Zhong Zhou

Binyi Su, Hua Zhang, Jingzhi Li et al.

Open-set object detection (OSOD) aims to detect the known categories and reject unknown objects in a dynamic world, which has achieved significant attention. However, previous approaches only consider this problem in data-abundant conditions, while neglecting the few-shot scenes. In this paper, we seek a solution for the generalized few-shot open-set object detection (G-FOOD), which aims to avoid detecting unknown classes as known classes with a high confidence score while maintaining the performance of few-shot detection. The main challenge for this task is that few training samples induce the model to overfit on the known classes, resulting in a poor open-set performance. We propose a new G-FOOD algorithm to tackle this issue, named \underline{F}ew-sh\underline{O}t \underline{O}pen-set \underline{D}etector (FOOD), which contains a novel class weight sparsification classifier (CWSC) and a novel unknown decoupling learner (UDL). To prevent over-fitting, CWSC randomly sparses parts of the normalized weights for the logit prediction of all classes, and then decreases the co-adaptability between the class and its neighbors. Alongside, UDL decouples training the unknown class and enables the model to form a compact unknown decision boundary. Thus, the unknown objects can be identified with a confidence probability without any threshold, prototype, or generation. We compare our method with several state-of-the-art OSOD methods in few-shot scenes and observe that our method improves the F-score of unknown classes by 4.80\%-9.08\% across all shots in VOC-COCO dataset settings \footnote[1]{The source code is available at \url{https://github.com/binyisu/food}}.

Zhaowei Wu, Binyi Su, Qichuan Geng et al.

Few-shot Open-set Object Detection (FOOD) poses a challenge in many open-world scenarios. It aims to train an open-set detector to detect known objects while rejecting unknowns with scarce training samples. Existing FOOD methods are subject to limited visual information, and often exhibit an ambiguous decision boundary between known and unknown classes. To address these limitations, we propose the first prompt-based few-shot open-set object detection framework, which exploits additional textual information and delves into constructing a robust decision boundary for unknown rejection. Specifically, as no available training data for unknown classes, we select pseudo-unknown samples with Attribution-Gradient based Pseudo-unknown Mining (AGPM), which leverages the discrepancy in attribution gradients to quantify uncertainty. Subsequently, we propose Conditional Evidence Decoupling (CED) to decouple and extract distinct knowledge from selected pseudo-unknown samples by eliminating opposing evidence. This optimization process can enhance the discrimination between known and unknown classes. To further regularize the model and form a robust decision boundary for unknown rejection, we introduce Abnormal Distribution Calibration (ADC) to calibrate the output probability distribution of local abnormal features in pseudo-unknown samples. Our method achieves superior performance over previous state-of-the-art approaches, improving the average recall of unknown class by 7.24% across all shots in VOC10-5-5 dataset settings and 1.38% in VOC-COCO dataset settings. Our source code is available at https://gitee.com/VR_NAVE/ced-food.

Weimin Shi, Mingchen Zhuge, Dehong Gao et al.

Daily images may convey abstract meanings that require us to memorize and infer profound information from them. To encourage such human-like reasoning, in this work, we teach machines to predict where and when it was taken rather than performing basic tasks like traditional segmentation or classification. Inspired by Horn's QR theory, we designed a novel QR-CLIP model consisting of two components: 1) the Quantity module first retrospects more open-world knowledge as the candidate language inputs; 2) the Relevance module carefully estimates vision and language cues and infers the location and time. Experiments show our QR-CLIP's effectiveness, and it outperforms the previous SOTA on each task by an average of about 10% and 130% relative lift in terms of location and time reasoning. This study lays a technical foundation for location and time reasoning and suggests that effectively introducing open-world knowledge is one of the panaceas for the tasks.

