Search Results for author: Jan Ernst

Found 9 papers, 1 papers with code

Quantization-Guided Training for Compact TinyML Models

no code implementations10 Mar 2021 Sedigh Ghamari, Koray Ozcan, Thu Dinh, Andrey Melnikov, Juan Carvajal, Jan Ernst, Sek Chai

We propose a Quantization Guided Training (QGT) method to guide DNN training towards optimized low-bit-precision targets and reach extreme compression levels below 8-bit precision.

Human Detection Quantization

Incremental Scene Synthesis

no code implementations NeurIPS 2019 Benjamin Planche, Xuejian Rong, Ziyan Wu, Srikrishna Karanam, Harald Kosch, YingLi Tian, Jan Ernst, Andreas Hutter

We present a method to incrementally generate complete 2D or 3D scenes with the following properties: (a) it is globally consistent at each step according to a learned scene prior, (b) real observations of a scene can be incorporated while observing global consistency, (c) unobserved regions can be hallucinated locally in consistence with previous observations, hallucinations and global priors, and (d) hallucinations are statistical in nature, i. e., different scenes can be generated from the same observations.

Autonomous Navigation

Tell Me Where to Look: Guided Attention Inference Network

2 code implementations CVPR 2018 Kunpeng Li, Ziyan Wu, Kuan-Chuan Peng, Jan Ernst, Yun Fu

Weakly supervised learning with only coarse labels can obtain visual explanations of deep neural network such as attention maps by back-propagating gradients.

Object Localization Semantic Segmentation

End-to-end learning of keypoint detector and descriptor for pose invariant 3D matching

no code implementations CVPR 2018 Georgios Georgakis, Srikrishna Karanam, Ziyan Wu, Jan Ernst, Jana Kosecka

Finding correspondences between images or 3D scans is at the heart of many computer vision and image retrieval applications and is often enabled by matching local keypoint descriptors.

Image Retrieval Keypoint Detection +1

Learning Compositional Visual Concepts with Mutual Consistency

no code implementations CVPR 2018 Yunye Gong, Srikrishna Karanam, Ziyan Wu, Kuan-Chuan Peng, Jan Ernst, Peter C. Doerschuk

Compositionality of semantic concepts in image synthesis and analysis is appealing as it can help in decomposing known and generatively recomposing unknown data.

Data Augmentation Face Verification +1

Weakly Supervised Summarization of Web Videos

no code implementations ICCV 2017 Rameswar Panda, Abir Das, Ziyan Wu, Jan Ernst, Amit K. Roy-Chowdhury

Casting the problem as a weakly supervised learning problem, we propose a flexible deep 3D CNN architecture to learn the notion of importance using only video-level annotation, and without any human-crafted training data.

Zero-Shot Deep Domain Adaptation

no code implementations ECCV 2018 Kuan-Chuan Peng, Ziyan Wu, Jan Ernst

Therefore, the source-domain task of interest solution (e. g. a classifier for classification tasks) which is jointly trained with the source-domain representation can be applicable to both the source and target representations.

Classification Domain Adaptation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.