I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition

Leveraging the advances of natural language processing, most recent scene text recognizers adopt an encoder-decoder architecture where text images are first converted to representative features and then a sequence of characters via `direct decoding'. However, scene text images suffer from rich noises of different sources such as complex background and geometric distortions which often confuse the decoder and lead to incorrect alignment of visual features at noisy decoding time steps. This paper presents I2C2W, a novel scene text recognizer that is accurate and tolerant to various noises in scenes. I2C2W consists of an image-to-character module (I2C) and a character-to-word module (C2W) which are complementary and can be trained end-to-end. I2C detects characters and predicts their relative positions in a word. It strives to detect all possible characters including incorrect and redundant ones based on different alignments of visual features without the restriction of time steps. Taking the detected characters as input, C2W learns from character semantics and their positions to filter out incorrect and redundant detection and produce the final word recognition. Extensive experiments over seven public datasets show that I2C2W achieves superior recognition performances and outperforms the state-of-the-art by large margins on challenging irregular scene text datasets.

Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

Image inpainting is an underdetermined inverse problem, it naturally allows diverse contents that fill up the missing or corrupted regions reasonably and realistically. Prevalent approaches using convolutional neural networks (CNNs) can synthesize visually pleasant contents, but CNNs suffer from limited perception fields for capturing global features. With image-level attention, transformers enable to model long-range dependencies and generate diverse contents with autoregressive modeling of pixel-sequence distributions. However, the unidirectional attention in transformers is suboptimal as corrupted regions can have arbitrary shapes with contexts from arbitrary directions. We propose BAT-Fill, an image inpainting framework with a novel bidirectional autoregressive transformer (BAT) that models deep bidirectional contexts for autoregressive generation of diverse inpainting contents. BAT-Fill inherits the merits of transformers and CNNs in a two-stage manner, which allows to generate high-resolution contents without being constrained by the quadratic complexity of attention in transformers. Specifically, it first generates pluralistic image structures of low resolution by adapting transformers and then synthesizes realistic texture details of high resolutions with a CNN-based up-sampling network. Extensive experiments over multiple datasets show that BAT-Fill achieves superior diversity and fidelity in image inpainting qualitatively and quantitatively.

DA-DETR: Domain Adaptive Detection Transformer by Hybrid Attention

The prevalent approach in domain adaptive object detection adopts a two-stage architecture (Faster R-CNN) that involves a number of hyper-parameters and hand-crafted designs such as anchors, region pooling, non-maximum suppression, etc. Such architecture makes it very complicated while adopting certain existing domain adaptation methods with different ways of feature alignment. In this work, we adopt a one-stage detector and design DA-DETR, a simple yet effective domain adaptive object detection network that performs inter-domain alignment with a single discriminator. DA-DETR introduces a hybrid attention module that explicitly pinpoints the hard-aligned features for simple yet effective alignment across domains. It greatly simplifies traditional domain adaptation pipelines by eliminating sophisticated routines that involve multiple adversarial learning frameworks with different types of features. Despite its simplicity, extensive experiments show that DA-DETR demonstrates superior accuracy as compared with highly-optimized state-of-the-art approaches.

Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection

Automated defect inspection is critical for effective and efficient maintenance, repair, and operations in advanced manufacturing. On the other hand, automated defect inspection is often constrained by the lack of defect samples, especially when we adopt deep neural networks for this task. This paper presents Defect-GAN, an automated defect synthesis network that generates realistic and diverse defect samples for training accurate and robust defect inspection networks. Defect-GAN learns through defacement and restoration processes, where the defacement generates defects on normal surface images while the restoration removes defects to generate normal images. It employs a novel compositional layer-based architecture for generating realistic defects within various image backgrounds with different textures and appearances. It can also mimic the stochastic variations of defects and offer flexible control over the locations and categories of the generated defects within the image background. Extensive experiments show that Defect-GAN is capable of synthesizing various defects with superior diversity and fidelity. In addition, the synthesized defect samples demonstrate their effectiveness in training better defect inspection networks.

Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning

Few-shot object detection aims at detecting novel objects with only a few annotated examples. Prior works have proved meta-learning a promising solution, and most of them essentially address detection by meta-learning over regions for their classification and location fine-tuning. However, these methods substantially rely on initially well-located region proposals, which are usually hard to obtain under the few-shot settings. This paper presents a novel meta-detector framework, namely Meta-DETR, which eliminates region-wise prediction and instead meta-learns object localization and classification at image level in a unified and complementary manner. Specifically, it first encodes both support and query images into category-specific features and then feeds them into a category-agnostic decoder to directly generate predictions for specific categories. To facilitate meta-learning with deep networks, we design a simple but effective Semantic Alignment Mechanism (SAM), which aligns high-level and low-level feature semantics to improve the generalization of meta-learned representations. Experiments over multiple few-shot object detection benchmarks show that Meta-DETR outperforms state-of-the-art methods by large margins.

MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation

Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation. However, most adversarial learning based methods align source and target distributions at a global image level but neglect the inconsistency around local image regions. This paper presents a novel multi-level adversarial network (MLAN) that aims to address inter-domain inconsistency at both global image level and local region level optimally. MLAN has two novel designs, namely, region-level adversarial learning (RL-AL) and co-regularized adversarial learning (CR-AL). Specifically, RL-AL models prototypical regional context-relations explicitly in the feature space of a labelled source domain and transfers them to an unlabelled target domain via adversarial learning. CR-AL fuses region-level AL and image-level AL optimally via mutual regularization. In addition, we design a multi-level consistency map that can guide domain adaptation in both input space ($i.e.$, image-to-image translation) and output space ($i.e.$, self-training) effectively. Extensive experiments show that MLAN outperforms the state-of-the-art with a large margin consistently across multiple datasets.

Cross-View Regularization for Domain Adaptive Panoptic Segmentation

Panoptic segmentation unifies semantic segmentation and instance segmentation which has been attracting increasing attention in recent years. However, most existing research was conducted under a supervised learning setup whereas unsupervised domain adaptive panoptic segmentation which is critical in different tasks and applications is largely neglected. We design a domain adaptive panoptic segmentation network that exploits inter-style consistency and inter-task regularization for optimal domain adaptive panoptic segmentation. The inter-style consistency leverages geometric invariance across the same image of the different styles which fabricates certain self-supervisions to guide the network to learn domain-invariant features. The inter-task regularization exploits the complementary nature of instance segmentation and semantic segmentation and uses it as a constraint for better feature alignment across domains. Extensive experiments over multiple domain adaptive panoptic segmentation tasks (e.g., synthetic-to-real and real-to-real) show that our proposed network achieves superior segmentation performance as compared with the state-of-the-art.

FSDR: Frequency Space Domain Randomization for Domain Generalization

Domain generalization aims to learn a generalizable model from a known source domain for various unknown target domains. It has been studied widely by domain randomization that transfers source images to different styles in spatial space for learning domain-agnostic features. However, most existing randomization uses GANs that often lack of controls and even alter semantic structures of images undesirably. Inspired by the idea of JPEG that converts spatial images into multiple frequency components (FCs), we propose Frequency Space Domain Randomization (FSDR) that randomizes images in frequency space by keeping domain-invariant FCs (DIFs) and randomizing domain-variant FCs (DVFs) only. FSDR has two unique features: 1) it decomposes images into DIFs and DVFs which allows explicit access and manipulation of them and more controllable randomization; 2) it has minimal effects on semantic structures of images and domain-invariant features. We examined domain variance and invariance property of FCs statistically and designed a network that can identify and fuse DIFs and DVFs dynamically through iterative learning. Extensive experiments over multiple domain generalizable segmentation tasks show that FSDR achieves superior segmentation and its performance is even on par with domain adaptation methods that access target data in training.

Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links

Detection and recognition of scene texts of arbitrary shapes remain a grand challenge due to the super-rich text shape variation in text line orientations, lengths, curvatures, etc. This paper presents a mask-guided multi-task network that detects and rectifies scene texts of arbitrary shapes reliably. Three types of keypoints are detected which specify the centre line and so the shape of text instances accurately. In addition, four types of keypoint links are detected of which the horizontal links associate the detected keypoints of each text instance and the vertical links predict a pair of landmark points (for each keypoint) along the upper and lower text boundary, respectively. Scene texts can be located and rectified by linking up the associated landmark points (giving localization polygon boxes) and transforming the polygon boxes via thin plate spline, respectively. Extensive experiments over several public datasets show that the use of text keypoints is tolerant to the variation in text orientations, lengths, and curvatures, and it achieves superior scene text detection and rectification performance as compared with state-of-the-art methods.