Zhong Zhou

Translation into severely low-resource languages has both the cultural goal of saving and reviving those languages and the humanitarian goal of assisting the everyday needs of local communities that are accelerated by the recent COVID-19 pandemic. In many humanitarian efforts, translation into severely low-resource languages often does not require a universal translation engine, but a dedicated text-specific translation engine. For example, healthcare records, hygienic procedures, government communication, emergency procedures and religious texts are all limited texts. While generic translation engines for all languages do not exist, translation of multilingually known limited texts into new, low-resource languages may be possible and reduce human translation effort. We attempt to leverage translation resources from rich-resource languages to efficiently produce best possible translation quality for well known texts, which are available in multiple languages, in a new, low-resource language. To reach this goal, we argue that in translating a closed text into low-resource languages, generalization to out-of-domain texts is not necessary, but generalization to new languages is. Performance gain comes from massive source parallelism by careful choice of close-by language families, style-consistent corpus-level paraphrases within the same language and strategic adaptation of existing large pretrained multilingual models to the domain first and then to the language. Such performance gain makes it possible for machine translation systems to collaborate with human translators to expedite the translation process into new, low-resource languages.

Zhong Zhou, Jan Niehues, Alex Waibel

In many humanitarian scenarios, translation into severely low resource languages often does not require a universal translation engine, but a dedicated text-specific translation engine. For example, healthcare records, hygienic procedures, government communication, emergency procedures and religious texts are all limited texts. While generic translation engines for all languages do not exist, translation of multilingually known limited texts into new, endangered languages may be possible and reduce human translation effort. We attempt to leverage translation resources from many rich resource languages to efficiently produce best possible translation quality for a well known text, which is available in multiple languages, in a new, severely low resource language. We examine two approaches: 1. best selection of seed sentences to jump start translations in a new language in view of best generalization to the remainder of a larger targeted text(s), and 2. we adapt large general multilingual translation engines from many other languages to focus on a specific text in a new, unknown language. We find that adapting large pretrained multilingual models to the domain/text first and then to the severely low resource language works best. If we also select a best set of seed sentences, we can improve average chrF performance on new test languages from a baseline of 21.9 to 50.7, while reducing the number of seed sentences to only around 1,000 in the new, unknown language.

Zhong Zhou, Alex Waibel

We translate a closed text that is known in advance and available in many languages into a new and severely low resource language. Most human translation efforts adopt a portion-based approach to translate consecutive pages/chapters in order, which may not suit machine translation. We compare the portion-based approach that optimizes coherence of the text locally with the random sampling approach that increases coverage of the text globally. Our results show that the random sampling approach performs better. When training on a seed corpus of ~1,000 lines from the Bible and testing on the rest of the Bible (~30,000 lines), random sampling gives a performance gain of +11.0 BLEU using English as a simulated low resource language, and +4.9 BLEU using Eastern Pokomchi, a Mayan language. Furthermore, we compare three ways of updating machine translation models with increasing amount of human post-edited data through iterations. We find that adding newly post-edited data to training after vocabulary update without self-supervision performs the best. We propose an algorithm for human and machine to work together seamlessly to translate a closed text into a severely low resource language.

Zhong Zhou, Alex Waibel

We translate a closed text that is known in advance into a severely low resource language by leveraging massive source parallelism. In other words, given a text in 124 source languages, we translate it into a severely low resource language using only ~1,000 lines of low resource data without any external help. Firstly, we propose a systematic method to rank and choose source languages that are close to the low resource language. We call the linguistic definition of language family Family of Origin (FAMO), and we call the empirical definition of higher-ranked languages using our metrics Family of Choice (FAMC). Secondly, we build an Iteratively Pretrained Multilingual Order-preserving Lexiconized Transformer (IPML) to train on ~1,000 lines (~3.5%) of low resource data. To translate named entities correctly, we build a massive lexicon table for 2,939 Bible named entities in 124 source languages, and include many that occur once and covers more than 66 severely low resource languages. Moreover, we also build a novel method of combining translations from different source languages into one. Using English as a hypothetical low resource language, we get a +23.9 BLEU increase over a multilingual baseline, and a +10.3 BLEU increase over our asymmetric baseline in the Bible dataset. We get a 42.8 BLEU score for Portuguese-English translation on the medical EMEA dataset. We also have good results for a real severely low resource Mayan language, Eastern Pokomchi.

