no code implementations • ACL 2022 • Aishwarya Agrawal, Damien Teney, Aida Nematzadeh
In addition to the larger pretraining datasets, the transformer architecture (Vaswani et al., 2017) and in particular self-attention applied to two modalities are responsible for the impressive performance of the recent pretrained models on downstream tasks (Hendricks et al., 2021).
no code implementations • 4 Mar 2024 • Damien Teney, Armand Nicolicioiu, Valentin Hartmann, Ehsan Abbasnejad
Prevailing explanations are based on implicit biases of gradient descent (GD) but they cannot account for the capabilities of models from gradient-free methods nor the simplicity bias recently observed in untrained networks.
no code implementations • 29 Nov 2023 • Hamed Damirchi, Cristian Rodríguez-Opazo, Ehsan Abbasnejad, Damien Teney, Javen Qinfeng Shi, Stephen Gould, Anton Van Den Hengel
Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box.
no code implementations • 23 Nov 2023 • Luca Scimeca, Alexander Rubinstein, Damien Teney, Seong Joon Oh, Armand Mihai Nicolicioiu, Yoshua Bengio
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to a phenomenon known as shortcut learning, where a model relies on erroneous, easy-to-learn cues while ignoring reliable ones.
1 code implementation • 8 Oct 2023 • Wang Lu, Hao Yu, Jindong Wang, Damien Teney, Haohan Wang, Yiqiang Chen, Qiang Yang, Xing Xie, Xiangyang Ji
When personalized federated learning (FL) meets large foundation models, new challenges arise from various limitations in resources.
no code implementations • 3 Oct 2023 • Luca Scimeca, Alexander Rubinstein, Armand Mihai Nicolicioiu, Damien Teney, Yoshua Bengio
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to shortcut learning phenomena, where a model may rely on erroneous, easy-to-learn, cues while ignoring reliable ones.
1 code implementation • 30 Aug 2023 • Armand Mihai Nicolicioiu, Andrei Liviu Nicolicioiu, Bogdan Alexe, Damien Teney
We observe improved out-of-distribution performance on diagnostic benchmarks (MNIST-CIFAR, Waterbirds) as a consequence of the enhanced diversity of features and the pruning of undesirable heads.
no code implementations • 26 May 2023 • Damien Teney, Jindong Wang, Ehsan Abbasnejad
We have found a new equivalence between two successful methods: selective mixup and resampling.
2 code implementations • 25 May 2023 • Zheyuan Liu, Weixuan Sun, Damien Teney, Stephen Gould
An alternative approach is to allow interactions between the query and every possible candidate, i. e., reference-text-candidate triplets, and pick the best from the entire set.
Ranked #2 on Image Retrieval on CIRR
no code implementations • 21 May 2023 • Jordan Meadows, Marco Valentino, Damien Teney, Andre Freitas
This paper proposes a methodology for generating and perturbing detailed derivations of equations at scale, aided by a symbolic engine, to evaluate the generalisability of Transformers to out-of-distribution mathematical reasoning problems.
1 code implementation • 29 Mar 2023 • Zheyuan Liu, Weixuan Sun, Yicong Hong, Damien Teney, Stephen Gould
Composed image retrieval searches for a target image based on a multi-modal user query comprised of a reference image and modification text describing the desired changes.
Ranked #6 on Image Retrieval on Fashion IQ
1 code implementation • 4 Nov 2022 • Inwoo Hwang, Sangjun Lee, Yunhyeok Kwak, Seong Joon Oh, Damien Teney, Jin-Hwa Kim, Byoung-Tak Zhang
Experiments on standard benchmarks demonstrate the effectiveness of the method, in particular when label noise complicates the identification of bias-conflicting examples.
no code implementations • 6 Jul 2022 • Damien Teney, Maxime Peyrard, Ehsan Abbasnejad
Underspecification refers to the existence of multiple models that are indistinguishable in their in-domain accuracy, even though they differ in other desirable properties such as out-of-distribution (OOD) performance.
no code implementations • 29 Jun 2022 • Violetta Shevchenko, Ehsan Abbasnejad, Anthony Dick, Anton Van Den Hengel, Damien Teney
In a simple setting similar to CLEVR, we find that CL representations also improve systematic generalization, and even match the performance of representations from a larger, supervised, ImageNet-pretrained model.
3 code implementations • CVPR 2022 • Amin Parvaneh, Ehsan Abbasnejad, Damien Teney, Reza Haffari, Anton Van Den Hengel, Javen Qinfeng Shi
We identify unlabelled instances with sufficiently-distinct features by seeking inconsistencies in predictions resulting from interventions on their representations.
3 code implementations • ICCV 2021 • Zheyuan Liu, Cristian Rodriguez-Opazo, Damien Teney, Stephen Gould
We demonstrate that with a relatively simple architecture, CIRPLANT outperforms existing methods on open-domain images, while matching state-of-the-art accuracy on the existing narrow datasets, such as fashion.
