Trending Research
Towards VQA Models That Can Read
CVPR 2019
• facebookresearch/pythia
• 
We show that LoRRA outperforms existing state-of-the-art VQA models on our TextVQA dataset.
#3 best model for
Visual Question Answering
on VQA v2
Pythia v0.1: the Winning Entry to the VQA Challenge 2018
We demonstrate that by making subtle but important changes to the model architecture and the learning rate schedule, fine-tuning image features, and adding data augmentation, we can significantly improve the performance of the up-down model on VQA v2. 0 dataset -- from 65. 67% to 70. 22%.
#2 best model for
Visual Question Answering
on VQA v2
Augmented Neural ODEs
• EmilienDupont/augmented-neural-odes
• 
We show that Neural Ordinary Differential Equations (ODEs) learn representations that preserve the topology of the input space and prove that this implies the existence of functions Neural ODEs cannot represent.
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features.
Selective Kernel Networks
CVPR 2019
• implus/PytorchInsight
•
A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches.
Learning to Prove Theorems via Interacting with Proof Assistants
Proof assistants offer a formalism that resembles human mathematical reasoning, representing theorems in higher-order logic and proofs as high-level tactics.
Objects as Points
We model an object as a single point --- the center point of its bounding box.
SOTA for Real-Time Object Detection on COCO
ERNIE: Enhanced Language Representation with Informative Entities
• thunlp/ERNIE
•
Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently improve the performance of various NLP tasks.
Learning What and Where to Transfer
• alinlab/L2T-ww
•
To address the issue, we propose a novel transfer learning approach based on meta-learning that can automatically learn what knowledge to transfer from the source network to where in the target network.
Self-Attention Generative Adversarial Networks
arXiv 2018
• sdoria/SimpleSelfAttention
•
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks.
#4 best model for
Conditional Image Generation
on ImageNet 128x128