Search Results for author: Mahsa Baktashmotlagh

Found 43 papers, 14 papers with code

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

no code implementations21 Jun 2024 Zhuoxiao Chen, Junjie Meng, Mahsa Baktashmotlagh, Zi Huang, Yadan Luo

The model assembly is directed by the proposed synergy weights (SW), employed for weighted averaging of the selected checkpoints to minimize redundancy in the composite supermodel.

3D Object Detection object-detection +1

DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection

no code implementations21 Jun 2024 Jia Syuen Lim, Zhuoxiao Chen, Mahsa Baktashmotlagh, Zhi Chen, Xin Yu, Zi Huang, Yadan Luo

We demonstrate the effectiveness of DiPEx through extensive class-agnostic OD and OOD-OD experiments on MS-COCO and LVIS, surpassing other prompting methods by up to 20. 1% in AR and achieving a 21. 3% AP improvement over SAM.

Class-agnostic Object Detection Multi-object discovery +3

Leveraging LLMs for Unsupervised Dense Retriever Ranking

1 code implementation7 Feb 2024 Ekaterina Khramtsova, Shengyao Zhuang, Mahsa Baktashmotlagh, Guido Zuccon

In this paper we present Large Language Model Assisted Retrieval Model Ranking (LARMOR), an effective unsupervised approach that leverages LLMs for selecting which dense retriever to use on a test corpus (target).

Language Modelling Large Language Model

Selecting which Dense Retriever to use for Zero-Shot Search

no code implementations18 Sep 2023 Ekaterina Khramtsova, Shengyao Zhuang, Mahsa Baktashmotlagh, Xi Wang, Guido Zuccon

We propose the new problem of choosing which dense retrieval model to use when searching on a new collection for which no labels are available, i. e. in a zero-shot setting.

Information Retrieval Retrieval

Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling

1 code implementation ICCV 2023 Zhuoxiao Chen, Yadan Luo, Zheng Wang, Mahsa Baktashmotlagh, Zi Huang

Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection.

3D Object Detection object-detection +1

KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection

no code implementations ICCV 2023 Yadan Luo, Zhuoxiao Chen, Zhen Fang, Zheng Zhang, Zi Huang, Mahsa Baktashmotlagh

Achieving a reliable LiDAR-based object detector in autonomous driving is paramount, but its success hinges on obtaining large amounts of precise 3D annotations.

3D Object Detection Active Learning +4

Exploring Active 3D Object Detection from a Generalization Perspective

1 code implementation23 Jan 2023 Yadan Luo, Zhuoxiao Chen, Zijian Wang, Xin Yu, Zi Huang, Mahsa Baktashmotlagh

To alleviate the high annotation cost in LiDAR-based 3D object detection, active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate, without compromising model performance.

3D Object Detection Active Learning +2

Center-aware Adversarial Augmentation for Single Domain Generalization

no code implementations WACV 2023 Tianle Chen, Mahsa Baktashmotlagh, Zijian Wang, Mathieu Salzmann

Domain generalization (DG) aims to learn a model from multiple training (i. e., source) domains that can generalize well to the unseen test (i. e., target) data coming from a different distribution.

Data Augmentation Photo to Rest Generalization

How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability

no code implementations ICCV 2023 Zijian Wang, Yadan Luo, Liang Zheng, Zi Huang, Mahsa Baktashmotlagh

This paper focuses on model transferability estimation, i. e., assessing the performance of pre-trained models on a downstream task without performing fine-tuning.

DI-NIDS: Domain Invariant Network Intrusion Detection System

no code implementations15 Oct 2022 Siamak Layeghy, Mahsa Baktashmotlagh, Marius Portmann

In order to enhance the generalisibility of machine learning based network intrusion detection systems, we propose to extract domain invariant features using adversarial domain adaptation from multiple network domains, and then apply an unsupervised technique for recognising abnormalities, i. e., intrusions.

Domain Adaptation Network Intrusion Detection

Rethinking Persistent Homology for Visual Recognition

no code implementations9 Jul 2022 Ekaterina Khramtsova, Guido Zuccon, Xi Wang, Mahsa Baktashmotlagh

This paper performs a detailed analysis of the effectiveness of topological properties for image classification in various training scenarios, defined by: the number of training samples, the complexity of the training data and the complexity of the backbone network.

Image Classification

Source-Free Progressive Graph Learning for Open-Set Domain Adaptation

2 code implementations13 Feb 2022 Yadan Luo, Zijian Wang, Zhuoxiao Chen, Zi Huang, Mahsa Baktashmotlagh

However, most existing OSDA approaches are limited due to three main reasons, including: (1) the lack of essential theoretical analysis of generalization bound, (2) the reliance on the coexistence of source and target data during adaptation, and (3) failing to accurately estimate the uncertainty of model predictions.

Action Recognition Domain Adaptation +2

Conditional Extreme Value Theory for Open Set Video Domain Adaptation

1 code implementation1 Sep 2021 Zhuoxiao Chen, Yadan Luo, Mahsa Baktashmotlagh

The majority of video domain adaptation algorithms are proposed for closed-set scenarios in which all the classes are shared among the domains.

Action Recognition Domain Adaptation +1

Learning to Diversify for Single Domain Generalization

1 code implementation ICCV 2021 Zijian Wang, Yadan Luo, Ruihong Qiu, Zi Huang, Mahsa Baktashmotlagh

Domain generalization (DG) aims to generalize a model trained on multiple source (i. e., training) domains to a distributionally different target (i. e., test) domain.

Photo to Rest Generalization

Going Deeper into Semi-supervised Person Re-identification

no code implementations24 Jul 2021 Olga Moskvyak, Frederic Maire, Feras Dayoub, Mahsa Baktashmotlagh

To reduce the need for labeled data, we focus on a semi-supervised approach that requires only a subset of the training data to be labeled.

Semi-Supervised Person Re-Identification

Learning Compositional Shape Priors for Few-Shot 3D Reconstruction

no code implementations11 Jun 2021 Mateusz Michalkiewicz, Stavros Tsogkas, Sarah Parisot, Mahsa Baktashmotlagh, Anders Eriksson, Eugene Belilovsky

The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space.

3D Reconstruction Decoder +2

Semi-supervised Keypoint Localization

no code implementations ICLR 2021 Olga Moskvyak, Frederic Maire, Feras Dayoub, Mahsa Baktashmotlagh

Keypoint representations are learnt with a semantic keypoint consistency constraint that forces the keypoint detection network to learn similar features for the same keypoint across the dataset.

Keypoint Detection

Learning to Generate the Unknowns for Open-set Domain Adaptation

no code implementations1 Jan 2021 Mahsa Baktashmotlagh, Tianle Chen, Mathieu Salzmann

In this setting, existing techniques focus on the challenging task of isolating the unknown target samples, so as to avoid the negative transfer resulting from aligning the source feature distributions with the broader target one that encompasses the additional unknown classes.

Domain Adaptation

Domain Adaptative Causality Encoder

1 code implementation ALTA 2020 Farhad Moghimifar, Gholamreza Haffari, Mahsa Baktashmotlagh

Our experiments on four different benchmark causality datasets demonstrate the superiority of our approach over the existing baselines, by up to 7% improvement, on the tasks of identification and localisation of the causal relations from the text.

Learning Causal Bayesian Networks from Text

no code implementations ALTA 2020 Farhad Moghimifar, Afshin Rahimi, Mahsa Baktashmotlagh, Xue Li

Causal relationships form the basis for reasoning and decision-making in Artificial Intelligence systems.

Decision Making

Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph

1 code implementation25 Nov 2020 Yadan Luo, Zi Huang, Hongxu Chen, Yang Yang, Mahsa Baktashmotlagh

Most of the prior efforts are devoted to learning node embeddings with graph neural networks (GNNs), which preserve the signed network topology by message-passing along edges to facilitate the downstream link prediction task.

Link Prediction

COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering

1 code implementation COLING 2020 Farhad Moghimifar, Lizhen Qu, Yue Zhuo, Mahsa Baktashmotlagh, Gholamreza Haffari

However, current approaches in this realm lack the ability to perform commonsense reasoning upon facing an unseen situation, mostly due to incapability of identifying a diverse range of implicit social relations.

Question Answering

Keypoint-Aligned Embeddings for Image Retrieval and Re-identification

no code implementations26 Aug 2020 Olga Moskvyak, Frederic Maire, Feras Dayoub, Mahsa Baktashmotlagh

Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification.

Image Retrieval Multi-Task Learning +1

Adversarial Bipartite Graph Learning for Video Domain Adaptation

1 code implementation31 Jul 2020 Yadan Luo, Zi Huang, Zijian Wang, Zheng Zhang, Mahsa Baktashmotlagh

To further enhance the model capacity and testify the robustness of the proposed architecture on difficult transfer tasks, we extend our model to work in a semi-supervised setting using an additional video-level bipartite graph.

