentence representations benefits a wide range of natural language processing tasks.

Semantic Textual Similarity

117
0.41 stars / hour

3DB: A Framework for Debugging Computer Vision Models

3db/3db 7 Jun 2021

We introduce 3DB: an extendable, unified framework for testing and debugging vision models using photorealistic simulation.

50
0.41 stars / hour

AndroidEnv: A Reinforcement Learning Platform for Android

deepmind/android_env 27 May 2021

We introduce AndroidEnv, an open-source platform for Reinforcement Learning (RL) research built on top of the Android ecosystem.

639
0.40 stars / hour

SOLQ: Segmenting Objects by Learning Queries

megvii-research/SOLQ 4 Jun 2021

Moreover, the joint learning of unified query representation can greatly improve the detection performance of original DETR.

Instance Segmentation Object Detection +1

66
0.39 stars / hour

CAT: Cross Attention in Vision Transformer

linhezheng19/CAT 10 Jun 2021

In this paper, we propose a new attention mechanism in Transformer termed Cross Attention, which alternates attention inner the image patch instead of the whole image to capture local information and apply attention between image patches which are divided from single-channel feature maps capture global information.

Tokenization

24
0.39 stars / hour