GitHub

AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer

This repository contains the official PyTorch implementation for the ECCV2024 paper "AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer". AdaLog adapts the ...
GitHub

GitHub - zuraiqi/neural-organ-transplant: Checkpoint-based modular adaptation for ...

Checkpoint-based modular adaptation for transformers. Train layer subsets once, deploy anywhere. 2.8-38.6× better than LoRA, 2-28× faster training. - zuraiqi/neural-organ-transplant ...
IEEE

An Empirical Study of Training Self-Supervised Vision Transformers

Abstract: This paper does not describe a novel method. Instead, it studies a straightforward, incremental, yet must-know baseline given the recent progress in computer vision: self-supervised learning ...
IEEE

Pair-VPR: Place-Aware Pre-Training and Contrastive Pair Classification for Visual Place ...

Abstract: In this work we propose a novel joint training method for Visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking. The pair ...