Binyi Su, Zhong Zhou, Haiyong Chen et al.

Solar cell electroluminescence (EL) defect segmentation is an interesting and challenging topic. Many methods have been proposed for EL defect detection, but these methods are still unsatisfactory due to the diversity of the defect and background. In this paper, we provide a new idea of using generative adversarial network (GAN) for defect segmentation. Firstly, the GAN-based method removes the defect region in the input defective image to get a defect-free image, while keeping the background almost unchanged. Then, the subtracted image is obtained by making difference between the defective input image with the generated defect-free image. Finally, the defect region can be segmented through thresholding the subtracted image. To keep the background unchanged before and after image generation, we propose a novel strong identity GAN (SIGAN), which adopts a novel strong identity loss to constraint the background consistency. The SIGAN can be used not only for defect segmentation, but also small-samples defective dataset augmentation. Moreover, we release a new solar cell EL image dataset named as EL-2019, which includes three types of images: crack, finger interruption and defect-free. Experiments on EL-2019 dataset show that the proposed method achieves 90.34% F-score, which outperforms many state-of-the-art methods in terms of solar cell defects segmentation results.

Binyi Su, Haiyong Chen, Zhong Zhou

The multi-scale defect detection for photovoltaic (PV) cell electroluminescence (EL) images is a challenging task, due to the feature vanishing as network deepens. To address this problem, an attention-based top-down and bottom-up architecture is developed to accomplish multi-scale feature fusion. This architecture, called Bidirectional Attention Feature Pyramid Network (BAFPN), can make all layers of the pyramid share similar semantic features. In BAFPN, cosine similarity is employed to measure the importance of each pixel in the fused features. Furthermore, a novel object detector is proposed, called BAF-Detector, which embeds BAFPN into Region Proposal Network (RPN) in Faster RCNN+FPN. BAFPN improves the robustness of the network to scales, thus the proposed detector achieves a good performance in multi-scale defects detection task. Finally, the experimental results on a large-scale EL dataset including 3629 images, 2129 of which are defective, show that the proposed method achieves 98.70% (F-measure), 88.07% (mAP), and 73.29% (IoU) in terms of multi-scale defects classification and detection results in raw PV cell EL images.

Qichuan Geng, Hong Zhang, Na Jiang et al.

We present an Object-aware Feature Aggregation (OFA) module for video object detection (VID). Our approach is motivated by the intriguing property that video-level object-aware knowledge can be employed as a powerful semantic prior to help object recognition. As a consequence, augmenting features with such prior knowledge can effectively improve the classification and localization performance. To make features get access to more content about the whole video, we first capture the object-aware knowledge of proposals and incorporate such knowledge with the well-established pair-wise contexts. With extensive experimental results on the ImageNet VID dataset, our approach demonstrates the effectiveness of object-aware knowledge with the superior performance of 83.93% and 86.09% mAP with ResNet-101 and ResNeXt-101, respectively. When further equipped with Sequence DIoU NMS, we obtain the best-reported mAP of 85.07% and 86.88% upon the paper submitted. The code to reproduce our results will be released after acceptance.

Zhong Zhou, Isak Czeresnia Etinger, Florian Metze et al.

There is a surging need across the world for protection against gun violence. There are three main areas that we have identified as challenging in research that tries to curb gun violence: temporal location of gunshots, gun type prediction and gun source (shooter) detection. Our task is gun source detection and muzzle head detection, where the muzzle head is the round opening of the firing end of the gun. We would like to locate the muzzle head of the gun in the video visually, and identify who has fired the shot. In our formulation, we turn the problem of muzzle head detection into two sub-problems of human object detection and gun smoke detection. Our assumption is that the muzzle head typically lies between the gun smoke caused by the shot and the shooter. We have interesting results both in bounding the shooter as well as detecting the gun smoke. In our experiments, we are successful in detecting the muzzle head by detecting the gun smoke and the shooter.

Qichuan Geng, Hong Zhang, Xiaojuan Qi et al.

