Search Results for author:
Found 47 papers, 17 papers with code
Feature Space Perturbation: A Panacea to Enhanced Transferability Estimation
Through extensive experimentation, we demonstrate the efficacy of our feature perturbation method in providing a more precise and robust estimation of model transferability.
Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models
In this paper, we analyze the viewpoint stability of foundational models - specifically, their sensitivity to changes in viewpoint- and define instability as significant feature variations resulting from minor changes in viewing angle, leading to generalization gaps in 3D reasoning tasks.
Color-Oriented Redundancy Reduction in Dataset Distillation
At the image level, we employ a palette network, a specialized neural network, to dynamically allocate colors from a reduced color space to each pixel.
Source-Free Domain-Invariant Performance Prediction
In this work, we propose a source-free approach centred on uncertainty-based estimation, using a generative model for calibration in the absence of source data.
Embark on DenseQuest: A System for Selecting the Best Dense Retriever for a Custom Collection
In this demo we present a web-based application for selecting an effective pre-trained dense retriever to use on a private collection.
MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
Specifically, we propose a Model Synergy (MOS) strategy that dynamically selects historical checkpoints with diverse knowledge and assembles them to best accommodate the current test batch.
DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
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.
Leveraging LLMs for Unsupervised Dense Retriever Ranking
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).
Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters
Overfitting to the source domain is a common issue in gradient-based training of deep neural networks.
Selecting which Dense Retriever to use for Zero-Shot Search
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.
KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection
Achieving a reliable LiDAR-based object detector in autonomous driving is paramount, but its success hinges on obtaining large amounts of precise 3D annotations.
Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection.
Exploring Active 3D Object Detection from a Generalization Perspective
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.
How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability
This paper focuses on model transferability estimation, i. e., assessing the performance of pre-trained models on a downstream task without performing fine-tuning.
Center-aware Adversarial Augmentation for Single Domain Generalization
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.
Ranked #3 on
Single-Source Domain Generalization
on Digits-five
DI-NIDS: Domain Invariant Network Intrusion Detection System
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.
Rethinking Persistent Homology for Visual Recognition
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.
Source-Free Progressive Graph Learning for Open-Set Domain Adaptation
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.
Conditional Extreme Value Theory for Open Set Video Domain Adaptation
The majority of video domain adaptation algorithms are proposed for closed-set scenarios in which all the classes are shared among the domains.
Learning to Diversify for Single Domain Generalization
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.
Ranked #7 on
Single-Source Domain Generalization
on Digits-five
Going Deeper into Semi-supervised Person Re-identification
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.
Learning Compositional Shape Priors for Few-Shot 3D Reconstruction
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.
Neural-Symbolic Commonsense Reasoner with Relation Predictors
The dynamic nature of commonsense knowledge postulates models capable of performing multi-hop reasoning over new situations.
Semi-supervised Keypoint Localization
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.
Learning to Generate the Unknowns for Open-set Domain Adaptation
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 Adaptative Causality Encoder
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
Causal relationships form the basis for reasoning and decision-making in Artificial Intelligence systems.
Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph
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.
COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering
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.
Keypoint-Aligned Embeddings for Image Retrieval and Re-identification
Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification.
Adversarial Bipartite Graph Learning for Video Domain Adaptation
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.
Ranked #3 on
Domain Adaptation
on HMDB --> UCF (full)
Progressive Graph Learning for Open-Set Domain Adaptation
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.
A Simple and Scalable Shape Representation for 3D Reconstruction
Deep learning applied to the reconstruction of 3D shapes has seen growing interest.
Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors
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.
Implicitly Defined Layers in Neural Networks
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
Our method outperforms the same model without body landmarks input by 26% and 18% on the synthetic and the real datasets respectively.
Correlation-aware Adversarial Domain Adaptation and Generalization
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.
Ranked #16 on
Domain Adaptation
on ImageCLEF-DA
Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling
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.
Robust Re-identification of Manta Rays from Natural Markings by Learning Pose Invariant Embeddings
We present a novel system for visual re-identification based on unique natural markings that is robust to occlusions, viewpoint and illumination changes.
Deep Level Sets: Implicit Surface Representations for 3D Shape Inference
This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"
On Minimum Discrepancy Estimation for Deep Domain Adaptation
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.
Multi-component Image Translation for Deep Domain Generalization
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.
Ranked #125 on
Domain Generalization
on PACS
Learning Factorized Representations for Open-set Domain Adaptation
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.
On Encoding Temporal Evolution for Real-time Action Prediction
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
In this work, we explore using statistical dependence measures for textual classification, representing text as word vectors.
Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs
State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution.
Domain Adaptation on the Statistical Manifold
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.