Ranked #10 on Image Retrieval on CIRR
1 code implementation • CVPR 2022 • Damien Teney, Ehsan Abbasnejad, Simon Lucey, Anton Van Den Hengel
The method - the first to evade the simplicity bias - highlights the need for a better understanding and control of inductive biases in deep learning.
1 code implementation • ICCV 2021 • Corentin Dancette, Remi Cadene, Damien Teney, Matthieu Cord
We use this new evaluation in a large-scale study of existing approaches for VQA.
Ranked #1 on Visual Question Answering (VQA) on VQA-CE
no code implementations • EACL (LANTERN) 2021 • Violetta Shevchenko, Damien Teney, Anthony Dick, Anton Van Den Hengel
The technique brings clear benefits to knowledge-demanding question answering tasks (OK-VQA, FVQA) by capturing semantic and relational knowledge absent from existing models.
no code implementations • ICCV 2021 • Damien Teney, Ehsan Abbasnejad, Anton Van Den Hengel
subsets treated as multiple training environments can guide the learning of models with better out-of-distribution generalization.
no code implementations • NeurIPS 2020 • Amin Parvaneh, Ehsan Abbasnejad, Damien Teney, Qinfeng Shi, Anton Van Den Hengel
The task of vision-and-language navigation (VLN) requires an agent to follow text instructions to find its way through simulated household environments.
no code implementations • NeurIPS 2020 • Damien Teney, Kushal Kafle, Robik Shrestha, Ehsan Abbasnejad, Christopher Kanan, Anton Van Den Hengel
Out-of-distribution (OOD) testing is increasingly popular for evaluating a machine learning system's ability to generalize beyond the biases of a training set.
no code implementations • 4 May 2020 • Violetta Shevchenko, Damien Teney, Anthony Dick, Anton Van Den Hengel
We present a novel mechanism to embed prior knowledge in a model for visual question answering.
no code implementations • ECCV 2020 • Damien Teney, Ehsan Abbasnedjad, Anton Van Den Hengel
One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest.
no code implementations • 27 Feb 2020 • Damien Teney, Ehsan Abbasnejad, Anton Van Den Hengel
subsets treated as multiple training environments can guide the learning of models with better out-of-distribution generalization.
no code implementations • 30 Sep 2019 • Damien Teney, Ehsan Abbasnejad, Anton Van Den Hengel
We also show that incorporating this type of prior knowledge with our method brings consistent improvements, independently from the amount of supervised data used.
no code implementations • 25 Sep 2019 • Damien Teney, Ehsan Abbasnejad, Anton Van Den Hengel
We also show that incorporating this type of prior knowledge with our method brings consistent improvements, independently from the amount of supervised data used.
no code implementations • 29 Jul 2019 • Damien Teney, Peng Wang, Jiewei Cao, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel
One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced.
no code implementations • CVPR 2019 • Damien Teney, Anton Van Den Hengel
One of the key limitations of traditional machine learning methods is their requirement for training data that exemplifies all the information to be learned.
no code implementations • ECCV 2018 • Damien Teney, Anton Van Den Hengel
At test time, the method is provided with a support set of example questions/answers, over which it reasons to resolve the given question.
8 code implementations • CVPR 2018 • Peter Anderson, Qi Wu, Damien Teney, Jake Bruce, Mark Johnson, Niko Sünderhauf, Ian Reid, Stephen Gould, Anton Van Den Hengel
This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering.
Ranked #10 on Visual Navigation on R2R
10 code implementations • CVPR 2018 • Damien Teney, Peter Anderson, Xiaodong He, Anton Van Den Hengel
This paper presents a state-of-the-art model for visual question answering (VQA), which won the first place in the 2017 VQA Challenge.
Ranked #30 on Visual Question Answering (VQA) on VQA v2 test-std
65 code implementations • CVPR 2018 • Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, Lei Zhang
Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning.
Ranked #29 on Visual Question Answering (VQA) on VQA v2 test-std
no code implementations • 17 Nov 2016 • Damien Teney, Anton Van Den Hengel
Answering general questions about images requires methods capable of Zero-Shot VQA, that is, methods able to answer questions beyond the scope of the training questions.
no code implementations • CVPR 2017 • Damien Teney, Lingqiao Liu, Anton Van Den Hengel
This paper proposes to improve visual question answering (VQA) with structured representations of both scene contents and questions.
1 code implementation • 20 Jul 2016 • Qi Wu, Damien Teney, Peng Wang, Chunhua Shen, Anthony Dick, Anton Van Den Hengel
Visual Question Answering (VQA) is a challenging task that has received increasing attention from both the computer vision and the natural language processing communities.
no code implementations • 27 Jan 2016 • Damien Teney, Martial Hebert
Our contributions on network design and rotation invariance offer insights nonspecific to motion estimation.
no code implementations • CVPR 2015 • Damien Teney, Matthew Brown, Dmitry Kit, Peter Hall
This paper addresses the segmentation of videos with arbitrary motion, including dynamic textures, using novel motion features and a supervised learning approach.