Ali Cheraghian

dblp:03/9794 · DBLP profile ↗
← Back
18ranked-venue papers
8as first author
13since 2021 · last 2026
0000-0002-3324-7849ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Graphics, computer vision, multimedia, augmented reality and games · 15 · 7 first-author · 11 since 2021Artificial intelligence and machine learning · 12 · 5 first-author · 10 since 2021
YearPublicationVenuePosition
2026 Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation Models
abstract
3D Vision-Language Foundation Models (VLFMs) have demonstrated strong generalization and zero-shot recognition capabilities in open-world point cloud processing tasks. However, their performance often degrades in practical scenarios where data are noisy, incomplete, or drawn from distributions that differ from the training data. To address this challenge, we propose Uni-Adapter, a novel training-free online test-time adaptation (TTA) strategy for 3D VLFMs based on dynamic prototype learning. Uni-Adapter maintains a 3D cache that stores class-specific cluster centers as prototypes, which are continuously updated to capture intra-class variability under heterogeneous data distributions. These dynamic prototypes serve as anchors for cache-based logit computation through similarity scoring. In parallel, a graph-based label smoothing module models inter-prototype similarities to enforce label consistency among related prototypes. Finally, predictions from the original 3D VLFM and the refined 3D cache are unified through entropy-weighted aggregation to ensure reliable adaptation. Without retraining, Uni-Adapter effectively mitigates distribution shifts and achieves state-of-the-art performance across diverse 3D benchmarks and multiple 3D VLFMs, improving performance on ModelNet-40C by 10.55%, ScanObjectNN-C by 8.26%, and ShapeNet-C by 4.49% over the source 3D VLFMs.
Mehran Tamjidi, Hamidreza Dastmalchi, Mohammadreza Alimoradijazi, Ali Cheraghian, Aijun An, Morteza Saberi
AAAI4
2026 Subspace-Guided Knowledge Distillation for Efficient Model Transfer
abstract
Compact models can be effectively trained via Knowledge Distillation (KD), where a lightweight student model learns to replicate the behavior of a larger, high-performing teacher. A persistent challenge in KD lies in the misalignment between the representational spaces of teacher and student networks, especially when they differ in architecture or capacity. To address this, we propose Subspace-Driven Knowledge Distillation (SDMD), a novel framework that mitigates representational disparity by projecting features into an indefinite inner product space. This relaxation from traditional Hilbert spaces enables more flexible geometric alignment, capturing transformations such as rotations and reflections that are often necessary for accurate knowledge transfer. By learning a subspace that bridges the semantic gap between teacher and student, SDMD facilitates more effective distillation without increasing model complexity. We validate SDMD through extensive experiments on large-scale image classification (ImageNet-1K) and object detection (COCO), where it consistently outperforms existing distillation methods. Notably, SDMD-trained models not only achieve state-of-the-art results in distilled settings but also surpass the performance of equivalent models trained from scratch, highlighting the strength of our subspace-based alignment strategy.
Zeeshan Hayder, Ali Cheraghian, Lars Petersson, Mehrtash Harandi
WACV2
2025 Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models
abstract
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. LiDAR data, for instance, can be affected by sensor failures or environmental factors, causing domain gaps. Adapting models to these distribution shifts online is crucial, as training for every possible variation is impractical. Existing methods often focus on fine-tuning pre-trained models based on self-supervised learning or pseudo-labeling, which can lead to forgetting valuable source domain knowledge over time and reduce generalization on future tests. In this paper, we introduce a novel 3D test-time adaptation method, termed 3DD-TTA, which stands for 3D Denoising Diffusion Test-Time Adaptation. This method uses a diffusion strategy that adapts input point cloud samples to the source domain while keeping the source model parameters intact. The approach uses a Variational Autoencoder (VAE) to encode the corrupted point cloud into a shape latent and latent points. These latent points are corrupted with Gaussian noise and subjected to a denoising diffusion process. During this process, both the shape latent and latent points are updated to preserve fidelity, guiding the denoising toward generating consistent samples that align more closely with the source domain. We conduct extensive experiments on the ShapeNet dataset and investigate its generalizability on ModelNet40 and ScanObjectNN, achieving state-of-the-art results. The code has been released at https://github.com/hamidreza-dastmalchi/3DD-Tta.
