Anh-Dzung Doan

Anh-Dzung Doan, Bach Long Nguyen, Surabhi Gupta et al.

To ensure reliable object detection in autonomous systems, the detector must be able to adapt to changes in appearance caused by environmental factors such as time of day, weather, and seasons. Continually adapting the detector to incorporate these changes is a promising solution, but it can be computationally costly. Our proposed approach is to selectively adapt the detector only when necessary, using new data that does not have the same distribution as the current training data. To this end, we investigate three popular metrics for domain gap evaluation and find that there is a correlation between the domain gap and detection accuracy. Therefore, we apply the domain gap as a criterion to decide when to adapt the detector. Our experiments show that our approach has the potential to improve the efficiency of the detector's operation in real-world scenarios, where environmental conditions change in a cyclical manner, without sacrificing the overall performance of the detector. Our code is publicly available at https://github.com/dadung/DGE-CDA.

Anh-Dzung Doan, Vu Minh Hieu Phan, Surabhi Gupta et al.

Infrared imaging offers resilience against changing lighting conditions by capturing object temperatures. Yet, in few scenarios, its lack of visual details compared to daytime visible images, poses a significant challenge for human and machine interpretation. This paper proposes a novel diffusion method, dubbed Temporally Consistent Patch Diffusion Models (TC-DPM), for infrared-to-visible video translation. Our method, extending the Patch Diffusion Model, consists of two key components. Firstly, we propose a semantic-guided denoising, leveraging the strong representations of foundational models. As such, our method faithfully preserves the semantic structure of generated visible images. Secondly, we propose a novel temporal blending module to guide the denoising trajectory, ensuring the temporal consistency between consecutive frames. Experiment shows that TC-PDM outperforms state-of-the-art methods by 35.3% in FVD for infrared-to-visible video translation and by 6.1% in AP50 for day-to-night object detection. Our code is publicly available at https://github.com/dzungdoan6/tc-pdm

Anh-Dzung Doan, Bach Long Nguyen, Terry Lim et al.

Prior to deployment, an object detector is trained on a dataset compiled from a previous data collection campaign. However, the environment in which the object detector is deployed will invariably evolve, particularly in outdoor settings where changes in lighting, weather and seasons will significantly affect the appearance of the scene and target objects. It is almost impossible for all potential scenarios that the object detector may come across to be present in a finite training dataset. This necessitates continuous updates to the object detector to maintain satisfactory performance. Test-time domain adaptation techniques enable machine learning models to self-adapt based on the distributions of the testing data. However, existing methods mainly focus on fully automated adaptation, which makes sense for applications such as self-driving cars. Despite the prevalence of fully automated approaches, in some applications such as surveillance, there is usually a human operator overseeing the system's operation. We propose to involve the operator in test-time domain adaptation to raise the performance of object detection beyond what is achievable by fully automated adaptation. To reduce manual effort, the proposed method only requires the operator to provide weak labels, which are then used to guide the adaptation process. Furthermore, the proposed method can be performed in a streaming setting, where each online sample is observed only once. We show that the proposed method outperforms existing works, demonstrating a great benefit of human-in-the-loop test-time domain adaptation. Our code is publicly available at https://github.com/dzungdoan6/WSTTA

Andrew Du, Anh-Dzung Doan, Yee Wei Law et al.

The advent of satellite-borne machine learning hardware accelerators has enabled the on-board processing of payload data using machine learning techniques such as convolutional neural networks (CNN). A notable example is using a CNN to detect the presence of clouds in hyperspectral data captured on Earth observation (EO) missions, whereby only clear sky data is downlinked to conserve bandwidth. However, prior to deployment, new missions that employ new sensors will not have enough representative datasets to train a CNN model, while a model trained solely on data from previous missions will underperform when deployed to process the data on the new missions. This underperformance stems from the domain gap, i.e., differences in the underlying distributions of the data generated by the different sensors in previous and future missions. In this paper, we address the domain gap problem in the context of on-board hyperspectral cloud detection. Our main contributions lie in formulating new domain adaptation tasks that are motivated by a concrete EO mission, developing a novel algorithm for bandwidth-efficient supervised domain adaptation, and demonstrating test-time adaptation algorithms on space deployable neural network accelerators. Our contributions enable minimal data transmission to be invoked (e.g., only 1% of the weights in ResNet50) to achieve domain adaptation, thereby allowing more sophisticated CNN models to be deployed and updated on satellites without being hampered by domain gap and bandwidth limitations.

