Methods > Computer Vision > Backbone Architectures

Spatial Broadcast Decoder is an architecture that aims to improve disentangling, reconstruction accuracy, and generalization to held-out regions in data space. It provides a particularly dramatic benefit when applied to datasets with small objects.

Source: Watters et al.

Image source: Watters et al.

Source: Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs

Latest Papers

PAPER DATE
Posting Bot Detection on Blockchain-based Social Media Platform using Machine Learning Techniques
Taehyun KimHyomin ShinHyung Ju HwangSeungwon Jeong
2020-08-28
Superpixel Segmentation via Convolutional Neural Networks with Regularized Information Maximization
| Teppei Suzuki
2020-02-17
f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation
| Konstantin SofiiukIlia PetrovOlga BarinovaAnton Konushin
2020-01-28
Sequence Labeling Approach to the Task of Sentence Boundary Detection
| The Anh Le
2020-01-20
An Approach for Time-aware Domain-based Social Influence Prediction
Bilal Abu-SalihKit Yan ChanOmar Al-KadiMarwan Al-TawilPornpit WongthongthamTomayess IssaHeba SaadehMalak Al-HassanBushra BremieAbdulaziz Albahlal
2020-01-19
Deep Snake for Real-Time Instance Segmentation
| Sida PengWen JiangHuaijin PiXiuli LiHujun BaoXiaowei Zhou
2020-01-06
GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
| Martin EngelckeAdam R. KosiorekOiwi Parker JonesIngmar Posner
2019-07-30
Omnidirectional Scene Text Detection with Sequential-free Box Discretization
| Yuliang LiuSheng ZhangLianwen JinLele XieYaqiang WuZhepeng Wang
2019-06-06
Object Instance Annotation With Deep Extreme Level Set Evolution
| Zian Wang David Acuna Huan Ling Amlan Kar Sanja Fidler
2019-06-01
Dynamic Feature Fusion for Semantic Edge Detection
| Yuan HuYunpeng ChenXiang LiJiashi Feng
2019-02-25
MONet: Unsupervised Scene Decomposition and Representation
| Christopher P. BurgessLoic MattheyNicholas WattersRishabh KabraIrina HigginsMatt BotvinickAlexander Lerchner
2019-01-22
Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
| Nicholas WattersLoic MattheyChristopher P. BurgessAlexander Lerchner
2019-01-21

Components

COMPONENT TYPE
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories