Jinjin Zhang

Ganlong Zhao, Guanbin Li, Yipeng Qin et al.

In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both in-distribution (ID) and out-of-distribution (OOD) samples. Unlike previous methods that only consider ID samples to be useful and aim to filter out OOD ones completely during training, we argue that the exploration and exploitation of both ID and OOD samples can benefit SSL. To support our claim, i) we propose a prototype-based clustering and identification algorithm that explores the inherent similarity and difference among samples at feature level and effectively cluster them around several predefined ID and OOD prototypes, thereby enhancing feature learning and facilitating ID/OOD identification; ii) we propose an importance-based sampling method that exploits the difference in importance of each ID and OOD sample to SSL, thereby reducing the sampling bias and improving the training. Our proposed method achieves state-of-the-art in several challenging benchmarks, and improves upon existing SSL methods even when ID samples are totally absent in unlabeled data.

Jinjin Zhang, Wei Wang, Di Huang et al.

Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision. In this paper, we propose a feasible framework for multi-lingual arbitrary-shaped STR, including instance segmentation based text detection and language model based attention mechanism for text recognition. Our STR algorithm not only recognizes Latin and Non-Latin characters, but also supports arbitrary-shaped text recognition. Our method wins the championship on Scene Text Spotting Task (Latin Only, Latin and Chinese) of ICDAR2019 Robust Reading Challenge on ArbitraryShaped Text Competition. Code is available at https://github.com/zhang0jhon/AttentionOCR.

Mengmeng Cui, Wei Wang, Jinjin Zhang et al.

Attention-based encoder-decoder framework is widely used in the scene text recognition task. However, for the current state-of-the-art(SOTA) methods, there is room for improvement in terms of the efficient usage of local visual and global context information of the input text image, as well as the robust correlation between the scene processing module(encoder) and the text processing module(decoder). In this paper, we propose a Representation and Correlation Enhanced Encoder-Decoder Framework(RCEED) to address these deficiencies and break performance bottleneck. In the encoder module, local visual feature, global context feature, and position information are aligned and fused to generate a small-size comprehensive feature map. In the decoder module, two methods are utilized to enhance the correlation between scene and text feature space. 1) The decoder initialization is guided by the holistic feature and global glimpse vector exported from the encoder. 2) The feature enriched glimpse vector produced by the Multi-Head General Attention is used to assist the RNN iteration and the character prediction at each time step. Meanwhile, we also design a Layernorm-Dropout LSTM cell to improve model's generalization towards changeable texts. Extensive experiments on the benchmarks demonstrate the advantageous performance of RCEED in scene text recognition tasks, especially the irregular ones.

Lixing Tan, Zhaohui Zhu, Jinjin Zhang

After a few decades of development, computational argumentation has become one of the active realms in AI. This paper considers extension-based concrete and abstract semantics of argumentation. For concrete ones, based on Grossi and Modgil's recent work, this paper considers some issues on graded extension-based semantics of abstract argumentation framework (AAF, for short). First, an alternative fundamental lemma is given, which generalizes the corresponding result due to Grossi and Modgil by relaxing the constraint on parameters. This lemma provides a new sufficient condition for preserving conflict-freeness and brings a Galois adjunction between admissible sets and complete extensions, which is of vital importance in constructing some special extensions in terms of iterations of the defense function. Applying such a lemma, some flaws in Grossi and Modgil's work are corrected, and the structural property and universal definability of various extension-based semantics are given. Second, an operator so-called reduced meet modulo an ultrafilter is presented, which is a simple but powerful tool in exploring infinite AAFs. The neutrality function and the defense function, which play central roles in Dung's abstract argumentation theory, are shown to be distributive over reduced meets modulo any ultrafilter. A variety of fundamental semantics of AAFs, including conflict-free, admissible, complete and stable semantics, etc, are shown to be closed under this operator. Based on this fact, a number of applications of such operators are considered. In particular, we provide a simple and uniform method to prove the universal definability of a family of range related semantics. Since all graded concrete semantics considered in this paper are generalizations of corresponding non-graded ones, all results about them obtained in this paper also hold in the traditional situation.