eomt

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).

TensorRT in Practice: Model Conversion, Extension, and Advanced Inference Optimization

Hugging Face Object Detection, Instance Segmentation, Semantic Segmentation, Panoptic Segmentation in PyTorch Fine-tuning.

Graph-Guided Token Merging (G2TM) is a lightweight one-shot module designed to eliminate redundant tokens in the early layers of a ViT-based models, through graph theory. It performs a single token merging step after a shallow attention block, enabling all subsequent layers to operate on a compact token set.

Anomaly segmentation for autonomous driving: ERFNet vs. EoMT with MSP/MaxLogit/MaxEntropy/RbA on SMIYC & Fishyscapes

Anomaly segmentation for autonomous-driving scenes using ERFNet and EoMT, with fine-tuning, post-hoc baselines, and temperature scaling.

A train-free CorrCLIP research and engineering workspace with VOC21 reproduction, Focused Residual Self-Calibration, EoMT-based system boosting, and full qualitative/mechanism visualization tooling.