Semantic segmentation is a challenging task that needs to handle large scale variations, deformations and different viewpoints. In this paper, we develop a novel network named Gated Path Selection Network (GPSNet), which aims to learn adaptive receptive fields. In GPSNet, we first design a two-dimensional multi-scale network - SuperNet, which densely incorporates features from growing receptive fields. To dynamically select desirable semantic context, a gate prediction module is further introduced. In contrast to previous works that focus on optimizing sample positions on the regular grids, GPSNet can adaptively capture free form dense semantic contexts. The derived adaptive receptive fields are data-dependent, and are flexible that can model different object geometric transformations. On two representative semantic segmentation datasets, i.e., Cityscapes, and ADE20K, we show that the proposed approach consistently outperforms previous methods and achieves competitive performance without bells and whistles.

Zhong Zhou, Lori Levin, David R. Mortensen et al.

We demonstrate a new approach to Neural Machine Translation (NMT) for low-resource languages using a ubiquitous linguistic resource, Interlinear Glossed Text (IGT). IGT represents a non-English sentence as a sequence of English lemmas and morpheme labels. As such, it can serve as a pivot or interlingua for NMT. Our contribution is four-fold. Firstly, we pool IGT for 1,497 languages in ODIN (54,545 glosses) and 70,918 glosses in Arapaho and train a gloss-to-target NMT system from IGT to English, with a BLEU score of 25.94. We introduce a multilingual NMT model that tags all glossed text with gloss-source language tags and train a universal system with shared attention across 1,497 languages. Secondly, we use the IGT gloss-to-target translation as a key step in an English-Turkish MT system trained on only 865 lines from ODIN. Thirdly, we we present five metrics for evaluating extremely low-resource translation when BLEU is no longer sufficient and evaluate the Turkish low-resource system using BLEU and also using accuracy of matching nouns, verbs, agreement, tense, and spurious repetition, showing large improvements.

Xinjian Li, Zhong Zhou, Siddharth Dalmia et al.

While low resource speech recognition has attracted a lot of attention from the speech community, there are a few tools available to facilitate low resource speech collection. In this work, we present SANTLR: Speech Annotation Toolkit for Low Resource Languages. It is a web-based toolkit which allows researchers to easily collect and annotate a corpus of speech in a low resource language. Annotators may use this toolkit for two purposes: transcription or recording. In transcription, annotators would transcribe audio files provided by the researchers; in recording, annotators would record their voice by reading provided texts. We highlight two properties of this toolkit. First, SANTLR has a very user-friendly User Interface (UI). Both researchers and annotators may use this simple web interface to interact. There is no requirement for the annotators to have any expertise in audio or text processing. The toolkit would handle all preprocessing and postprocessing steps. Second, we employ a multi-step ranking mechanism facilitate the annotation process. In particular, the toolkit would give higher priority to utterances which are easier to annotate and are more beneficial to achieving the goal of the annotation, e.g. quickly training an acoustic model.

Qichuan Geng, Hong Zhang, Xinyu Huang et al.

Part information has been shown to be resistant to occlusions and viewpoint changes, which is beneficial for various vision-related tasks. However, we found very limited work in car pose estimation and reconstruction from street views leveraging the part information. There are two major contributions in this paper. Firstly, we make the first attempt to build a framework to simultaneously estimate shape, translation, orientation, and semantic parts of cars in 3D space from a single street view. As it is labor-intensive to annotate semantic parts on real street views, we propose a specific approach to implicitly transfer part features from synthesized images to real street views. For pose and shape estimation, we propose a novel network structure that utilizes both part features and 3D losses. Secondly, we are the first to construct a high-quality dataset that contains 348 different car models with physical dimensions and part-level annotations based on global and local deformations. Given these models, we further generate 60K synthesized images with randomization of orientation, illumination, occlusion, and texture. Our results demonstrate that our part segmentation performance is significantly improved after applying our implicit transfer approach. Our network for pose and shape estimation achieves the state-of-the-art performance on the ApolloCar3D dataset and outperforms 3D-RCNN and DeepMANTA by 12.57 and 8.91 percentage points in terms of mean A3DP-Abs.

