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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “YOLOv4”

Automatic Bounding Box Annotation with Small Training Data Sets for Industrial Manufacturingcs.CV

New methods detect objects in industrial settings with little training data.

problem Lack of training data limits object detection in industrial settings.

method Adapted Faster R-CNN and Scaled Yolov4-p5 architectures for small training data.

result Both models can distinguish unknown objects from homogeneous backgrounds.

object detection Faster R-CNN Yolov4-p5 industrial manufacturing small training data

2022-06-01abs ↗pdf ↗

Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measurecs.CV

Efficiently explains model outputs using HSIC, a dependence measure.

problem Efficiently explain model outputs for various architectures.

method HSIC, RKHS, Reproducing Kernel Hilbert Spaces, black-box attribution.

result Up to 8 times faster than previous methods while maintaining fidelity.

HSIC Reproducing Kernel Hilbert Spaces black-box attribution object detection YOLOv4

2022-06-13abs ↗pdf ↗

Mish: A Self Regularized Non-Monotonic Activation Functioncs.LG

We propose $\textit{Mish}$ , a novel self-regularized non-monotonic activation function which can be mathematically defined as: $f(x)=x\tanh(softplus(x))$ . As activation functions play a crucial role in the performance and training dynamics in neural networks, we validated experimentally on several well-known benchmarks…

2019-08-23abs ↗pdf ↗