activity
20172023
most citedSTN-OCR: A single Neural Network for Text Detection and Text Recognition

51 citations · 205 across the 19 of their papers we have counts for

collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG20232 cited

Supervised Knowledge May Hurt Novel Class Discovery Performance

Ziyun Li, Jona Otholt, Ben Dai +3

Novel class discovery (NCD) aims to infer novel categories in an unlabeled dataset by leveraging prior knowledge of a labeled set comprising disjoint but related classes. Given tha…

cs.LG202112 cited

BoolNet: Minimizing The Energy Consumption of Binary Neural Networks

Nianhui Guo, Joseph Bethge, Haojin Yang +4

Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts. However, the accuracy gains are often…

cs.LG2021

Evaluating Post-Training Compression in GANs using Locality-Sensitive Hashing

Gonçalo Mordido, Haojin Yang, Christoph Meinel

The analysis of the compression effects in generative adversarial networks (GANs) after training, i.e. without any fine-tuning, remains an unstudied, albeit important, topic with t…

cs.LG2020

microbatchGAN: Stimulating Diversity with Multi-Adversarial Discrimination

Gonçalo Mordido, Haojin Yang, Christoph Meinel

We propose to tackle the mode collapse problem in generative adversarial networks (GANs) by using multiple discriminators and assigning a different portion of each minibatch, calle…

cs.LG2020

MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?

Joseph Bethge, Christian Bartz, Haojin Yang +2

Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. They have reduced model sizes and al…

cs.LG2019

K-Metamodes: frequency- and ensemble-based distributed k-modes clustering for security analytics

Andrey Sapegin, Christoph Meinel

Nowadays processing of Big Security Data, such as log messages, is commonly used for intrusion detection purposed. Its heterogeneous nature, as well as combination of numerical and…