Anh-Dzung Doan, Michele Sasdelli, David Suter et al.

Fitting geometric models onto outlier contaminated data is provably intractable. Many computer vision systems rely on random sampling heuristics to solve robust fitting, which do not provide optimality guarantees and error bounds. It is therefore critical to develop novel approaches that can bridge the gap between exact solutions that are costly, and fast heuristics that offer no quality assurances. In this paper, we propose a hybrid quantum-classical algorithm for robust fitting. Our core contribution is a novel robust fitting formulation that solves a sequence of integer programs and terminates with a global solution or an error bound. The combinatorial subproblems are amenable to a quantum annealer, which helps to tighten the bound efficiently. While our usage of quantum computing does not surmount the fundamental intractability of robust fitting, by providing error bounds our algorithm is a practical improvement over randomised heuristics. Moreover, our work represents a concrete application of quantum computing in computer vision. We present results obtained using an actual quantum computer (D-Wave Advantage) and via simulation. Source code: https://github.com/dadung/HQC-robust-fitting

Anh-Dzung Doan, Yasir Latif, Tat-Jun Chin et al.

A major focus of current research on place recognition is visual localization for autonomous driving. In this scenario, as cameras will be operating continuously, it is realistic to expect videos as an input to visual localization algorithms, as opposed to the single-image querying approach used in other visual localization works. In this paper, we show that exploiting temporal continuity in the testing sequence significantly improves visual localization - qualitatively and quantitatively. Although intuitive, this idea has not been fully explored in recent works. To this end, we propose two filtering approaches to exploit the temporal smoothness of image sequences: i) filtering on discrete domain with Hidden Markov Model, and ii) filtering on continuous domain with Monte Carlo-based visual localization. Our approaches rely on local features with an encoding technique to represent an image as a single vector. The experimental results on synthetic and real datasets show that our proposed methods achieve better results than state of the art (i.e., deep learning-based pose regression approaches) for the task on visual localization under significant appearance change. Our synthetic dataset and source code are made publicly available at https://sites.google.com/view/g2d-software/home and https://github.com/dadung/Visual-Localization-Filtering.

Tam Ngoc-Bang Nguyen, Anh-Dzung Doan, Zhipeng Cai et al.

Robust fitting of geometric models is a fundamental task in many computer vision pipelines. Numerous innovations have been produced on the topic, from improving the efficiency and accuracy of random sampling heuristics to generating novel theoretical insights that underpin new approaches with mathematical guarantees. However, one aspect of robust fitting that has received little attention is energy efficiency. This performance metric has become critical as high energy consumption is a growing concern for AI adoption. In this paper, we explore energy-efficient robust fitting via the neuromorphic computing paradigm. Specifically, we designed a novel spiking neural network for robust fitting on real neuromorphic hardware, the Intel Loihi 2. Enabling this are novel event-driven formulations of model estimation that allow robust fitting to be implemented in the unique architecture of Loihi 2, and algorithmic strategies to alleviate the current limited precision and instruction set of the hardware. Results show that our neuromorphic robust fitting consumes only a fraction (15%) of the energy required to run the established robust fitting algorithm on a standard CPU to equivalent accuracy.

Ryan Faulkner, Luke Haub, Simon Ratcliffe et al.

By enabling capturing of 3D point clouds that reflect the geometry of the immediate environment, LiDAR has emerged as a primary sensor for autonomous systems. If a LiDAR scan is too sparse, occluded by obstacles, or too small in range, enhancing the point cloud scan by while respecting the geometry of the scene is useful for downstream tasks. Motivated by the explosive growth of interest in generative methods in vision, conditional LiDAR generation is starting to take off. This paper proposes a novel simultaneous diffusion sampling methodology to generate point clouds conditioned on the 3D structure of the scene as seen from multiple views. The key idea is to impose multi-view geometric constraints on the generation process, exploiting mutual information for enhanced results. Our method begins by recasting the input scan to multiple new viewpoints around the scan, thus creating multiple synthetic LiDAR scans. Then, the synthetic and input LiDAR scans simultaneously undergo conditional generation according to our methodology. Results show that our method can produce accurate and geometrically consistent enhancements to point cloud scans, allowing it to outperform existing methods by a large margin in a variety of benchmarks.

