Unsupervised domain adaptation is one of the challenging problems in computer vision. This paper presents a novel approach to unsupervised domain adaptations based on the optimal transport-based distance. Our approach allows aligning target and source domains without the requirement of meaningful metrics across domains. In addition, the proposal can associate the correct mapping between source and target domains and guarantee a constraint of topology between source and target domains. The proposed method is evaluated on different datasets in various problems, i.e. (i) digit recognition on MNIST, MNIST-M, USPS datasets, (ii) Object recognition on Amazon, Webcam, DSLR, and VisDA datasets, (iii) Insect Recognition on the IP102 dataset. The experimental results show that our proposed method consistently improves performance accuracy. Also, our framework could be incorporated with any other CNN frameworks within an end-to-end deep network design for recognition problems to improve their performance.
Human action recognition has recently become one of the popular research topics in the computer vision community. Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in the task of video action recognition with competitive results. However, these methods have suffered some fundamental limitations such as lack of robustness and generalization, e.g., how does the temporal ordering of video frames affect the recognition results? This work presents a novel end-to-end Transformer-based Directed Attention (DirecFormer) framework for robust action recognition. The method takes a simple but novel perspective of Transformer-based approach to understand the right order of sequence actions. Therefore, the contributions of this work are three-fold. Firstly, we introduce the problem of ordered temporal learning issues to the action recognition problem. Secondly, a new Directed Attention mechanism is introduced to understand and provide attentions to human actions in the right order. Thirdly, we introduce the conditional dependency in action sequence modeling that includes orders and classes. The proposed approach consistently achieves the state-of-the-art (SOTA) results compared with the recent action recognition methods, on three standard large-scale benchmarks, i.e. Jester, Kinetics-400 and Something-Something-V2.
Semantic segmentation aims to predict pixel-level labels. It has become a popular task in various computer vision applications. While fully supervised segmentation methods have achieved high accuracy on large-scale vision datasets, they are unable to generalize on a new test environment or a new domain well. In this work, we first introduce a new Un-aligned Domain Score to measure the efficiency of a learned model on a new target domain in unsupervised manner. Then, we present the new Bijective Maximum Likelihood(BiMaL) loss that is a generalized form of the Adversarial Entropy Minimization without any assumption about pixel independence. We have evaluated the proposed BiMaL on two domains. The proposed BiMaL approach consistently outperforms the SOTA methods on empirical experiments on "SYNTHIA to Cityscapes", "GTA5 to Cityscapes", and "SYNTHIA to Vistas".
Turn-taking has played an essential role in structuring the regulation of a conversation. The task of identifying the main speaker (who is properly taking his/her turn of speaking) and the interrupters (who are interrupting or reacting to the main speaker's utterances) remains a challenging task. Although some prior methods have partially addressed this task, there still remain some limitations. Firstly, a direct association of Audio and Visual features may limit the correlations to be extracted due to different modalities. Secondly, the relationship across temporal segments helping to maintain the consistency of localization, separation, and conversation contexts is not effectively exploited. Finally, the interactions between speakers that usually contain the tracking and anticipatory decisions about the transition to a new speaker are usually ignored. Therefore, this work introduces a new Audio-Visual Transformer approach to the problem of localization and highlighting the main speaker in both audio and visual channels of a multi-speaker conversation video in the wild. The proposed method exploits different types of correlations presented in both visual and audio signals. The temporal audio-visual relationships across spatial-temporal space are anticipated and optimized via the self-attention mechanism in a Transformerstructure. Moreover, a newly collected dataset is introduced for the main speaker detection. To the best of our knowledge, it is one of the first studies that is able to automatically localize and highlight the main speaker in both visual and audio channels in multi-speaker conversation videos.
Multi-Camera Multiple Object Tracking (MC-MOT) is a significant computer vision problem due to its emerging applicability in several real-world applications. Despite a large number of existing works, solving the data association problem in any MC-MOT pipeline is arguably one of the most challenging tasks. Developing a robust MC-MOT system, however, is still highly challenging due to many practical issues such as inconsistent lighting conditions, varying object movement patterns, or the trajectory occlusions of the objects between the cameras. To address these problems, this work, therefore, proposes a new Dynamic Graph Model with Link Prediction (DyGLIP) approach to solve the data association task. Compared to existing methods, our new model offers several advantages, including better feature representations and the ability to recover from lost tracks during camera transitions. Moreover, our model works gracefully regardless of the overlapping ratios between the cameras. Experimental results show that we outperform existing MC-MOT algorithms by a large margin on several practical datasets. Notably, our model works favorably on online settings but can be extended to an incremental approach for large-scale datasets.
