Tuan Hoang

Cuong Pham, Tuan Hoang, Thanh-Toan Do

Knowledge distillation which learns a lightweight student model by distilling knowledge from a cumbersome teacher model is an attractive approach for learning compact deep neural networks (DNNs). Recent works further improve student network performance by leveraging multiple teacher networks. However, most of the existing knowledge distillation-based multi-teacher methods use separately pretrained teachers. This limits the collaborative learning between teachers and the mutual learning between teachers and student. Network quantization is another attractive approach for learning compact DNNs. However, most existing network quantization methods are developed and evaluated without considering multi-teacher support to enhance the performance of quantized student model. In this paper, we propose a novel framework that leverages both multi-teacher knowledge distillation and network quantization for learning low bit-width DNNs. The proposed method encourages both collaborative learning between quantized teachers and mutual learning between quantized teachers and quantized student. During learning process, at corresponding layers, knowledge from teachers will form an importance-aware shared knowledge which will be used as input for teachers at subsequent layers and also be used to guide student. Our experimental results on CIFAR100 and ImageNet datasets show that the compact quantized student models trained with our method achieve competitive results compared to other state-of-the-art methods, and in some cases, indeed surpass the full precision models.

Tuan Hoang, Santu Rana, Sunil Gupta et al.

Recent data-privacy laws have sparked interest in machine unlearning, which involves removing the effect of specific training samples from a learnt model as if they were never present in the original training dataset. The challenge of machine unlearning is to discard information about the ``forget'' data in the learnt model without altering the knowledge about the remaining dataset and to do so more efficiently than the naive retraining approach. To achieve this, we adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU), in which the model takes steps in the orthogonal direction to the gradient subspaces deemed unimportant for the retaining dataset, so as to its knowledge is preserved. By utilizing Stochastic Gradient Descent (SGD) to update the model weights, our method can efficiently scale to any model and dataset size. We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible. Our code is available at https://github.com/hnanhtuan/projected_gradient_unlearning.

Duc Kieu, Kien Do, Tuan Hoang et al.

Multi-domain translation (MDT) aims to learn translations between multiple domains, yet existing approaches either require fully aligned tuples or can only handle domain pairs seen in training, limiting their practicality and excluding many cross-domain mappings. We introduce universal MDT (UMDT), a generalization of MDT that seeks to translate between any pair of $K$ domains using only $K-1$ paired datasets with a central domain. To tackle this problem, we propose Diffusion Router (DR), a unified diffusion-based framework that models all central$\leftrightarrow$non-central translations with a single noise predictor conditioned on the source and target domain labels. DR enables indirect non-central translations by routing through the central domain. We further introduce a novel scalable learning strategy with a variational-bound objective and an efficient Tweedie refinement procedure to support direct non-central mappings. Through evaluation on three large-scale UMDT benchmarks, DR achieves state-of-the-art results for both indirect and direct translations, while lowering sampling cost and unlocking novel tasks such as sketch$\leftrightarrow$segmentation. These results establish DR as a scalable and versatile framework for universal translation across multiple domains.

Mohammad Usman Altam, Md Imtiaz Habib, Tuan Hoang

Retrieval-Augmented Generation (RAG) represents a transformative approach within natural language processing (NLP), combining neural information retrieval with generative language modeling to enhance both contextual accuracy and factual reliability of responses. Unlike conventional Large Language Models (LLMs), which are constrained by static training corpora, RAG-powered systems dynamically integrate domain-specific external knowledge sources, thereby overcoming temporal and disciplinary limitations. In this study, we present the design and evaluation of a RAG-enabled system tailored for Mycophyto, with a focus on advancing agricultural applications related to arbuscular mycorrhizal fungi (AMF). These fungi play a critical role in sustainable agriculture by enhancing nutrient acquisition, improving plant resilience under abiotic and biotic stresses, and contributing to soil health. Our system operationalizes a dual-layered strategy: (i) semantic retrieval and augmentation of domain-specific content from agronomy and biotechnology corpora using vector embeddings, and (ii) structured data extraction to capture predefined experimental metadata such as inoculation methods, spore densities, soil parameters, and yield outcomes. This hybrid approach ensures that generated responses are not only semantically aligned but also supported by structured experimental evidence. To support scalability, embeddings are stored in a high-performance vector database, allowing near real-time retrieval from an evolving literature base. Empirical evaluation demonstrates that the proposed pipeline retrieves and synthesizes highly relevant information regarding AMF interactions with crop systems, such as tomato (Solanum lycopersicum). The framework underscores the potential of AI-driven knowledge discovery to accelerate agroecological innovation and enhance decision-making in sustainable farming systems.

Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen et al.

In this paper, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval. We proposed a novel method, dubbed Cross-Modal Info-Max Hashing (CMIMH). First, to learn informative representations that can preserve both intra- and inter-modal similarities, we leverage the recent advances in estimating variational lower-bound of MI to maximize the MI between the binary representations and input features and between binary representations of different modalities. By jointly maximizing these MIs under the assumption that the binary representations are modelled by multivariate Bernoulli distributions, we can learn binary representations, which can preserve both intra- and inter-modal similarities, effectively in a mini-batch manner with gradient descent. Furthermore, we find out that trying to minimize the modality gap by learning similar binary representations for the same instance from different modalities could result in less informative representations. Hence, balancing between reducing the modality gap and losing modality-private information is important for the cross-modal retrieval tasks. Quantitative evaluations on standard benchmark datasets demonstrate that the proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods.

Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen et al.

This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing quantization on the full-precision network weights. However, this approach would result in some mismatch: the gradient descent updates full-precision weights, but it does not update the quantized weights. To address this issue, we propose a novel method that enables {direct} updating of quantized weights {with learnable quantization levels} to minimize the cost function using gradient descent. Second, to obtain low bit-width activations, existing works consider all channels equally. However, the activation quantizers could be biased toward a few channels with high-variance. To address this issue, we propose a method to take into account the quantization errors of individual channels. With this approach, we can learn activation quantizers that minimize the quantization errors in the majority of channels. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on the image classification task, using AlexNet, ResNet and MobileNetV2 architectures on CIFAR-100 and ImageNet datasets.

Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen et al.

This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes for efficient cross-modal retrieval. The framework is a two-step hashing approach which decouples the optimization into (1) binary optimization and (2) hashing function learning. In the first step, we propose a novel spectral embedding-based algorithm to simultaneously learn single-modality and binary cross-modality representations. While the former is capable of well preserving the local structure of each modality, the latter reveals the hidden patterns from all modalities. In the second step, to learn mapping functions from informative data inputs (images and word embeddings) to binary codes obtained from the first step, we leverage the powerful CNN for images and propose a CNN-based deep architecture to learn text modality. Quantitative evaluations on three standard benchmark datasets demonstrate that the proposed DCSH method consistently outperforms other state-of-the-art methods.

Huu Le, Tuan Hoang, Michael Milford

Visual localization algorithms have achieved significant improvements in performance thanks to recent advances in camera technology and vision-based techniques. However, there remains one critical caveat: all current approaches that are based on image retrieval currently scale at best linearly with the size of the environment with respect to both storage, and consequentially in most approaches, query time. This limitation severely curtails the capability of autonomous systems in a wide range of compute, power, storage, size, weight or cost constrained applications such as drones. In this work, we present a novel binary tree encoding approach for visual localization which can serve as an alternative for existing quantization and indexing techniques. The proposed tree structure allows us to derive a compressed training scheme that achieves sub-linearity in both required storage and inference time. The encoding memory can be easily configured to satisfy different storage constraints. Moreover, our approach is amenable to an optional sequence filtering mechanism to further improve the localization results, while maintaining the same amount of storage. Our system is entirely agnostic to the front-end descriptors, allowing it to be used on top of recent state-of-the-art image representations. Experimental results show that the proposed method significantly outperforms state-of-the-art approaches under limited storage constraints.

Thanh-Toan Do, Khoa Le, Tuan Hoang et al.

Representing images by compact hash codes is an attractive approach for large-scale content-based image retrieval. In most state-of-the-art hashing-based image retrieval systems, for each image, local descriptors are first aggregated as a global representation vector. This global vector is then subjected to a hashing function to generate a binary hash code. In previous works, the aggregating and the hashing processes are designed independently. Hence these frameworks may generate suboptimal hash codes. In this paper, we first propose a novel unsupervised hashing framework in which feature aggregating and hashing are designed simultaneously and optimized jointly. Specifically, our joint optimization generates aggregated representations that can be better reconstructed by some binary codes. This leads to more discriminative binary hash codes and improved retrieval accuracy. In addition, the proposed method is flexible. It can be extended for supervised hashing. When the data label is available, the framework can be adapted to learn binary codes which minimize the reconstruction loss w.r.t. label vectors. Furthermore, we also propose a fast version of the state-of-the-art hashing method Binary Autoencoder to be used in our proposed frameworks. Extensive experiments on benchmark datasets under various settings show that the proposed methods outperform state-of-the-art unsupervised and supervised hashing methods.

