activity
20152024
most citedFully Connected Deep Structured Networks

263 citations · 811 across the 52 of their papers we have counts for

collaborators
Showing 2018Show all

16 papers · 1 filter

cs.LG2018★ 10 cited

GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training

Mingchao Yu, Zhifeng Lin, Krishna Narra +6

Data parallelism can boost the training speed of convolutional neural networks (CNN), but could suffer from significant communication costs caused by gradient aggregation. To allev…

cs.CV2018

No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training Techniques

Tanmay Gupta, Alexander Schwing, Derek Hoiem

We show that for human-object interaction detection a relatively simple factorized model with appearance and layout encodings constructed from pre-trained object detectors outperfo…

cs.LG2018

Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training

Youjie Li, Mingchao Yu, Songze Li +3

Distributed training of deep nets is an important technique to address some of the present day computing challenges like memory consumption and computational demands. Classical dis…

cs.LG2018

Deep Structured Prediction with Nonlinear Output Transformations

Colin Graber, Ofer Meshi, Alexander Schwing

Deep structured models are widely used for tasks like semantic segmentation, where explicit correlations between variables provide important prior information which generally helps…

cs.CV2018

Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering

Medhini Narasimhan, Svetlana Lazebnik, Alexander G. Schwing

Accurately answering a question about a given image requires combining observations with general knowledge. While this is effortless for humans, reasoning with general knowledge re…

cs.CV2018

Structural Consistency and Controllability for Diverse Colorization

Safa Messaoud, David Forsyth, Alexander G. Schwing

Colorizing a given gray-level image is an important task in the media and advertising industry. Due to the ambiguity inherent to colorization (many shades are often plausible), rec…