Domain Adaptation Graph Learning +1

Progressive Graph Learning for Open-Set Domain Adaptation

1 code implementation ICML 2020 Yadan Luo, Zijian Wang, Zi Huang, Mahsa Baktashmotlagh

The existing domain adaptation approaches which tackle this problem work in the closed-set setting with the assumption that the source and the target data share exactly the same classes of objects.

Domain Adaptation Graph Learning +1

Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors

1 code implementation ECCV 2020 Mateusz Michalkiewicz, Sarah Parisot, Stavros Tsogkas, Mahsa Baktashmotlagh, Anders Eriksson, Eugene Belilovsky

In this work we demonstrate experimentally that naive baselines do not apply when the goal is to learn to reconstruct novel objects using very few examples, and that in a \emph{few-shot} learning setting, the network must learn concepts that can be applied to new categories, avoiding rote memorization.

3D Reconstruction Decoder +4

Implicitly Defined Layers in Neural Networks

no code implementations3 Mar 2020 Qianggong Zhang, Yanyang Gu, Michalkiewicz Mateusz, Mahsa Baktashmotlagh, Anders Eriksson

In conventional formulations of multilayer feedforward neural networks, the individual layers are customarily defined by explicit functions.

Learning landmark guided embeddings for animal re-identification

no code implementations9 Jan 2020 Olga Moskvyak, Frederic Maire, Feras Dayoub, Mahsa Baktashmotlagh

Our method outperforms the same model without body landmarks input by 26% and 18% on the synthetic and the real datasets respectively.

Person Re-Identification

Correlation-aware Adversarial Domain Adaptation and Generalization

no code implementations29 Nov 2019 Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, Sridha Sridharan

Domain adaptation (DA) and domain generalization (DG) have emerged as a solution to the domain shift problem where the distribution of the source and target data is different.

Domain Generalization

Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling

no code implementations12 Nov 2019 Yadan Luo, Zi Huang, Zheng Zhang, Ziwei Wang, Mahsa Baktashmotlagh, Yang Yang

Meta-learning for few-shot learning allows a machine to leverage previously acquired knowledge as a prior, thus improving the performance on novel tasks with only small amounts of data.

Continual Learning Few-Shot Learning

Robust Re-identification of Manta Rays from Natural Markings by Learning Pose Invariant Embeddings

1 code implementation28 Feb 2019 Olga Moskvyak, Frederic Maire, Asia O. Armstrong, Feras Dayoub, Mahsa Baktashmotlagh

We present a novel system for visual re-identification based on unique natural markings that is robust to occlusions, viewpoint and illumination changes.

On Minimum Discrepancy Estimation for Deep Domain Adaptation

1 code implementation2 Jan 2019 Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, Sridha Sridharan

In the presence of large sets of labeled data, Deep Learning (DL) has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks.

Domain Adaptation General Classification +1

Multi-component Image Translation for Deep Domain Generalization

no code implementations21 Dec 2018 Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, Sridha Sridharan

If DA methods are applied directly to DG by a simple exclusion of the target data from training, poor performance will result for a given task.

Domain Generalization Generative Adversarial Network +1

Learning Factorized Representations for Open-set Domain Adaptation

no code implementations ICLR 2019 Mahsa Baktashmotlagh, Masoud Faraki, Tom Drummond, Mathieu Salzmann

To this end, we rely on the intuition that the source and target samples depicting the known classes can be generated by a shared subspace, whereas the target samples from unknown classes come from a different, private subspace.

Domain Adaptation

On Encoding Temporal Evolution for Real-time Action Prediction

no code implementations22 Sep 2017 Fahimeh Rezazadegan, Sareh Shirazi, Mahsa Baktashmotlagh, Larry S. Davis

Anticipating future actions is a key component of intelligence, specifically when it applies to real-time systems, such as robots or autonomous cars.

From Review to Rating: Exploring Dependency Measures for Text Classification

no code implementations4 Sep 2017 Samuel Cunningham-Nelson, Mahsa Baktashmotlagh, Wageeh Boles

In this work, we explore using statistical dependence measures for textual classification, representing text as word vectors.

feature selection General Classification +3

Domain Adaptation on the Statistical Manifold

no code implementations CVPR 2014 Mahsa Baktashmotlagh, Mehrtash T. Harandi, Brian C. Lovell, Mathieu Salzmann

Here, we propose to make better use of the structure of this manifold and rely on the distance on the manifold to compare the source and target distributions.

Object Recognition Unsupervised Domain Adaptation

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