Thanh-Toan Do, Toan Tran, Ian Reid et al.

We propose a method that substantially improves the efficiency of deep distance metric learning based on the optimization of the triplet loss function. One epoch of such training process based on a naive optimization of the triplet loss function has a run-time complexity O(N^3), where N is the number of training samples. Such optimization scales poorly, and the most common approach proposed to address this high complexity issue is based on sub-sampling the set of triplets needed for the training process. Another approach explored in the field relies on an ad-hoc linearization (in terms of N) of the triplet loss that introduces class centroids, which must be optimized using the whole training set for each mini-batch - this means that a naive implementation of this approach has run-time complexity O(N^2). This complexity issue is usually mitigated with poor, but computationally cheap, approximate centroid optimization methods. In this paper, we first propose a solid theory on the linearization of the triplet loss with the use of class centroids, where the main conclusion is that our new linear loss represents a tight upper-bound to the triplet loss. Furthermore, based on the theory above, we propose a training algorithm that no longer requires the centroid optimization step, which means that our approach is the first in the field with a guaranteed linear run-time complexity. We show that the training of deep distance metric learning methods using the proposed upper-bound is substantially faster than triplet-based methods, while producing competitive retrieval accuracy results on benchmark datasets (CUB-200-2011 and CAR196).

Huu Le, Thanh-Toan Do, Tuan Hoang et al.

This paper presents a novel randomized algorithm for robust point cloud registration without correspondences. Most existing registration approaches require a set of putative correspondences obtained by extracting invariant descriptors. However, such descriptors could become unreliable in noisy and contaminated settings. In these settings, methods that directly handle input point sets are preferable. Without correspondences, however, conventional randomized techniques require a very large number of samples in order to reach satisfactory solutions. In this paper, we propose a novel approach to address this problem. In particular, our work enables the use of randomized methods for point cloud registration without the need of putative correspondences. By considering point cloud alignment as a special instance of graph matching and employing an efficient semi-definite relaxation, we propose a novel sampling mechanism, in which the size of the sampled subsets can be larger-than-minimal. Our tight relaxation scheme enables fast rejection of the outliers in the sampled sets, resulting in high-quality hypotheses. We conduct extensive experiments to demonstrate that our approach outperforms other state-of-the-art methods. Importantly, our proposed method serves as a generic framework which can be extended to problems with known correspondences.

Huu Le, Tuan Hoang, Qianggong Zhang et al.

Visual localization has become a key enabling component of many place recognition and SLAM systems. Contemporary research has primarily focused on improving accuracy and precision-recall type metrics, with relatively little attention paid to a system's absolute storage scaling characteristics, its flexibility to adapt to available computational resources, and its longevity with respect to easily incorporating newly learned or hand-crafted image descriptors. Most significantly, improvement in one of these aspects typically comes at the cost of others: for example, a snapshot-based system that achieves sub-linear storage cost typically provides no metric pose estimation, or, a highly accurate pose estimation technique is often ossified in adapting to recent advances in appearance-invariant features. In this paper, we present a novel 6-DOF localization system that for the first time simultaneously achieves all the three characteristics: significantly sub-linear storage growth, agnosticism to image descriptors, and customizability to available storage and computational resources. The key features of our method are developed based on a novel adaptation of multiple-label learning, together with effective dimensional reduction and learning techniques that enable simple and efficient optimization. We evaluate our system on several large benchmarking datasets and provide detailed comparisons to state-of-the-art systems. The proposed method demonstrates competitive accuracy with existing pose estimation methods while achieving better sub-linear storage scaling, significantly reduced absolute storage requirements, and faster training and deployment speeds.

Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan et al.

Learning compact binary codes for image retrieval task using deep neural networks has attracted increasing attention recently. However, training deep hashing networks for the task is challenging due to the binary constraints on the hash codes, the similarity preserving property, and the requirement for a vast amount of labelled images. To the best of our knowledge, none of the existing methods has tackled all of these challenges completely in a unified framework. In this work, we propose a novel end-to-end deep learning approach for the task, in which the network is trained to produce binary codes directly from image pixels without the need of manual annotation. In particular, to deal with the non-smoothness of binary constraints, we propose a novel pairwise constrained loss function, which simultaneously encodes the distances between pairs of hash codes, and the binary quantization error. In order to train the network with the proposed loss function, we propose an efficient parameter learning algorithm. In addition, to provide similar / dissimilar training images to train the network, we exploit 3D models reconstructed from unlabelled images for automatic generation of enormous training image pairs. The extensive experiments on image retrieval benchmark datasets demonstrate the improvements of the proposed method over the state-of-the-art compact representation methods on the image retrieval problem.

