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.

VISUAL QUESTION ANSWERING

2,105
2.02 stars / hour

Pythia v0.1: the Winning Entry to the VQA Challenge 2018

26 Jul 2018facebookresearch/pythia

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%.

VISUAL QUESTION ANSWERING

2,105
2.02 stars / hour

Augmented Neural ODEs

2 Apr 2019EmilienDupont/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.

98
1.48 stars / hour

Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks

23 May 2019implus/PytorchInsight

The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features.

70
1.11 stars / hour

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.

70
1.11 stars / hour

Learning to Prove Theorems via Interacting with Proof Assistants

21 May 2019princeton-vl/CoqGym

Proof assistants offer a formalism that resembles human mathematical reasoning, representing theorems in higher-order logic and proofs as high-level tactics.

24
0.58 stars / hour

Objects as Points

16 Apr 2019xingyizhou/CenterNet

We model an object as a single point --- the center point of its bounding box.

KEYPOINT DETECTION REAL-TIME OBJECT DETECTION

1,285
0.45 stars / hour

ERNIE: Enhanced Language Representation with Informative Entities

17 May 2019thunlp/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.

KNOWLEDGE GRAPHS

161
0.44 stars / hour

Learning What and Where to Transfer

15 May 2019alinlab/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.

META-LEARNING TRANSFER LEARNING

20
0.24 stars / hour

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.

CONDITIONAL IMAGE GENERATION

21
0.24 stars / hour