Search Results for author:
Found 18 papers, 11 papers with code
Task Progressive Curriculum Learning for Robust Visual Question Answering
In this work, we show for the first time that robust Visual Question Answering is attainable by simply enhancing the training strategy.
Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models
Test-time adaptation (TTA) of 3D point clouds is crucial for mitigating discrepancies between training and testing samples in real-world scenarios, particularly when handling corrupted point clouds.
Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor
This paper introduces a new method to tackle the Few-Shot Continual Incremental Learning (FSCIL) problem in 3D point cloud environments.
class-incremental learning
Few-Shot Class-Incremental Learning
+1
3D Point Cloud Network Pruning: When Some Weights Do not Matter
The adoption of deep neural networks referred to as Point Cloud Neural Networks (PC- NNs), for processing 3D point clouds, has significantly advanced fields that rely on 3D geometric data to enhance the efficiency of tasks.
Backpropagation-free Network for 3D Test-time Adaptation
Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data.
ChatGPT-guided Semantics for Zero-shot Learning
Then, we enrich word vectors by combining the word embeddings from class names and descriptions generated by ChatGPT.
LumiNet: The Bright Side of Perceptual Knowledge Distillation
In knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models.
Ranked #1 on
Classification
on CIFAR-100
Continual Test-time Domain Adaptation via Dynamic Sample Selection
DSS consists of dynamic thresholding, positive learning, and negative learning processes.
Prompt-guided Scene Generation for 3D Zero-Shot Learning
To address this problem, we propose a prompt-guided 3D scene generation and supervision method that augments 3D data to learn the network better, exploring the complex interplay of seen and unseen objects.
Few-shot Class-incremental Learning for 3D Point Cloud Objects
Few-shot class-incremental learning (FSCIL) aims to incrementally fine-tune a model (trained on base classes) for a novel set of classes using a few examples without forgetting the previous training.
class-incremental learning
Few-Shot Class-Incremental Learning
+1
Learning without Forgetting for 3D Point Cloud Objects
Experimenting on three 3D point cloud recognition backbones (PointNet, DGCNN, and PointConv) and synthetic (ModelNet40, ModelNet10) and real scanned (ScanObjectNN) datasets, we establish new baseline results on learning without forgetting for 3D data.
Zero-Shot Learning on 3D Point Cloud Objects and Beyond
Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification.
Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner.
class-incremental learning
Few-Shot Class-Incremental Learning
+3
Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of Subspaces
In this paper, we propose addressing this problem using a mixture of subspaces.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
Transductive Zero-Shot Learning for 3D Point Cloud Classification
This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification.
Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
In this paper, we therefore propose a loss to specifically address the hubness problem.
Zero-shot Learning of 3D Point Cloud Objects
A challenge for a 3D point cloud recognition system is, then, to classify objects from new, unseen, classes.
3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds
This paper introduces the 3DCapsule, which is a 3D extension of the recently introduced Capsule concept that makes it applicable to unordered point sets.