Ragav Sachdeva, Ravi Hammond, James Bockman et al.

Future Moon bases will likely be constructed using resources mined from the surface of the Moon. The difficulty of maintaining a human workforce on the Moon and communications lag with Earth means that mining will need to be conducted using collaborative robots with a high degree of autonomy. In this paper, we describe our solution for Phase 2 of the NASA Space Robotics Challenge, which provided a simulated lunar environment in which teams were tasked to develop software systems to achieve autonomous collaborative robots for mining on the Moon. Our 3rd place and innovation award winning solution shows how machine learning-enabled vision could alleviate major challenges posed by the lunar environment towards autonomous space mining, chiefly the lack of satellite positioning systems, hazardous terrain, and delicate robot interactions. A robust multi-robot coordinator was also developed to achieve long-term operation and effective collaboration between robots.

Anh-Dzung Doan, Daniyar Turmukhambetov, Yasir Latif et al.

Many robotics applications require interest points that are highly repeatable under varying viewpoints and lighting conditions. However, this requirement is very challenging as the environment changes continuously and indefinitely, leading to appearance changes of interest points with respect to time. This paper proposes to predict the repeatability of an interest point as a function of time, which can tell us the lifespan of the interest point considering daily or seasonal variation. The repeatability predictor (RP) is formulated as a regressor trained on repeated interest points from multiple viewpoints over a long period of time. Through comprehensive experiments, we demonstrate that our RP can estimate when a new interest point is repeated, and also highlight an insightful analysis about this problem. For further comparison, we apply our RP to the map summarization under visual localization framework, which builds a compact representation of the full context map given the query time. The experimental result shows a careful selection of potentially repeatable interest points predicted by our RP can significantly mitigate the degeneration of localization accuracy from map summarization.

Anh-Dzung Doan, Yasir Latif, Tat-Jun Chin et al.

Visual place recognition needs to be robust against appearance variability due to natural and man-made causes. Training data collection should thus be an ongoing process to allow continuous appearance changes to be recorded. However, this creates an unboundedly-growing database that poses time and memory scalability challenges for place recognition methods. To tackle the scalability issue for visual place recognition in autonomous driving, we develop a Hidden Markov Model approach with a two-tiered memory management. Our algorithm, dubbed HM$^4$, exploits temporal look-ahead to transfer promising candidate images between passive storage and active memory when needed. The inference process takes into account both promising images and a coarse representations of the full database. We show that this allows constant time and space inference for a fixed coverage area. The coarse representations can also be updated incrementally to absorb new data. To further reduce the memory requirements, we derive a compact image representation inspired by Locality Sensitive Hashing (LSH). Through experiments on real world data, we demonstrate the excellent scalability and accuracy of the approach under appearance changes and provide comparisons against state-of-the-art techniques.

Yu Liu, Yutong Dai, Anh-Dzung Doan et al.

As a milestone for video object segmentation, one-shot video object segmentation (OSVOS) has achieved a large margin compared to the conventional optical-flow based methods regarding to the segmentation accuracy. Its excellent performance mainly benefit from the three-step training mechanism, that are: (1) acquiring object features on the base dataset (i.e. ImageNet), (2) training the parent network on the training set of the target dataset (i.e. DAVIS-2016) to be capable of differentiating the object of interest from the background. (3) online fine-tuning the interested object on the first frame of the target test set to overfit its appearance, then the model can be utilized to segment the same object in the rest frames of that video. In this paper, we argue that for the step (2), OSVOS has the limitation to 'overemphasize' the generic semantic object information while 'dilute' the instance cues of the object(s), which largely block the whole training process. Through adding a common module, video loss, which we formulate with various forms of constraints (including weighted BCE loss, high-dimensional triplet loss, as well as a novel mixed instance-aware video loss), to train the parent network in the step (2), the network is then better prepared for the step (3), i.e. online fine-tuning on the target instance. Through extensive experiments using different network structures as the backbone, we show that the proposed video loss module can improve the segmentation performance significantly, compared to that of OSVOS. Meanwhile, since video loss is a common module, it can be generalized to other fine-tuning based methods and similar vision tasks such as depth estimation and saliency detection.

