4 papers
DAC-Loop: Distillation-Aware Compression for Remote Sensing CNN
Rico Staedeli, Lorena Raichle, Konstantinos Tzevelekakis +2
While large-scale models achieve strong results in remote sensing scene classification, deploying them on edge devices remains difficult due to limited compute, memory, and energy…
WeightCLIP: Aligning Datasets and Models for Weight Space Learning
Aron Asefaw, Konstantinos Tzevelekakis, Damian Falk +2
Weight space learning aims to learn representations of neural network (NN) weights, enabling different downstream tasks. Existing approaches show promising performance, but lacking…
Learning Model Representations Using Publicly Available Model Hubs
Damian Falk, Konstantin Schürholt, Konstantinos Tzevelekakis +2
The weights of neural networks have emerged as a novel data modality, giving rise to the field of weight space learning. A central challenge in this area is that learning meaningfu…
Sun Off, Lights On: Photorealistic Monocular Nighttime Simulation for Robust Semantic Perception
Konstantinos Tzevelekakis, Shutong Zhang, Luc Van Gool +1
Nighttime scenes are hard to semantically perceive with learned models and annotate for humans. Thus, realistic synthetic nighttime data become all the more important for learning…