On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Instance-Aware”

InstaNAS: Instance-aware Neural Architecture Searchcs.LG

InstaNAS searches for a distribution of architectures to improve performance and reduce latency.

problem Finding a single architecture that represents the whole dataset with high diversity and variety.

method InstaNAS uses a controller trained to search for a 'distribution of architectures' that assigns each input sample a domain expert architecture.

result InstaNAS achieves up to 48.8% latency reduction without compromising accuracy.

Neural Architecture Search Latency Reduction Instance-Aware MobileNetV2 Diverse Datasets

2018-11-26abs ↗pdf ↗

Dynamic Routing Networkscs.LG

DRNets dynamically route instances to efficient transformations.

problem High inference costs due to static model capacity.

method Dynamic Routing Networks (DRNets) with RouterNets for branch selection.

result DRNets reduce inference costs with comparable performance.

Dynamic Routing Networks Instance-aware Inference Efficient Inference RouterNets Gumbel-Softmax

2019-05-13abs ↗pdf ↗

InstaGAN: Instance-aware Image-to-Image Translationcs.LG

InstaGAN tackles image-to-image translation for images with multiple instances and significant shape changes.

problem Challenging cases, especially images with multiple target instances and significant shape changes.

method Instance-aware GAN (InstaGAN) that incorporates instance information and context preserving loss.

result Improves multi-instance transfiguration while maintaining permutation invariance of instances.

image-to-image translation multi-instance shape changes instance information context preserving loss

2018-12-28abs ↗pdf ↗

Self-PU: Self Boosted and Calibrated Positive-Unlabeled Trainingcs.LG

Self-PU combines self-training with PU learning for improved binary classification.

problem Binary classification from unlabeled data and few labeled positives.

method Integrates self-paced training, self-calibrated loss, and self-distillation.

result Significantly improved performance on Alzheimer's Disease classification.

PU learning self-training binary classification Alzheimer's Disease brain imaging

2020-06-22abs ↗pdf ↗