Hamidreza Dastmalchi, Aijun An, Ali Cheraghian, Shafin Rahman, Sameera Ramasinghe
WACV3
2024 Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-Free Adaptor
Sahar Ahmadi, Ali Cheraghian, Morteza Saberi, Md. Towsif Abir, Hamidreza Dastmalchi, Farookh Khadeer Hussain, Shafin Rahman
ACCV (10)2
2024 3D Point Cloud Network Pruning: When Some Weights Do not Matter
Amrijit Biswas, Mirza M. Lutfe Elahi, Ali Cheraghian, Fuad Rahman 0001, Nabeel Mohammed, Shafin Rahman
BMVC4
2024 Backpropagation-free Network for 3D Test-time Adaptation
abstract
Real-world systems often encounter new data over time, which leads to experiencing target domain shifts. Existing Test- Time Adaptation (TTA) methods tend to apply computationally heavy and memory-intensive backpropagation-based approaches to handle this. Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data. Our model uses a two-stream architecture to maintain knowledge about the source domain as well as complementary target-domain-specific information. The backpropagation-free property of our model helps address the well-known forgetting prob-lem and mitigates the error accumulation issue. The pro-posed method also eliminates the need for the usually noisy process of pseudo-labeling and reliance on costly self-supervised training. Moreover, our method leverages sub-space learning, effectively reducing the distribution vari-ance between the two domains. Furthermore, the source-domain-specific and the target-domain-specific streams are aligned using a novel entropy-based adaptive fusion strat-egy. Extensive experiments on popular benchmarks demon-strate the effectiveness of our method. The code will be available at https://github.com/abie-e/BFTT3D.
Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder, Sameera Ramasinghe, Shafin Rahman, David Ahmedt-Aristizabal, Xuesong Li 0001, Lars Petersson, Mehrtash Harandi
CVPR2
2024 Canonical Shape Projection Is All You Need for 3D Few-Shot Class Incremental Learning
Ali Cheraghian, Zeeshan Hayder, Sameera Ramasinghe, Shafin Rahman, Javad Jafaryahya, Lars Petersson, Mehrtash Harandi
ECCV (41)1
2024 Continual Test-time Domain Adaptation via Dynamic Sample Selection
abstract
The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This paper proposes a Dynamic Sample Selection (DSS) method for CTDA. DSS consists of dynamic thresholding, positive learning, and negative learning processes. Traditionally, models learn from unlabeled unknown environment data and equally rely on all samples’ pseudo-labels to update their parameters through self-training. However, noisy predictions exist in these pseudo-labels, so all samples are not equally trustworthy. Therefore, in our method, a dynamic thresholding module is first designed to select suspected low-quality from high-quality samples. The selected low-quality samples are more likely to be wrongly predicted. Therefore, we apply joint positive and negative learning on both high- and low-quality samples to reduce the risk of using wrong information. We conduct extensive experiments that demonstrate the effectiveness of our proposed method for CTDA in the image domain, outperforming the state-of-the-art results. Furthermore, our approach is also evaluated in the 3D point cloud domain, showcasing its versatility and potential for broader applicability.
Yanshuo Wang, Ali Cheraghian, Shafin Rahman, David Ahmedt-Aristizabal, Lars Petersson, Mehrtash Harandi
WACV3
2024 3D scene generation for zero-shot learning using ChatGPT guided language prompts
Sahar Ahmadi, Ali Cheraghian, Townim F. Chowdhury, Morteza Saberi, Shafin Rahman
Comput. Vis. Image Underst.2
2022 Few-Shot Class-Incremental Learning for 3D Point Cloud Objects
Townim F. Chowdhury, Ali Cheraghian, Sameera Ramasinghe, Sahar Ahmadi, Morteza Saberi, Shafin Rahman
ECCV (20)2
2022 Zero-Shot Learning on 3D Point Cloud Objects and Beyond
Ali Cheraghian, Shafin Rahman, Townim F. Chowdhury, Dylan Campbell, Lars Petersson
Int. J. Comput. Vis.1
2021 Semantic-Aware Knowledge Distillation for Few-Shot Class-Incremental Learning
abstract
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. Due to the limited number of examples for training, the techniques developed for standard incremental learning cannot be applied verbatim to FSCIL. In this work, we introduce a distillation algorithm to address the problem of FSCIL and propose to make use of semantic information during training. To this end, we make use of word embeddings as semantic information which is cheap to obtain and which facilitate the distillation process. Furthermore, we propose a method based on an attention mechanism on multiple parallel embeddings of visual data to align visual and semantic vectors, which reduces issues related to catastrophic forgetting. Via experiments on MiniImageNet, CUB200, and CIFAR100 dataset, we establish new state-of-the-art results by outperforming existing approaches.
