IEEE

Mitigating Backdoor Attacks in Pre-Trained Encoders via Self-Supervised Knowledge Distillation

Abstract: Pre-trained encoders in computer vision have recently received great attention from both research and industry communities. Among others, a promising paradigm is to utilize self-supervised ...
IEEE

Dual Encoder-Based Dynamic-Channel Graph Convolutional Network With Edge Enhancement for Retinal Vessel Segmentation

Abstract: Retinal vessel segmentation with deep learning technology is a crucial auxiliary method for clinicians to diagnose fundus diseases. However, the deep learning approaches inevitably lose the ...
GitHub

A powerful MK8 map editor for creating and editing track models, objects, paths and animations.

Byaml editing (paths, area, clips, cameras, object placement, and map parameters). Intro camera auto keying tool. Collision exporting and importing. Bgenv lighting editing including loading/saving ...
GitHub

SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation

We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...