Anh-Dzung Doan, Yasir Latif, Tat-Jun Chin et al.

A major challenge in place recognition for autonomous driving is to be robust against appearance changes due to short-term (e.g., weather, lighting) and long-term (seasons, vegetation growth, etc.) environmental variations. A promising solution is to continuously accumulate images to maintain an adequate sample of the conditions and incorporate new changes into the place recognition decision. However, this demands a place recognition technique that is scalable on an ever growing dataset. To this end, we propose a novel place recognition technique that can be efficiently retrained and compressed, such that the recognition of new queries can exploit all available data (including recent changes) without suffering from visible growth in computational cost. Underpinning our method is a novel temporal image matching technique based on Hidden Markov Models. Our experiments show that, compared to state-of-the-art techniques, our method has much greater potential for large-scale place recognition for autonomous driving.

Anh-Dzung Doan, Abdul Mohsi Jawaid, Thanh-Toan Do et al.

This document describes G2D, a software that enables capturing videos from Grand Theft Auto V (GTA V), a popular role playing game set in an expansive virtual city. The target users of our software are computer vision researchers who wish to collect hyper-realistic computer-generated imagery of a city from the street level, under controlled 6DOF camera poses and varying environmental conditions (weather, season, time of day, traffic density, etc.). G2D accesses/calls the native functions of the game; hence users can directly interact with G2D while playing the game. Specifically, G2D enables users to manipulate conditions of the virtual environment on the fly, while the gameplay camera is set to automatically retrace a predetermined 6DOF camera pose trajectory within the game coordinate system. Concurrently, automatic screen capture is executed while the virtual environment is being explored. G2D and its source code are publicly available at https://goo.gl/SS7fS6 In addition, we demonstrate an application of G2D to generate a large-scale dataset with groundtruth camera poses for testing structure-from-motion (SfM) algorithms. The dataset and generated 3D point clouds are also made available at https://goo.gl/DNzxHx

Ngoc-Trung Tran, Dang-Khoa Le Tan, Anh-Dzung Doan et al.

We present the design of an entire on-device system for large-scale urban localization using images. The proposed design integrates compact image retrieval and 2D-3D correspondence search to estimate the location in extensive city regions. Our design is GPS agnostic and does not require network connection. In order to overcome the resource constraints of mobile devices, we propose a system design that leverages the scalability advantage of image retrieval and accuracy of 3D model-based localization. Furthermore, we propose a new hashing-based cascade search for fast computation of 2D-3D correspondences. In addition, we propose a new one-many RANSAC for accurate pose estimation. The new one-many RANSAC addresses the challenge of repetitive building structures (e.g. windows, balconies) in urban localization. Extensive experiments demonstrate that our 2D-3D correspondence search achieves state-of-the-art localization accuracy on multiple benchmark datasets. Furthermore, our experiments on a large Google Street View (GSV) image dataset show the potential of large-scale localization entirely on a typical mobile device.

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.

Thanh-Toan Do, Anh-Dzung Doan, Duc-Thanh Nguyen et al.

This paper proposes two approaches for inferencing binary codes in two-step (supervised, unsupervised) hashing. We first introduce an unified formulation for both supervised and unsupervised hashing. Then, we cast the learning of one bit as a Binary Quadratic Problem (BQP). We propose two approaches to solve BQP. In the first approach, we relax BQP as a semidefinite programming problem which its global optimum can be achieved. We theoretically prove that the objective value of the binary solution achieved by this approach is well bounded. In the second approach, we propose an augmented Lagrangian based approach to solve BQP directly without relaxing the binary constraint. Experimental results on three benchmark datasets show that our proposed methods compare favorably with the state of the art.

Thanh-Toan Do, Anh-Dzung Doan, Ngai-Man Cheung

This work proposes deep network models and learning algorithms for unsupervised and supervised binary hashing. Our novel network design constrains one hidden layer to directly output the binary codes. This addresses a challenging issue in some previous works: optimizing non-smooth objective functions due to binarization. Moreover, we incorporate independence and balance properties in the direct and strict forms in the learning. Furthermore, we include similarity preserving property in our objective function. Our resulting optimization with these binary, independence, and balance constraints is difficult to solve. We propose to attack it with alternating optimization and careful relaxation. Experimental results on three benchmark datasets show that our proposed methods compare favorably with the state of the art.