3 papers
cs.CV2025
Ternarization of Vision Language Models for use on edge devices
Ben Crulis, Cyril De Runz, Barthelemy Serres +1
We propose a process to compress a pre-trained Vision Language Model into a ternary version of itself instead of training a ternary model from scratch. A new initialization scheme…
cs.CV2024
Few-shot target-driven instance detection based on open-vocabulary object detection models
Ben Crulis, Barthelemy Serres, Cyril De Runz +1
Current large open vision models could be useful for one and few-shot object recognition. Nevertheless, gradient-based re-training solutions are costly. On the other hand, open-voc…
cs.LG2024
An experimental comparative study of backpropagation and alternatives for training binary neural networks for image classification
Ben Crulis, Barthelemy Serres, Cyril de Runz +1
Current artificial neural networks are trained with parameters encoded as floating point numbers that occupy lots of memory space at inference time. Due to the increase in the size…