Italy


Though deep learning based scene text detection has achieved great progress, well-trained detectors suffer from severe performance degradation for different domains. In general, a tremendous amount of data is indispensable to train the detector in the target domain. However, data collection and annotation are expensive and time-consuming. To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images. To reduce the noise of hard examples, a novel text mining module is implemented based on the fusion of detection and tracking results. Then, an image-to-video generation method is designed for the tasks that videos are unavailable and only images can be used. Experimental results on standard benchmarks, including ICDAR2015, MSRA-TD500, ICDAR2017 MLT, demonstrate the effectiveness of our self-training method. The simple Mask RCNN adapted with self-training and fine-tuned on real data can achieve comparable or even superior results with the state-of-the-art methods.

ICPR 2020

Self-Training for Domain Adaptive Scene Text Detection

scene text detection

self-training

domain adaptation

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


technical paper

Deep convolutional neural networks (DCNN) based methodologies have achieved remarkable performance on various low-level vision tasks recently. Restoring images captured at night is one of the trickiest low-level vision tasks due to its high-level noise and low-level intensity. We propose a DCNN-based methodology, Illumination and Noise Separation Network (INSNet), which performs both denoising and enhancement on these extremely low-light images. INSNet fully utilizes global-ware features and local-ware features using the modified network structure and image sampling scheme. Compared to well-designed complex neural networks, our proposed methodology only needs to add a bypass network to the existing network. However, it can boost the quality of recovered images dramatically but only increase the computational cost by less than 0.1%. Even without any manual settings, INSNet can stably restore the extremely low-light images to desired high-quality images.

Automatical Enhancement and Denoising of Extremely Low-light Images

Completing sparse data captured with commercial depth sensors is a vital and fundamental procedure for many computer vision applications. For execution in real-world scenarios, a good trade-off between accuracy and speed is increasingly in demand for depth completion methods. Most previous methods achieve satisfactory accuracy on standard benchmarks. However, they extensively rely on heavy models to handle diverse structures and require additional run time on multimodal data. In this paper, we present an efficient method of depth completion. We propose a grouped fusion strategy for efficiently extracting depth and guidance features in parallel and fusing them naturally in the feature spaces to achieve high performance. Instead of a monolithic architecture, we employ cascaded hourglass networks, each of which is specialized for certain structures and has a lightweight architecture. Given the sparsity of the depth maps, we downsample the inputs to multiple scales to further accelerate the computation. Our model runs at over 39 FPS on an embedded GPU with high-resolution inputs. Evaluations on the KITTI benchmark demonstrate that the proposed model is an ideal approach for real-world applications.

FastCompletion: A Cascade Network with Multiscale Group-Fused Inputs for Real-Time Depth Completion


Photo retouching features are being integrated into a growing number of mobile applications. Current learning-based approaches enhance images using large convolutional neural network-based models, where the result is received directly from the neural network outputs. This method can lead to artifacts in the resulting images, models that are complicated to interpret, and can be computationally expensive.
In this paper, we explore the application of a filter-based approach in order to overcome the problems outlined above. We focus on creating a lightweight solution suitable for use on mobile devices when designing our model. A significant performance increase was achieved through implementing consistency regularization used in semi-supervised learning. The proposed model can be used on mobile devices and achieves competitive results compared to known models.

LFIEM: Lightweight Filter-based Image Enhancement Model

Visual Question Answering (VQA) is one of the most challenging emerging applications of deep learning. Providing powerful attention mechanisms is crucial for VQA, since the model must correctly identify the region of an image that is relevant to the question at hand. However, existing models analyze the input images at a fixed and typically small resolution, often leading to discarding valuable fine-grained details. To overcome this limitation, in this work we propose a reinforcement learning- based active perception approach that works by applying a series of transformation operations on the images (translation, zoom) in order to facilitate answering the question at hand. This allows for performing fine-grained analysis, effectively increasing the resolution at which the models process information. The proposed method is orthogonal to existing attention mechanisms and it can be combined with most existing VQA methods. The effectiveness of the proposed method is experimentally demonstrated on a challenging VQA dataset.

Improving Visual Question Answering using Active Perception on Static Images


Several deep supervised hashing techniques have been proposed to allow for querying large image databases. However, it is often overlooked that the process of information retrieval can be modeled using information-theoretic metrics, leading to optimizing various proxies for the problem at hand instead. Contrary to this, we propose a deep supervised hashing algorithm that optimizes the learned codes using an information-theoretic measure, the Quadratic Mutual Information (QMI). The proposed method is adapted to the needs of large-scale hashing and information retrieval leading to a novel information-theoretic measure, the Quadratic Spherical Mutual Information (QSMI), that is inspired by QMI, but leads to significant better retrieval precision. Indeed, the effectiveness of the proposed method is demonstrated under several different scenarios, using different datasets and network architectures, outperforming existing deep supervised image hashing techniques.

