Trending Research

LambdaNetworks: Modeling long-range Interactions without Attention

ICLR 2021 lucidrains/lambda-networks

We present a general framework for capturing long-range interactions between an input and structured contextual information (e. g. a pixel surrounded by other pixels).

IMAGE CLASSIFICATION INSTANCE SEGMENTATION OBJECT DETECTION SCENE SEGMENTATION

566
4.76 stars / hour

AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients

15 Oct 2020juntang-zhuang/Adabelief-Optimizer

Viewing the exponential moving average (EMA) of the noisy gradient as the prediction of the gradient at the next time step, if the observed gradient greatly deviates from the prediction, we distrust the current observation and take a small step; if the observed gradient is close to the prediction, we trust it and take a large step.

IMAGE CLASSIFICATION LANGUAGE MODELLING

453
3.00 stars / hour

Neural circuit policies enabling auditable autonomy

13 Oct 2020mlech26l/keras-ncp

A central goal of artificial intelligence in high-stakes decision-making applications is to design a single algorithm that simultaneously expresses generalizability by learning coherent representations of their world and interpretable explanations of its dynamics.

AUTONOMOUS VEHICLES DECISION MAKING

239
1.05 stars / hour

NeRF++: Analyzing and Improving Neural Radiance Fields

15 Oct 2020Kai-46/nerfplusplus

Neural Radiance Fields (NeRF) achieve impressive view synthesis results for a variety of capture settings, including 360 capture of bounded scenes and forward-facing capture of bounded and unbounded scenes.

116
0.59 stars / hour

Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Reconstruction

ICLR 2021 AutodeskAILab/Fusion360GalleryDataset

We provide a dataset of 8, 625 designs, comprising sequential sketch and extrude modeling operations, together with a complementary environment called the Fusion 360 Gym, to assist with performing CAD reconstruction.

57
0.59 stars / hour

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

ICLR 2021 lucidrains/vit-pytorch

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited.

 Ranked #1 on Image Classification on CIFAR-10 (using extra training data)

FINE-GRAINED IMAGE CLASSIFICATION

725
0.48 stars / hour

Flow-edge Guided Video Completion

ECCV 2020 vt-vl-lab/FGVC

We present a new flow-based video completion algorithm.

797
0.40 stars / hour

A Survey of Knowledge-Enhanced Text Generation

9 Oct 2020wyu97/KENLG-Reading

To address this issue, researchers have considered incorporating various forms of knowledge beyond the input text into the generation models.

TEXT GENERATION

65
0.40 stars / hour