no code implementations • 21 Mar 2024 • Nikolaos Tsagkas, Jack Rome, Subramanian Ramamoorthy, Oisin Mac Aodha, Chris Xiaoxuan Lu
Precise manipulation that is generalizable across scenes and objects remains a persistent challenge in robotics.
no code implementations • 20 Dec 2023 • Octave Mariotti, Oisin Mac Aodha, Hakan Bilen
To address these limitations, we propose a new approach for semantic correspondence estimation that supplements discriminative self-supervised features with 3D understanding via a weak geometric spherical prior.
1 code implementation • NeurIPS 2023 • Christian Lange, Elijah Cole, Grant van Horn, Oisin Mac Aodha
Our results demonstrate that our method outperforms alternative active learning methods and approaches the performance of end-to-end trained models, even when only using a fraction of the data.
2 code implementations • 5 Jun 2023 • Elijah Cole, Grant van Horn, Christian Lange, Alexander Shepard, Patrick Leary, Pietro Perona, Scott Loarie, Oisin Mac Aodha
Estimating the geographical range of a species from sparse observations is a challenging and important geospatial prediction problem.
no code implementations • 21 May 2023 • Nikolaos Tsagkas, Oisin Mac Aodha, Chris Xiaoxuan Lu
We present Visual-Language Fields (VL-Fields), a neural implicit spatial representation that enables open-vocabulary semantic queries.
1 code implementation • CVPR 2023 • Jamie Watson, Mohamed Sayed, Zawar Qureshi, Gabriel J. Brostow, Sara Vicente, Oisin Mac Aodha, Michael Firman
We instead propose an implicit model for depth and use that to predict the occlusion mask directly.
no code implementations • ICCV 2023 • Bingchen Zhao, Oisin Mac Aodha
We explore the problem of Incremental Generalized Category Discovery (IGCD).
1 code implementation • 31 Mar 2023 • Yongshuo Zong, Oisin Mac Aodha, Timothy Hospedales
In this survey, we provide a comprehensive review of the state-of-the-art in SSML, in which we elucidate three major challenges intrinsic to self-supervised learning with multimodal data: (1) learning representations from multimodal data without labels, (2) fusion of different modalities, and (3) learning with unaligned data.
no code implementations • 23 Mar 2023 • Mehmet Aygün, Oisin Mac Aodha
We introduce SAOR, a novel approach for estimating the 3D shape, texture, and viewpoint of an articulated object from a single image captured in the wild.
no code implementations • 17 Jan 2023 • Bingchen Zhao, Quan Cui, Hao Wu, Osamu Yoshie, Cheng Yang, Oisin Mac Aodha
In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data.
no code implementations • 1 Dec 2022 • Octave Mariotti, Oisin Mac Aodha, Hakan Bilen
We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimation method that learns to predict category-level viewpoints directly from images during training.
no code implementations • ICCV 2021 • Octave Mariotti, Oisin Mac Aodha, Hakan Bilen
Understanding the 3D world without supervision is currently a major challenge in computer vision as the annotations required to supervise deep networks for tasks in this domain are expensive to obtain on a large scale.
2 code implementations • 10 Oct 2022 • Kiyoon Kim, Davide Moltisanti, Oisin Mac Aodha, Laura Sevilla-Lara
In practice, a given video can contain multiple valid positive annotations for the same action.
1 code implementation • 7 Oct 2022 • Omiros Pantazis, Gabriel Brostow, Kate Jones, Oisin Mac Aodha
To combat this, a series of light-weight adaptation methods have been proposed to efficiently adapt such models when limited supervision is available.
1 code implementation • 21 Jul 2022 • Grant van Horn, Rui Qian, Kimberly Wilber, Hartwig Adam, Oisin Mac Aodha, Serge Belongie
We thoroughly benchmark audiovisual classification performance and modality fusion experiments through the use of state-of-the-art transformer methods.
1 code implementation • 20 Jul 2022 • Neehar Kondapaneni, Pietro Perona, Oisin Mac Aodha
In this work, we propose a novel task of tracing the evolving classification behavior of human learners as they engage in challenging visual classification tasks.
1 code implementation • 20 Jul 2022 • Elijah Cole, Kimberly Wilber, Grant van Horn, Xuan Yang, Marco Fornoni, Pietro Perona, Serge Belongie, Andrew Howard, Oisin Mac Aodha
Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels.
no code implementations • 11 Jul 2022 • Mehmet Aygün, Oisin Mac Aodha
We explore semantic correspondence estimation through the lens of unsupervised learning.
1 code implementation • 25 Jan 2022 • Kiyoon Kim, Shreyank N Gowda, Oisin Mac Aodha, Laura Sevilla-Lara
We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost.
no code implementations • 11 Nov 2021 • Xiu-Shen Wei, Yi-Zhe Song, Oisin Mac Aodha, Jianxin Wu, Yuxin Peng, Jinhui Tang, Jian Yang, Serge Belongie
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications.
1 code implementation • ICCV 2021 • Omiros Pantazis, Gabriel Brostow, Kate Jones, Oisin Mac Aodha
We address the problem of learning self-supervised representations from unlabeled image collections.
