Search Results for author: Matthias Kayser

Found 5 papers, 0 papers with code

SABER-6D: Shape Representation Based Implicit Object Pose Estimation

no code implementations11 Aug 2024 Shishir Reddy Vutukur, Mengkejiergeli Ba, Benjamin Busam, Matthias Kayser, Gurprit Singh

In this paper, we propose a novel encoder-decoder architecture, named SABER, to learn the 6D pose of the object in the embedding space by learning shape representation at a given pose.

Decoder Object +1

NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging

no code implementations CVPR 2023 Karim Guirguis, Johannes Meier, George Eskandar, Matthias Kayser, Bin Yang, Juergen Beyerer

Our contribution is three-fold: (1) we design a standalone lightweight generator with (2) class-wise heads (3) to generate and replay diverse instance-level base features to the RoI head while finetuning on the novel data.

Data-free Knowledge Distillation Few-Shot Object Detection +2

Towards Discriminative and Transferable One-Stage Few-Shot Object Detectors

no code implementations11 Oct 2022 Karim Guirguis, Mohamed Abdelsamad, George Eskandar, Ahmed Hendawy, Matthias Kayser, Bin Yang, Juergen Beyerer

We make the observation that the large gap in performance between two-stage and one-stage FSODs are mainly due to their weak discriminability, which is explained by a small post-fusion receptive field and a small number of foreground samples in the loss function.

Few-Shot Object Detection object-detection

CFA: Constraint-based Finetuning Approach for Generalized Few-Shot Object Detection

no code implementations11 Apr 2022 Karim Guirguis, Ahmed Hendawy, George Eskandar, Mohamed Abdelsamad, Matthias Kayser, Juergen Beyerer

In this work, we propose a constraint-based finetuning approach (CFA) to alleviate catastrophic forgetting, while achieving competitive results on the novel task without increasing the model capacity.

Continual Learning Few-Shot Object Detection +1

Few-Shot Object Detection in Unseen Domains

no code implementations11 Apr 2022 Karim Guirguis, George Eskandar, Matthias Kayser, Bin Yang, Juergen Beyerer

First, we leverage a meta-training paradigm, where we learn the domain shift on the base classes, then transfer the domain knowledge to the novel classes.

Domain Generalization Few-Shot Object Detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.