Leveraging Quadratic Spherical Mutual Information Hashing for Fast Image Retrieval

We tackle depth completion task. Based on our assumption, color image and depth map share some structural information, we proposed DEN network that disentangle and exchange the structural information of color and depth domain to accomplish depth completion. In this presentation, we'll show the mechanism and design ideas of our method.

DEN: Disentangling and Exchanging Network for Depth Completion

Non-negative matrix factorization (NMF) is an important method in learning latent data representation. The local geometrical structure can make the learned representation more effectively and significantly improve the performance of NMF. However, most of existing graph-based learning methods are determined by a predefined similarity graph which may be not optimal for specific tasks. To solve the above problem, we propose the Double Manifolds Regularized NMF (DMR-NMF) model which jointly learns an adaptive affinity matrix with the non-negative matrix factorization. The learned affinity matrix can guide the NMF to fit the clustering task. Moreover, we develop the iterative updating optimization schemes for DMR-NMF, and provide the strict convergence proof of our optimization strategy. Empirical experiments on four different real-world data sets demonstrate the state-of-the-art performance of DMR-NMF in comparison with the other related algorithms.

Double Manifolds Regularized Non-negative Matrix Factorization for Data Representation

Clustering high dimension multi-view data with complex intrinsic properties and nonlinear manifold structure is a challenging task since these data are always embedded in low dimension manifolds. Inspired by Low Rank Representation (LRR), some researchers extended classic LRR on Grassmann manifold or Product Grassmann manifold to represent data with non-linear metrics. However, most of these methods utilized convex nuclear norm to leverage a low-rank structure, which was over-relaxation of true rank and would lead to the results deviated from the true underlying ones. And, the computational complexity of singular value decomposition of matrix is high for nuclear norm minimization. In this paper, we propose a new low rank model for high-dimension multi-view data clustering on Product Grassmann Manifold with the matrix tri-factorization which is used to control the upper bound of true rank of representation matrix. And, the original problem can be transformed into the nuclear norm minimization with smaller scale matrices. An effective solution and theoretical analysis are also provided. The experimental results show
that the proposed method obviously outperforms other state-of-the-art methods on several multi-source human/crowd action video datasets.

Low Rank Representation on Product Grassmann Manifolds for Multi-view Subspace Clustering

Face synthesis is an interesting yet challenging task in computer vision. It is even much harder to generate a portrait video than a single image. In this paper, we propose a novel video generation framework for synthesizing arbitrarylength face videos without any face exemplar or landmark. To overcome the synthesis ambiguity of face video, we propose a divide-and-conquer strategy to separately address the video face synthesis problem from two aspects, face identity synthesis and rearrangement. To this end, we design a cascaded network which contains three components, Identity-aware GAN (IA-GAN), Face Coherence Network, and Interpolation Network. IA-GAN is proposed to synthesize photorealistic faces with the same identity from a set of noises. Face Coherence Network is designed to re-arrange the faces generated by IA-GAN while keeping the inter-frame coherence. Interpolation Network is introduced to eliminate the discontinuity between two adjacent frames and improve the smoothness of the face video. Experimental results demonstrate that our proposed network is able to generate face video with high visual quality while preserving the identity. Statistics show that our method outperforms state-of-the-art unconditional face video generative models in multiple challenging datasets.

Coherence and Identity Learning for Arbitrary-length Face Video Generation


Deep clustering aims to cluster unlabeled real-world samples by mining deep feature representation. Most of existing methods remain challenging when handling high-dimensional data and simultaneously exploring the complementarity of deep
feature representation and clustering. In this paper, we propose a novel Deep Variational Attention Encoder-decoder for Clustering (DVAEC). Our DVAEC improves the representation learning ability by fusing variational attention. Specifically, we design a feature-aware automatic clustering module to mitigate the
unreliability of similarity calculation and guide network learning. Besides, to further boost the performance of deep clustering from a global perspective, we define a joint optimization objective to promote feature representation learning and automatic clustering synergistically. Extensive experimental results show the promising
performance achieved by our DVAEC on six datasets comparing with several popular baseline clustering methods.

Premium content

Self-Training for Domain Adaptive Scene Text Detection

Downloads

Next from ICPR 2020

Automatical Enhancement and Denoising of Extremely Low-light Images

Similar lecture

Self-Training for Domain Adaptive Scene Text Detection