IEEE

JOANet: An Integrated Joint Optimization Architecture Making Medical Image Segmentation Really Helped by Super-Resolution Pre-Processing

Abstract: Conventional computer vision pipelines typically treat low-level enhancement and high-level semantic tasks as isolated processes, focusing on optimizing enhancement for perceptual quality ...
GitHub

Gemma Multimodal Fine-Tuner

Loss curve. Attention heatmap. Gradient signal strength. Memory pressure. Token-by-token predictions — all updating in real time, in your browser, while the model trains on your Mac. No TensorBoard.
IEEE

A Review of Classical Underwater Image Stitching Techniques and a Dynamic Matching Method for Low-Cost Underwater Robotic Platforms

Abstract: Underwater image stitching is a fundamental technology for marine environmental perception and underwater robotic vision, particularly for low-cost and micro-sized systems operating under ...
GitHub

Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention (CVPR 2020, Oral)

PyTorch implementation of the model presented in "Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention" published ar CVPR 2020. Satellite image time series, ...