Zhong Zhou, Matthias Sperber, Alex Waibel

Paraphrases, the rewordings of the same semantic meaning, are useful for improving generalization and translation. However, prior works only explore paraphrases at the word or phrase level, not at the sentence or corpus level. Unlike previous works that only explore paraphrases at the word or phrase level, we use different translations of the whole training data that are consistent in structure as paraphrases at the corpus level. We train on parallel paraphrases in multiple languages from various sources. We treat paraphrases as foreign languages, tag source sentences with paraphrase labels, and train on parallel paraphrases in the style of multilingual Neural Machine Translation (NMT). Our multi-paraphrase NMT that trains only on two languages outperforms the multilingual baselines. Adding paraphrases improves the rare word translation and increases entropy and diversity in lexical choice. Adding the source paraphrases boosts performance better than adding the target ones. Combining both the source and the target paraphrases lifts performance further; combining paraphrases with multilingual data helps but has mixed performance. We achieve a BLEU score of 57.2 for French-to-English translation using 24 corpus-level paraphrases of the Bible, which outperforms the multilingual baselines and is +34.7 above the single-source single-target NMT baseline.

Qichuan Geng, Xinyu Huang, Zhong Zhou et al.

Confusing classes that are ubiquitous in real world often degrade performance for many vision related applications like object detection, classification, and segmentation. The confusion errors are not only caused by similar visual patterns but also amplified by various factors during the training of our designed models, such as reduced feature resolution in the encoding process or imbalanced data distributions. A large amount of deep learning based network structures has been proposed in recent years to deal with these individual factors and improve network performance. However, to our knowledge, no existing work in semantic image segmentation is designed to tackle confusion errors explicitly. In this paper, we present a novel and general network structure that reduces confusion errors in more direct manner and apply the network for semantic segmentation. There are two major contributions in our network structure: 1) We ensemble subnets with heterogeneous output spaces based on the discriminative confusing groups. The training for each subnet can distinguish confusing classes within the group without affecting unrelated classes outside the group. 2) We propose an improved cross-entropy loss function that maximizes the probability assigned to the correct class and penalizes the probabilities assigned to the confusing classes at the same time. Our network structure is a general structure and can be easily adapted to any other networks to further reduce confusion errors. Without any changes in the feature encoder and post-processing steps, our experiments demonstrate consistent and significant improvements on different baseline models on Cityscapes and PASCAL VOC datasets (e.g., 3.05% over ResNet-101 and 1.30% over ResNet-38).

Zhong Zhou, Matthias Sperber, Alex Waibel

We work on translation from rich-resource languages to low-resource languages. The main challenges we identify are the lack of low-resource language data, effective methods for cross-lingual transfer, and the variable-binding problem that is common in neural systems. We build a translation system that addresses these challenges using eight European language families as our test ground. Firstly, we add the source and the target family labels and study intra-family and inter-family influences for effective cross-lingual transfer. We achieve an improvement of +9.9 in BLEU score for English-Swedish translation using eight families compared to the single-family multi-source multi-target baseline. Moreover, we find that training on two neighboring families closest to the low-resource language is often enough. Secondly, we construct an ablation study and find that reasonably good results can be achieved even with considerably less target data. Thirdly, we address the variable-binding problem by building an order-preserving named entity translation model. We obtain 60.6% accuracy in qualitative evaluation where our translations are akin to human translations in a preliminary study.

Bhuwan Dhingra, Zhong Zhou, Dylan Fitzpatrick et al.

Text from social media provides a set of challenges that can cause traditional NLP approaches to fail. Informal language, spelling errors, abbreviations, and special characters are all commonplace in these posts, leading to a prohibitively large vocabulary size for word-level approaches. We propose a character composition model, tweet2vec, which finds vector-space representations of whole tweets by learning complex, non-local dependencies in character sequences. The proposed model outperforms a word-level baseline at predicting user-annotated hashtags associated with the posts, doing significantly better when the input contains many out-of-vocabulary words or unusual character sequences. Our tweet2vec encoder is publicly available.