Disentangled representations have been commonly adopted to Age-invariant Face Recognition (AiFR) tasks. However, these methods have reached some limitations with (1) the requirement of large-scale face recognition (FR) training data with age labels, which is limited in practice; (2) heavy deep network architecture for high performance; and (3) their evaluations are usually taken place on age-related face databases while neglecting the standard large-scale FR databases to guarantee its robustness. This work presents a novel Attentive Angular Distillation (AAD) approach to Large-scale Lightweight AiFR that overcomes these limitations. Given two high-performance heavy networks as teachers with different specialized knowledge, AAD introduces a learning paradigm to efficiently distill the age-invariant attentive and angular knowledge from those teachers to a lightweight student network making it more powerful with higher FR accuracy and robust against age factor. Consequently, AAD approach is able to take the advantages of both FR datasets with and without age labels to train an AiFR model. Far apart from prior distillation methods mainly focusing on accuracy and compression ratios in closed-set problems, our AAD aims to solve the open-set problem, i.e. large-scale face recognition. Evaluations on LFW, IJB-B and IJB-C Janus, AgeDB and MegaFace-FGNet with one million distractors have demonstrated the efficiency of the proposed approach. This work also presents a new longitudinal face aging (LogiFace) database for further studies in age-related facial problems in future.
Unveiling face images of a subject given his/her high-level representations extracted from a blackbox Face Recognition engine is extremely challenging. It is because the limitations of accessible information from that engine including its structure and uninterpretable extracted features. This paper presents a novel generative structure with Bijective Metric Learning, namely Bijective Generative Adversarial Networks in a Distillation framework (DiBiGAN), for synthesizing faces of an identity given that person's features. In order to effectively address this problem, this work firstly introduces a bijective metric so that the distance measurement and metric learning process can be directly adopted in image domain for an image reconstruction task. Secondly, a distillation process is introduced to maximize the information exploited from the blackbox face recognition engine. Then a Feature-Conditional Generator Structure with Exponential Weighting Strategy is presented for a more robust generator that can synthesize realistic faces with ID preservation. Results on several benchmarking datasets including CelebA, LFW, AgeDB, CFP-FP against matching engines have demonstrated the effectiveness of DiBiGAN on both image realism and ID preservation properties.
Image alignment across domains has recently become one of the realistic and popular topics in the research community. In this problem, a deep learning-based image alignment method is usually trained on an available largescale database. During the testing steps, this trained model is deployed on unseen images collected under different camera conditions and modalities. The delivered deep network models are unable to be updated, adapted or fine-tuned in these scenarios. Thus, recent deep learning techniques, e.g. domain adaptation, feature transferring, and fine-tuning, are unable to be deployed. This paper presents a novel deep learning based approach to tackle the problem of across unseen modalities. The proposed network is then applied to image alignment as an illustration. The proposed approach is designed as an end-to-end deep convolutional neural network to optimize the deep models to improve the performance. The proposed network has been evaluated in digit recognition when the model is trained on MNIST and then tested on unseen domain MNIST-M. Finally, the proposed method is benchmarked in image alignment problem when training on RGB images and testing on Depth and X-Ray images.
Recognition across domains has recently become an active topic in the research community. However, it has been largely overlooked in the problem of recognition in new unseen domains. Under this condition, the delivered deep network models are unable to be updated, adapted or fine-tuned. Therefore, recent deep learning techniques, such as: domain adaptation, feature transferring, and fine-tuning, cannot be applied. This paper presents a novel approach to the problem of domain generalization in the context of deep learning. The proposed method is evaluated on different datasets in various problems, i.e. (i) digit recognition on MNIST, SVHN and MNIST-M, (ii) face recognition on Extended Yale-B, CMU-PIE and CMU-MPIE, and (iii) pedestrian recognition on RGB and Thermal image datasets. The experimental results show that our proposed method consistently improves the performance accuracy. It can be also easily incorporated with any other CNN frameworks within an end-to-end deep network design for object detection and recognition problems to improve their performance.
Flow-based generative models have recently become one of the most efficient approaches to model the data generation. Indeed, they are constructed with a sequence of invertible and tractable transformations. Glow first introduced a simple type of generative flow using an invertible 1x1 convolution. However, the 1x1 convolution suffers from limited flexibility compared to the standard convolutions. In this paper, we propose a novel invertible nxn convolution approach that overcomes the limitations of the invertible 1x1 convolution. In addition, our proposed network is not only tractable and invertible but also uses fewer parameters than standard convolutions. The experiments on CIFAR-10, ImageNet, and Celeb-HQ datasets, have showed that our invertible nxn convolution helps to improve the performance of generative models significantly.