68 citations · 216 across the 24 of their papers we have counts for
29 papers
MambaNetBurst: Direct Byte-level Network Traffic Classification without Tokenization or Pretraining
Gayan K. Kulatilleke, Siamak Layeghy, Mahsa Baktashmotlagh +1
We present MambaNetBurst, a compact tokenizer-free byte-level sequence classifier for network burst classification based on a Mamba-2 backbone. In contrast to most recent strong tr…
Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data
Shijie Wang, Zijian Wang, Yadan Luo +3
Ultra-fine-grained visual categorization (Ultra-FGVC) aims to classify highly similar subcategories within fine-grained objects using limited training samples. However, holistic ye…
Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization
Tan Pan, Kaiyu Guo, Dongli Xu +8
The generalization ability of deep learning has been extensively studied in supervised settings, yet it remains less explored in unsupervised scenarios. Recently, the Unsupervised…
ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimation
Chenzhi Liu, Mahsa Baktashmotlagh, Yanran Tang +2
Estimating model accuracy on unseen, unlabeled datasets is crucial for real-world machine learning applications, especially under distribution shifts that can degrade performance.…
Improving Out-of-Distribution Detection via Dynamic Covariance Calibration
Kaiyu Guo, Zijian Wang, Tan Pan +2
Out-of-Distribution (OOD) detection is essential for the trustworthiness of AI systems. Methods using prior information (i.e., subspace-based methods) have shown effective performa…
GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra
Mateusz Michalkiewicz, Anekha Sokhal, Tadeusz Michalkiewicz +4
Modern monocular 3D reconstruction methods and vision-language models (VLMs) demonstrate impressive results on standard benchmarks, yet recent works cast doubt on their true unders…
SD-MAD: Sign-Driven Few-shot Multi-Anomaly Detection in Medical Images
Kaiyu Guo, Tan Pan, Chen Jiang +5
Medical anomaly detection (AD) is crucial for early clinical intervention, yet it faces challenges due to limited access to high-quality medical imaging data, caused by privacy con…
Benchmarking Transferability: A Framework for Fair and Robust Evaluation
Alireza Kazemi, Helia Rezvani, Mahsa Baktashmotlagh
Transferability scores aim to quantify how well a model trained on one domain generalizes to a target domain. Despite numerous methods proposed for measuring transferability, their…
Feature Space Perturbation: A Panacea to Enhanced Transferability Estimation
Prafful Kumar Khoba, Zijian Wang, Chetan Arora +1
Leveraging a transferability estimation metric facilitates the non-trivial challenge of selecting the optimal model for the downstream task from a pool of pre-trained models. Most…
Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models
Mateusz Michalkiewicz, Sheena Bai, Mahsa Baktashmotlagh +2
In this paper, we analyze the viewpoint stability of foundational models - specifically, their sensitivity to changes in viewpoint- and define instability as significant feature va…
Color-Oriented Redundancy Reduction in Dataset Distillation
Bowen Yuan, Zijian Wang, Mahsa Baktashmotlagh +2
Dataset Distillation (DD) is designed to generate condensed representations of extensive image datasets, enhancing training efficiency. Despite recent advances, there remains consi…
Shape-Space Deformer: Unified Visuo-Tactile Representations for Robotic Manipulation of Deformable Objects
Sean M. V. Collins, Brendan Tidd, Mahsa Baktashmotlagh +1
Accurate modelling of object deformations is crucial for a wide range of robotic manipulation tasks, where interacting with soft or deformable objects is essential. Current methods…
Exploring Active 3D Object Detection from a Generalization Perspective
Yadan Luo, Zhuoxiao Chen, Zijian Wang +3
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 an…
DI-NIDS: Domain Invariant Network Intrusion Detection System
Siamak Layeghy, Mahsa Baktashmotlagh, Marius Portmann
The performance of machine learning based network intrusion detection systems (NIDSs) severely degrades when deployed on a network with significantly different feature distribution…
Conditional Extreme Value Theory for Open Set Video Domain Adaptation
Zhuoxiao Chen, Yadan Luo, Mahsa Baktashmotlagh
With the advent of media streaming, video action recognition has become progressively important for various applications, yet at the high expense of requiring large-scale data labe…
Learning Compositional Shape Priors for Few-Shot 3D Reconstruction
Mateusz Michalkiewicz, Stavros Tsogkas, Sarah Parisot +3
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…
Domain Adaptative Causality Encoder
Farhad Moghimifar, Gholamreza Haffari, Mahsa Baktashmotlagh
Current approaches which are mainly based on the extraction of low-level relations among individual events are limited by the shortage of publicly available labelled data. Therefor…
Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph
Yadan Luo, Zi Huang, Hongxu Chen +2
Signed link prediction in social networks aims to reveal the underlying relationships (i.e. links) among users (i.e. nodes) given their existing positive and negative interactions…
Progressive Graph Learning for Open-Set Domain Adaptation
Yadan Luo, Zijian Wang, Zi Huang +1
Domain shift is a fundamental problem in visual recognition which typically arises when the source and target data follow different distributions. The existing domain adaptation ap…
A Simple and Scalable Shape Representation for 3D Reconstruction
Mateusz Michalkiewicz, Eugene Belilovsky, Mahsa Baktashmotlagh +1
Deep learning applied to the reconstruction of 3D shapes has seen growing interest. A popular approach to 3D reconstruction and generation in recent years has been the CNN encoder-…
Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors
Mateusz Michalkiewicz, Sarah Parisot, Stavros Tsogkas +3
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…
Implicitly Defined Layers in Neural Networks
Qianggong Zhang, Yanyang Gu, Michalkiewicz Mateusz +2
In conventional formulations of multilayer feedforward neural networks, the individual layers are customarily defined by explicit functions. In this paper we demonstrate that defin…
Learning landmark guided embeddings for animal re-identification
Olga Moskvyak, Frederic Maire, Feras Dayoub +1
Re-identification of individual animals in images can be ambiguous due to subtle variations in body markings between different individuals and no constraints on the poses of animal…
Correlation-aware Adversarial Domain Adaptation and Generalization
Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh +1
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. The…