Tuan Hoang, Thanh-Toan Do, Huu Le et al.

For unsupervised data-dependent hashing, the two most important requirements are to preserve similarity in the low-dimensional feature space and to minimize the binary quantization loss. A well-established hashing approach is Iterative Quantization (ITQ), which addresses these two requirements in separate steps. In this paper, we revisit the ITQ approach and propose novel formulations and algorithms to the problem. Specifically, we propose a novel approach, named Simultaneous Compression and Quantization (SCQ), to jointly learn to compress (reduce dimensionality) and binarize input data in a single formulation under strict orthogonal constraint. With this approach, we introduce a loss function and its relaxed version, termed Orthonormal Encoder (OnE) and Orthogonal Encoder (OgE) respectively, which involve challenging binary and orthogonal constraints. We propose to attack the optimization using novel algorithms based on recent advances in cyclic coordinate descent approach. Comprehensive experiments on unsupervised image retrieval demonstrate that our proposed methods consistently outperform other state-of-the-art hashing methods. Notably, our proposed methods outperform recent deep neural networks and GAN based hashing in accuracy, while being very computationally-efficient.

Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan et al.

In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations. Regarding the former requirement, Convolutional Neural Network (CNN) is proven to be a very powerful tool to extract highly discriminative local descriptors for effective image search. Additionally, in order to further improve the discriminative power of the descriptors, recent works adopt fine-tuned strategies. In this paper, taking a different approach, we propose a novel, computationally efficient, and competitive framework. Specifically, we firstly propose various strategies to compute masks, namely SIFT-mask, SUM-mask, and MAX-mask, to select a representative subset of local convolutional features and eliminate redundant features. Our in-depth analyses demonstrate that proposed masking schemes are effective to address the burstiness drawback and improve retrieval accuracy. Secondly, we propose to employ recent embedding and aggregating methods which can significantly boost the feature discriminability. Regarding the computation and storage efficiency, we include a hashing module to produce very compact binary image representations. Extensive experiments on six image retrieval benchmarks demonstrate that our proposed framework achieves the state-of-the-art retrieval performances.

Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan et al.

Learning compact binary codes for image retrieval problem using deep neural networks has recently attracted increasing attention. However, training deep hashing networks is challenging due to the binary constraints on the hash codes. In this paper, we propose deep network models and learning algorithms for learning binary hash codes given image representations under both unsupervised and supervised manners. The novelty of our network design is that we constrain one hidden layer to directly output the binary codes. This design has overcome a challenging problem in some previous works: optimizing non-smooth objective functions because of binarization. In addition, we propose to incorporate independence and balance properties in the direct and strict forms into the learning schemes. We also include a similarity preserving property in our objective functions. The resulting optimizations involving these binary, independence, and balance constraints are difficult to solve. To tackle this difficulty, we propose to learn the networks with alternating optimization and careful relaxation. Furthermore, by leveraging the powerful capacity of convolutional neural networks, we propose an end-to-end architecture that jointly learns to extract visual features and produce binary hash codes. Experimental results for the benchmark datasets show that the proposed methods compare favorably or outperform the state of the art.

Tuan Hoang, Thanh-Toan Do, Dang-Khoa Le Tan et al.

Convolutional Neural Network (CNN) is a very powerful approach to extract discriminative local descriptors for effective image search. Recent work adopts fine-tuned strategies to further improve the discriminative power of the descriptors. Taking a different approach, in this paper, we propose a novel framework to achieve competitive retrieval performance. Firstly, we propose various masking schemes, namely SIFT-mask, SUM-mask, and MAX-mask, to select a representative subset of local convolutional features and remove a large number of redundant features. We demonstrate that this can effectively address the burstiness issue and improve retrieval accuracy. Secondly, we propose to employ recent embedding and aggregating methods to further enhance feature discriminability. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art retrieval accuracy.

Tuan Hoang, Thanh-Toan Do, Dang-Khoa Le Tan et al.

We introduce a novel approach to improve unsupervised hashing. Specifically, we propose a very efficient embedding method: Gaussian Mixture Model embedding (Gemb). The proposed method, using Gaussian Mixture Model, embeds feature vector into a low-dimensional vector and, simultaneously, enhances the discriminative property of features before passing them into hashing. Our experiment shows that the proposed method boosts the hashing performance of many state-of-the-art, e.g. Binary Autoencoder (BA) [1], Iterative Quantization (ITQ) [2], in standard evaluation metrics for the three main benchmark datasets.