Ali Cheraghian, Shafin Rahman, Pengfei Fang, Soumava Kumar Roy, Lars Petersson, Mehrtash Harandi
CVPR1
2021 Synthesized Feature based Few-Shot Class-Incremental Learning on a Mixture of Subspaces
abstract
Few-shot class incremental learning (FSCIL) aims to incrementally add sets of novel classes to a well-trained base model in multiple training sessions with the restriction that only a few novel instances are available per class. While learning novel classes, FSCIL methods gradually forget base (old) class training and overfit to a few novel class samples. Existing approaches have addressed this problem by computing the class prototypes from the visual or semantic word vector domain. In this paper, we propose addressing this problem using a mixture of subspaces. Subspaces define the cluster structure of the visual domain and help to describe the visual and semantic domain considering the overall distribution of the data. Additionally, we propose to employ a variational autoencoder (VAE) to generate synthesized visual samples for augmenting pseudo-feature while learning novel classes incrementally. The combined effect of the mixture of subspaces and synthesized features reduces the forgetting and overfitting problem of FSCIL. Extensive experiments on three image classification datasets show that our proposed method achieves competitive results compared to state-of-the-art methods.
Ali Cheraghian, Shafin Rahman, Sameera Ramasinghe, Pengfei Fang, Christian Simon, Lars Petersson, Mehrtash Harandi
ICCV1
2020 Transductive Zero-Shot Learning for 3D Point Cloud Classification
abstract
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. However despite the increasing ubiquity of 3D sensors, the corresponding 3D point cloud classification problem has not been meaningfully explored and introduces new challenges. This paper extends, for the first time, transductive ZeroShot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification. To this end, a novel triplet loss is developed that takes advantage of unlabeled test data. While designed for the task of 3D point cloud classification, the method is also shown to be applicable to the more common use-case of 2D image classification. An extensive set of experiments is carried out, establishing state-of-the-art for ZSL and GZSL in the 3D point cloud domain, as well as demonstrating the applicability of the approach to the image domain.1
Ali Cheraghian, Shafin Rahman, Dylan Campbell, Lars Petersson
WACV1
2019 Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
Ali Cheraghian, Shafin Rahman, Dylan Campbell, Lars Petersson
BMVC1
2019 3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds
abstract
This paper introduces the 3DCapsule, which is a 3D extension of the recently introduced Capsule concept that makes it applicable to unordered point sets. The original Capsule relies on the existence of a spatial relationship between the elements in the feature map it is presented with, whereas in point permutation invariant formulations of 3D point set classification methods, such relationships are typically lost. Here, a new layer called ComposeCaps is introduced that, in lieu of a spatially relevant feature mapping, learns a new mapping that can be exploited by the 3DCapsule. Previous works in the 3D point set classification domain have focused on other parts of the architecture, whereas instead, the 3DCapsule is a drop-in replacement of the commonly used fully connected classifier. It is demonstrated via an ablation study, that when the 3DCapsule is applied to recent 3D point set classification architectures, it consistently shows an improvement, in particular when subjected to noisy data. Similarly, the ComposeCaps layer is evaluated and demonstrates an improvement over the baseline. In an apples-to-apples comparison against state-of-the-art methods, again, better performance is demonstrated by the 3DCapsule.
Ali Cheraghian, Lars Petersson
WACV1
2017 Surface geodesic pattern for 3D deformable texture matching
Farshid Hajati, Ali Cheraghian, Soheila Gheisari, Yongsheng Gao 0001, Ajmal Mian
Pattern Recognit.2
2013 3D face recognition using topographic high-order derivatives
abstract
This paper presents a novel feature, Topographic High-order Derivatives (THD) for 3D face recognition. THD is based on the high-order micro-pattern information extracted from face topography maps. Face topography maps are partitioned into polar sectors, and THDs are computed using directional highorder derivatives within the sectors. Local features are extracted by encoding directional high-order derivatives within polar neighborhoods. To evaluate the proposed method, we use Bosphorus and FRGC 3D face databases which include pose and expression changes. The performance of the proposed method is higher compared to the state-of-the-art benchmark approaches in 3D face recognition.
Ali Cheraghian, Farshid Hajati, Ajmal Mian, Yongsheng Gao 0001, Soheila Gheisari
ICIP1