Article

Parameter-Efficient Domain Adaptation for Edge Detectors: A Comparative Study of Colormap Models and LoRA

2024-09-02

Abstract excerpt

<title>Abstract</title> <p>Edge Detectors are one of the most fundamental tools in Computer Vision applications. Using deep learning, state-of-the-art (SOTA) models can produce sharp, fine edges, mirroring human-level performance. However, most of these SOTA models are trained solely on color images. We experimentally determined that this limited data severely hinders performance on images from other domain space...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 665dc1f4-3033-5e1e-a772-77e9e7488d57
DOI: 10.21203/rs.3.rs-4870776/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Parameter-Efficient Domain Adaptation for Edge Detectors: A Comparative Study of Colormap Models and LoRADOI 10.21203/rs.3.rs-4870776/v1Read

A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image EnhancementSemantic proximity Read

Biological convolutions improve DNN robustness to noise and generalisationSemantic proximity Read

Automatic Classification and Style Analysis ofLandscape Architecture Images Based on DeepLearningSemantic proximity Read

Teaching deep networks to see shape: Lessons from a simplified visual worldSemantic proximity Read

MS-CANet: Multi-Scale Subtraction Network with Coordinate Attention for Retinal Vessel SegmentationSemantic proximity Read

Benchmarking and Stress-Testing Off-the-Shelf Vision Embeddings for Surface Re-Identification in Open-Source IntelligenceSemantic proximity Read

Symbiotic Convolution Block (SCB): An Implicit Feature Recalibration without Attention-Mechanism for Efficient CNNs in Image ClassificationSemantic proximity Read

Advancing Arecanut Quality Grading: A Comparative Analysis of YOLO Models with Hyperparameter OptimizationSemantic proximity Read

Contrast invariant tuning in human perception of image contentSemantic proximity Read

The re-identification generative adversarial network for image super-resolutionSemantic proximity Read

Leveraging synthetic data produced from museum specimens to train adaptable species classification modelsSemantic proximity Read

Noise robust neural network architectureSemantic proximity Read