1 code implementation • 13 Feb 2024 • Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip H. S. Torr, Ozan Sener, Puneet K. Dokania
Our investigation is both surprising and alarming as it questions our understanding of how to effectively design and train models that require efficient continual representation learning, and necessitates a principled reinvestigation of the widely explored problem formulation itself.
no code implementations • 30 Aug 2023 • Ozan Sener, Vladlen Koltun
To solve the proposed optimization problem, we demonstrate an exciting connection to rate-distortion theory and utilize its tools to design an efficient method.
1 code implementation • ICCV 2023 • Yeti Z. Gurbuz, Ozan Sener, A. Aydin Alatan
GSP improves GAP with two distinct abilities: i) the ability to choose a subset of semantic entities, effectively learning to ignore nuisance information, and ii) learning the weights corresponding to the importance of each entity.
no code implementations • 26 Jul 2023 • Antoine Wehenkel, Jens Behrmann, Andrew C. Miller, Guillermo Sapiro, Ozan Sener, Marco Cuturi, Jörn-Henrik Jacobsen
Over the past decades, hemodynamics simulators have steadily evolved and have become tools of choice for studying cardiovascular systems in-silico.
1 code implementation • 16 May 2023 • Ameya Prabhu, Zhipeng Cai, Puneet Dokania, Philip Torr, Vladlen Koltun, Ozan Sener
In this paper, we target such applications, investigating the online continual learning problem under relaxed storage constraints and limited computational budgets.
1 code implementation • 27 Nov 2022 • Katelyn Gao, Ozan Sener
Gaussian smoothing (GS) is a derivative-free optimization (DFO) algorithm that estimates the gradient of an objective using perturbations of the current parameters sampled from a standard normal distribution.
no code implementations • 12 Oct 2022 • Zhipeng Cai, Vladlen Koltun, Ozan Sener
The typical approach to address information retention (the ability to retain previous knowledge) is keeping a replay buffer of a fixed size and computing gradients using a mixture of new data and the replay buffer.
2 code implementations • CVPR 2020 • John Lambert, Zhuang Liu, Ozan Sener, James Hays, Vladlen Koltun
We adopt zero-shot cross-dataset transfer as a benchmark to systematically evaluate a model's robustness and show that MSeg training yields substantially more robust models in comparison to training on individual datasets or naive mixing of datasets without the presented contributions.
Ranked #8 on Semantic Segmentation on ScanNetV2
1 code implementation • ICCV 2021 • Zhipeng Cai, Ozan Sener, Vladlen Koltun
We argue that "online" continual learning, where data is a single continuous stream without task boundaries, enables evaluating both information retention and online learning efficacy.
1 code implementation • NeurIPS 2020 • Katelyn Gao, Ozan Sener
By searching for shared inductive biases across tasks, meta-learning promises to accelerate learning on novel tasks, but with the cost of solving a complex bilevel optimization problem.
1 code implementation • 18 Jul 2020 • Hexiang Hu, Ozan Sener, Fei Sha, Vladlen Koltun
Collectively, the POLL problem setting, the Firehose datasets, and the ConGraD algorithm enable a complete benchmark for reproducible research on web-scale continual learning.
1 code implementation • NeurIPS 2020 • Umut Şimşekli, Ozan Sener, George Deligiannidis, Murat A. Erdogdu
Despite its success in a wide range of applications, characterizing the generalization properties of stochastic gradient descent (SGD) in non-convex deep learning problems is still an important challenge.
1 code implementation • ICLR 2020 • Ozan Sener, Vladlen Koltun
In other words, we jointly learn the manifold and optimize the function.
5 code implementations • NeurIPS 2018 • Ozan Sener, Vladlen Koltun
These algorithms are not directly applicable to large-scale learning problems since they scale poorly with the dimensionality of the gradients and the number of tasks.
Ranked #1 on Multi-Task Learning on CelebA
2 code implementations • NeurIPS 2018 • Riccardo Volpi, Hongseok Namkoong, Ozan Sener, John Duchi, Vittorio Murino, Silvio Savarese
Only using training data from a single source distribution, we propose an iterative procedure that augments the dataset with examples from a fictitious target domain that is "hard" under the current model.
1 code implementation • CVPR 2018 • John Lambert, Ozan Sener, Silvio Savarese
This is what the Learning Under Privileged Information (LUPI) paradigm endeavors to model by utilizing extra knowledge only available during training.
no code implementations • NeurIPS 2016 • Ozan Sener, Hyun Oh Song, Ashutosh Saxena, Silvio Savarese
Supervised learning with large scale labelled datasets and deep layered models has caused a paradigm shift in diverse areas in learning and recognition.
no code implementations • CVPR 2016 • Iro Armeni, Ozan Sener, Amir R. Zamir, Helen Jiang, Ioannis Brilakis, Martin Fischer, Silvio Savarese
In this paper, we propose a method for semantic parsing the 3D point cloud of an entire building using a hierarchical approach: first, the raw data is parsed into semantically meaningful spaces (e. g. rooms, etc) that are aligned into a canonical reference coordinate system.
no code implementations • 11 May 2016 • Ozan Sener, Amir Roshan Zamir, Chenxia Wu, Silvio Savarese, Ashutosh Saxena
Our method can also provide a textual description for each of the identified semantic steps and video segments.
no code implementations • 11 Mar 2016 • Chenxia Wu, Jiemi Zhang, Ozan Sener, Bart Selman, Silvio Savarese, Ashutosh Saxena
For evaluation, we contribute a new challenging RGB-D activity video dataset recorded by the new Kinect v2, which contains several human daily activities as compositions of multiple actions interacting with different objects.
no code implementations • 10 Feb 2016 • Ozan Sener, Hyun Oh Song, Ashutosh Saxena, Silvio Savarese
We incorporate the domain shift and the transductive target inference into our framework by jointly solving for an asymmetric similarity metric and the optimal transductive target label assignment.
no code implementations • ICCV 2015 • Ozan Sener, Amir Zamir, Silvio Savarese, Ashutosh Saxena
The proposed method is capable of providing a semantic "storyline" of the video composed of its objective steps.
no code implementations • 1 Dec 2014 • Ashutosh Saxena, Ashesh Jain, Ozan Sener, Aditya Jami, Dipendra K. Misra, Hema S. Koppula
In this paper we introduce a knowledge engine, which learns and shares knowledge representations, for robots to carry out a variety of tasks.
no code implementations • 22 Jan 2013 • Ozan Sener, Kemal Ugur, A. Aydin Alatan
Depending on the application, automatic or interactive methods are desired; however, regardless of the application type, efficient computation of video object segmentation is crucial for time-critical applications; specifically, mobile and interactive applications require near real-time efficiencies.