1 code implementation • 5 Oct 2023 • Stefan Smeu, Elena Burceanu, Emanuela Haller, Andrei Liviu Nicolicioiu
Similar to works in out-of-distribution generalization, we propose to use the formalization of separating into semantic or content changes, that are relevant to our task, and style changes, that are irrelevant.
no code implementations • 21 Sep 2023 • Stefan Smeu, Elena Burceanu, Emanuela Haller, Andrei Liviu Nicolicioiu
Thus, we propose a method that starts with a pretrained embedding and a multi-env setup and manages to rank the features based on their environment-focus.
no code implementations • 15 Dec 2022 • Elena Burceanu, Marius Leordeanu
Our motivation for a spectral space-time clustering approach, unique in video semantic segmentation literature, is that such clustering is dedicated to preserving object consistency over time, which we evaluate using our novel segmentation consistency measure.
no code implementations • 6 Oct 2022 • Stefan Smeu, Elena Burceanu, Andrei Liviu Nicolicioiu, Emanuela Haller
We introduce a formalization and benchmark for the unsupervised anomaly detection task in the distribution-shift scenario.
1 code implementation • 30 Jun 2022 • Marius Dragoi, Elena Burceanu, Emanuela Haller, Andrei Manolache, Florin Brad
Analyzing the distribution shift of data is a growing research direction in nowadays Machine Learning (ML), leading to emerging new benchmarks that focus on providing a suitable scenario for studying the generalization properties of ML models.
Ranked #5 on Unsupervised Anomaly Detection on AnoShift
1 code implementation • 9 Dec 2021 • Florin Brad, Andrei Manolache, Elena Burceanu, Antonio Barbalau, Radu Ionescu, Marius Popescu
One of the main drivers of the recent advances in authorship verification is the PAN large-scale authorship dataset.
1 code implementation • NAACL 2021 • Andrei Manolache, Florin Brad, Elena Burceanu
Leveraging deep learning models for Anomaly Detection (AD) has seen widespread use in recent years due to superior performances over traditional methods.
Ranked #1 on Anomaly Detection on AG News
1 code implementation • 26 Mar 2021 • Emanuela Haller, Elena Burceanu, Marius Leordeanu
The human ability to synchronize the feedback from all their senses inspired recent works in multi-task and multi-modal learning.
1 code implementation • 27 Nov 2020 • Elena Burceanu
We propose an object tracking method, SFTrack++, that smoothly learns to preserve the tracked object consistency over space and time dimensions by taking a spectral clustering approach over the graph of pixels from the video, using a fast 3D filtering formulation for finding the principal eigenvector of this graph's adjacency matrix.
1 code implementation • 5 Jul 2019 • Elena Burceanu, Marius Leordeanu
Our method is based on the power iteration for finding the principal eigenvector of a matrix, which we prove is equivalent to performing a specific set of 3D convolutions in the space-time feature volume.
Ranked #45 on Semi-Supervised Video Object Segmentation on DAVIS 2016 (Jaccard (Mean) metric)
no code implementations • 5 Apr 2018 • Elena Burceanu, Marius Leordeanu
We address this challenge by proposing a deep neural network composed of different parts, which functions as a society of tracking parts.
no code implementations • 26 May 2017 • Elena Burceanu, Marius Leordeanu
They are classifiers that respond at different scales and locations.