2 code implementations • CVPR 2021 • Elijah Cole, Oisin Mac Aodha, Titouan Lorieul, Pietro Perona, Dan Morris, Nebojsa Jojic
When the number of potential labels is large, human annotators find it difficult to mention all applicable labels for each training image.
no code implementations • CVPR 2022 • Elijah Cole, Xuan Yang, Kimberly Wilber, Oisin Mac Aodha, Serge Belongie
Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification.
1 code implementation • CVPR 2021 • Jamie Watson, Oisin Mac Aodha, Victor Prisacariu, Gabriel Brostow, Michael Firman
We propose ManyDepth, an adaptive approach to dense depth estimation that can make use of sequence information at test time, when it is available.
Monocular Depth Estimation Unsupervised Monocular Depth Estimation
1 code implementation • CVPR 2021 • Grant van Horn, Elijah Cole, Sara Beery, Kimberly Wilber, Serge Belongie, Oisin Mac Aodha
In order to facilitate progress in this area we present two new natural world visual classification datasets, iNat2021 and NeWT.
2 code implementations • ECCV 2020 • Jamie Watson, Oisin Mac Aodha, Daniyar Turmukhambetov, Gabriel J. Brostow, Michael Firman
We propose that it is unnecessary to have such a high reliance on ground truth depths or even corresponding stereo pairs.
no code implementations • 5 Feb 2020 • Daniel Laumer, Nico Lang, Natalie van Doorn, Oisin Mac Aodha, Pietro Perona, Jan Dirk Wegner
We introduce an approach for updating older tree inventories with geographic coordinates using street-level panorama images and a global optimization framework for tree instance matching.
4 code implementations • ICCV 2019 • Oisin Mac Aodha, Elijah Cole, Pietro Perona
Appearance information alone is often not sufficient to accurately differentiate between fine-grained visual categories.
no code implementations • 11 Apr 2019 • Sara Beery, Grant van Horn, Oisin Mac Aodha, Pietro Perona
Camera traps are a valuable tool for studying biodiversity, but research using this data is limited by the speed of human annotation.
14 code implementations • 4 Jun 2018 • Clément Godard, Oisin Mac Aodha, Michael Firman, Gabriel Brostow
Per-pixel ground-truth depth data is challenging to acquire at scale.
Ranked #3 on Monocular Depth Estimation on VA (Virtual Apartment)
no code implementations • NeurIPS 2019 • Anette Hunziker, Yuxin Chen, Oisin Mac Aodha, Manuel Gomez Rodriguez, Andreas Krause, Pietro Perona, Yisong Yue, Adish Singla
Our framework is both generic, allowing the design of teaching schedules for different memory models, and also interactive, allowing the teacher to adapt the schedule to the underlying forgetting mechanisms of the learner.
no code implementations • 17 May 2018 • Matteo Ruggero Ronchi, Oisin Mac Aodha, Robert Eng, Pietro Perona
We address the problem of 3D human pose estimation from 2D input images using only weakly supervised training data.
no code implementations • CVPR 2018 • Oisin Mac Aodha, Shih-An Su, Yuxin Chen, Pietro Perona, Yisong Yue
We study the problem of computer-assisted teaching with explanations.
no code implementations • NeurIPS 2018 • Yuxin Chen, Adish Singla, Oisin Mac Aodha, Pietro Perona, Yisong Yue
We highlight that adaptivity does not speed up the teaching process when considering existing models of version space learners, such as "worst-case" (the learner picks the next hypothesis randomly from the version space) and "preference-based" (the learner picks hypothesis according to some global preference).
no code implementations • CVPR 2018 • Kun Ho Kim, Oisin Mac Aodha, Pietro Perona
Low dimensional embeddings that capture the main variations of interest in collections of data are important for many applications.
19 code implementations • CVPR 2018 • Grant Van Horn, Oisin Mac Aodha, Yang song, Yin Cui, Chen Sun, Alex Shepard, Hartwig Adam, Pietro Perona, Serge Belongie
Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories.
Ranked #8 on Image Classification on iNaturalist
16 code implementations • CVPR 2017 • Clément Godard, Oisin Mac Aodha, Gabriel J. Brostow
Learning based methods have shown very promising results for the task of depth estimation in single images.
Ranked #4 on Monocular Depth Estimation on Mid-Air Dataset
no code implementations • CVPR 2016 • Michael Firman, Oisin Mac Aodha, Simon Julier, Gabriel J. Brostow
Building a complete 3D model of a scene, given only a single depth image, is underconstrained.
no code implementations • CVPR 2014 • Oisin Mac Aodha, Neill D. F. Campbell, Jan Kautz, Gabriel J. Brostow
Under some specific circumstances, Expected Error Reduction has been one of the strongest-performing informativeness criteria for active learning.
no code implementations • CVPR 2015 • Edward Johns, Oisin Mac Aodha, Gabriel J. Brostow
However, image-importance is individual-specific, i. e. a teaching image is important to a student if it changes their overall ability to discriminate between classes.