38 citations · 102 across the 22 of their papers we have counts for
25 papers
Open Vocabulary Domain Unlearning
Sumanth Udupa, Mehrtash Harandi, Yadan Luo +1
Vision-Language Models (VLMs) exhibit remarkable zero-shot generalization, yet they often encode unwanted or hazardous stylistic domains such as idealized textbook diagrams in medi…
Foveated Probes Recover Localized Binding Information in Vision Foundation Models
Mateusz Michalkiewicz, Mahsa Baktashmotlagh, Guha Balakrishnan
Frozen vision foundation models are commonly evaluated through a single global image embedding, but this interface can conflate missing information with information lost at readout…
T5-CSBoost: Adversarial Perturbation Resistant LLM Fingerprinting
Gayan K. Kulatilleke, Mahsa Baktashmotlagh, Siamak Layeghy +1
While many AI-generated text (AIGT) detectors achieve strong performance on clean inputs, their accuracy degrades significantly under light paraphrasing, word substitutions, charac…
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
Tan Pan, Shuhao Mei, Yixuan Sun +8
Self-supervised pre-training methods in medical imaging typically treat each individual as an isolated instance, learning representations through augmentation-based objectives or m…
WisWheat: A Three-Tiered Vision-Language Dataset for Wheat Management
Bowen Yuan, Selena Song, Javier Fernandez +3
Wheat management strategies play a critical role in determining yield. Traditional management decisions often rely on labour-intensive expert inspections, which are expensive, subj…
Source-Free Domain-Invariant Performance Prediction
Ekaterina Khramtsova, Mahsa Baktashmotlagh, Guido Zuccon +2
Accurately estimating model performance poses a significant challenge, particularly in scenarios where the source and target domains follow different data distributions. Most exist…
Embark on DenseQuest: A System for Selecting the Best Dense Retriever for a Custom Collection
Ekaterina Khramtsova, Teerapong Leelanupab, Shengyao Zhuang +2
In this demo we present a web-based application for selecting an effective pre-trained dense retriever to use on a private collection. Our system, DenseQuest, provides unsupervised…
DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
Jia Syuen Lim, Zhuoxiao Chen, Mahsa Baktashmotlagh +4
Class-agnostic object detection (OD) can be a cornerstone or a bottleneck for many downstream vision tasks. Despite considerable advancements in bottom-up and multi-object discover…
MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
Zhuoxiao Chen, Junjie Meng, Mahsa Baktashmotlagh +3
LiDAR-based 3D object detection is crucial for various applications but often experiences performance degradation in real-world deployments due to domain shifts. While most studies…
Leveraging LLMs for Unsupervised Dense Retriever Ranking
Ekaterina Khramtsova, Shengyao Zhuang, Mahsa Baktashmotlagh +1
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…
Selecting which Dense Retriever to use for Zero-Shot Search
Ekaterina Khramtsova, Shengyao Zhuang, Mahsa Baktashmotlagh +2
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. Many de…
Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling
Zhuoxiao Chen, Yadan Luo, Zheng Wang +2
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing…
KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection
Yadan Luo, Zhuoxiao Chen, Zhen Fang +3
Achieving a reliable LiDAR-based object detector in autonomous driving is paramount, but its success hinges on obtaining large amounts of precise 3D annotations. Active learning (A…
Rethinking Persistent Homology for Visual Recognition
Ekaterina Khramtsova, Guido Zuccon, Xi Wang +1
Persistent topological properties of an image serve as an additional descriptor providing an insight that might not be discovered by traditional neural networks. The existing resea…
Source-Free Progressive Graph Learning for Open-Set Domain Adaptation
Yadan Luo, Zijian Wang, Zhuoxiao Chen +2
Open-set domain adaptation (OSDA) has gained considerable attention in many visual recognition tasks. However, most existing OSDA approaches are limited due to three main reasons,…
Learning to Diversify for Single Domain Generalization
Zijian Wang, Yadan Luo, Ruihong Qiu +2
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. In contrast to…
Going Deeper into Semi-supervised Person Re-identification
Olga Moskvyak, Frederic Maire, Feras Dayoub +1
Person re-identification is the challenging task of identifying a person across different camera views. Training a convolutional neural network (CNN) for this task requires annotat…
Neural-Symbolic Commonsense Reasoner with Relation Predictors
Farhad Moghimifar, Lizhen Qu, Yue Zhuo +2
Commonsense reasoning aims to incorporate sets of commonsense facts, retrieved from Commonsense Knowledge Graphs (CKG), to draw conclusion about ordinary situations. The dynamic na…
Semi-supervised Keypoint Localization
Olga Moskvyak, Frederic Maire, Feras Dayoub +1
Knowledge about the locations of keypoints of an object in an image can assist in fine-grained classification and identification tasks, particularly for the case of objects that ex…
Learning Causal Bayesian Networks from Text
Farhad Moghimifar, Afshin Rahimi, Mahsa Baktashmotlagh +1
Causal relationships form the basis for reasoning and decision-making in Artificial Intelligence systems. To exploit the large volume of textual data available today, the automatic…
COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering
Farhad Moghimifar, Lizhen Qu, Yue Zhuo +2
Commonsense reasoning refers to the ability of evaluating a social situation and acting accordingly. Identification of the implicit causes and effects of a social context is the dr…
Keypoint-Aligned Embeddings for Image Retrieval and Re-identification
Olga Moskvyak, Frederic Maire, Feras Dayoub +1
Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification. The existing approaches for person, vehicle, or animal…
Adversarial Bipartite Graph Learning for Video Domain Adaptation
Yadan Luo, Zi Huang, Zijian Wang +2
Domain adaptation techniques, which focus on adapting models between distributionally different domains, are rarely explored in the video recognition area due to the significant sp…
Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling
Yadan Luo, Zi Huang, Zheng Zhang +3
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…