Search Results for author: Damien Teney

Found 40 papers, 13 papers with code

Vision-Language Pretraining: Current Trends and the Future

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).

Question Answering Representation Learning +1

CulturePark: Boosting Cross-cultural Understanding in Large Language Models

no code implementations24 May 2024 Cheng Li, Damien Teney, Linyi Yang, Qingsong Wen, Xing Xie, Jindong Wang

Results show that for content moderation, our GPT-3. 5-based models either match or outperform GPT-4 on datasets.

Neural Redshift: Random Networks are not Random Functions

no code implementations CVPR 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.

Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines

no code implementations29 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.


Mitigating Biases with Diverse Ensembles and Diffusion Models

no code implementations23 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.


ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning

1 code implementation8 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.

Personalized Federated Learning

Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks

no code implementations3 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.


Learning Diverse Features in Vision Transformers for Improved Generalization

1 code implementation30 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.


Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup

no code implementations26 May 2023 Damien Teney, Jindong Wang, Ehsan Abbasnejad

We have found a new equivalence between two successful methods: selective mixup and resampling.

Binary Classification

Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder

2 code implementations25 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.

Composed Image Retrieval (CoIR) Re-Ranking +1

A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers

no code implementations21 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.

Mathematical Reasoning

Bi-directional Training for Composed Image Retrieval via Text Prompt Learning

1 code implementation29 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.

Composed Image Retrieval (CoIR) Retrieval

SelecMix: Debiased Learning by Contradicting-pair Sampling

1 code implementation4 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.

Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning

no code implementations6 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.

BIG-bench Machine Learning Model Selection

EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering

no code implementations29 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.

Contrastive Learning Out of Distribution (OOD) Detection +4

Active Learning by Feature Mixing

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.

Active Learning

Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models

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.

Composed Image Retrieval (CoIR) Retrieval +1

Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge

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.

Question Answering Visual Question Answering (VQA) +1

Counterfactual Vision-and-Language Navigation: Unravelling the Unseen

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.

counterfactual Embodied Question Answering +2

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

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.

Model Selection Question Answering +1

Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision

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.

counterfactual Multi-Label Image Classification +4

Unshuffling Data for Improved Generalization

no code implementations27 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.

Clustering Data Augmentation +3

On Incorporating Semantic Prior Knowledge in Deep Learning Through Embedding-Space Constraints

no code implementations30 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.

Data Augmentation Question Answering +1

On Incorporating Semantic Prior Knowlegde in Deep Learning Through Embedding-Space Constraints

no code implementations25 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.

Data Augmentation Question Answering +1

V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices

no code implementations29 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.

Visual Reasoning

Actively Seeking and Learning from Live Data

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.

Domain Adaptation Meta-Learning +3

Visual Question Answering as a Meta Learning Task

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.

Meta-Learning Question Answering +1

Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments

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.

Translation Vision and Language Navigation +2

Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

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.

Image Captioning Visual Question Answering

Zero-Shot Visual Question Answering

no code implementations17 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.

Question Answering Retrieval +2

Visual Question Answering: A Survey of Methods and Datasets

1 code implementation20 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.

General Knowledge Visual Question Answering

Learning to Extract Motion from Videos in Convolutional Neural Networks

no code implementations27 Jan 2016 Damien Teney, Martial Hebert

Our contributions on network design and rotation invariance offer insights nonspecific to motion estimation.

Motion Estimation Optical Flow Estimation

Learning Similarity Metrics for Dynamic Scene Segmentation

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.

Metric Learning Motion Segmentation +3

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