Discovering the existence of universal adversarial perturbations had large theoretical and practical impacts on the field of adversarial learning. In the text domain, most universal studies focused on adversarial prefixes which are added to all texts. However, unlike the vision domain, adding the same perturbation to different inputs results in noticeably unnatural inputs. Therefore, we introduce a new universal adversarial setup - a universal adversarial policy, which has many advantages of other universal attacks but also results in valid texts - thus making it relevant in practice. We achieve this by learning a single search policy over a predefined set of semantics preserving text alterations, on many texts. This formulation is universal in that the policy is successful in finding adversarial examples on new texts efficiently. Our approach uses text perturbations which were extensively shown to produce natural attacks in the non-universal setup (specific synonym replacements). We suggest a strong baseline approach for this formulation which uses reinforcement learning. It's ability to generalise (from as few as 500 training texts) shows that universal adversarial patterns exist in the text domain as well.
Arbitrary-shaped scene text detection is a challenging task due to the variety of text changes in font, size, color, and orientation. Most existing regression based methods resort to regress the masks or contour points of text regions to model the text instances. However, regressing the complete masks requires high training complexity, and contour points are not sufficient to capture the details of highly curved texts. To tackle the above limitations, we propose a novel light-weight anchor-free text detection framework called TextDCT, which adopts the discrete cosine transform (DCT) to encode the text masks as compact vectors. Further, considering the imbalanced number of training samples among pyramid layers, we only employ a single-level head for top-down prediction. To model the multi-scale texts in a single-level head, we introduce a novel positive sampling strategy by treating the shrunk text region as positive samples, and design a feature awareness module (FAM) for spatial-awareness and scale-awareness by fusing rich contextual information and focusing on more significant features. Moreover, we propose a segmented non-maximum suppression (S-NMS) method that can filter low-quality mask regressions. Extensive experiments are conducted on four challenging datasets, which demonstrate our TextDCT obtains competitive performance on both accuracy and efficiency. Specifically, TextDCT achieves F-measure of 85.1 at 17.2 frames per second (FPS) and F-measure of 84.9 at 15.1 FPS for CTW1500 and Total-Text datasets, respectively.
Personalization of speech models on mobile devices (on-device personalization) is an active area of research, but more often than not, mobile devices have more text-only data than paired audio-text data. We explore training a personalized language model on text-only data, used during inference to improve speech recognition performance for that user. We experiment on a user-clustered LibriSpeech corpus, supplemented with personalized text-only data for each user from Project Gutenberg. We release this User-Specific LibriSpeech (UserLibri) dataset to aid future personalization research. LibriSpeech audio-transcript pairs are grouped into 55 users from the test-clean dataset and 52 users from test-other. We are able to lower the average word error rate per user across both sets in streaming and nonstreaming models, including an improvement of 2.5 for the harder set of test-other users when streaming.
3D face generation has achieved high visual quality and 3D consistency thanks to the development of neural radiance fields (NeRF). Recently, to generate and edit 3D faces with NeRF representation, some methods are proposed and achieve good results in decoupling geometry and texture. The latent codes of these generative models affect the whole face, and hence modifications to these codes cause the entire face to change. However, users usually edit a local region when editing faces and do not want other regions to be affected. Since changes to the latent code affect global generation results, these methods do not allow for fine-grained control of local facial regions. To improve local controllability in NeRF-based face editing, we propose LC-NeRF, which is composed of a Local Region Generators Module and a Spatial-Aware Fusion Module, allowing for local geometry and texture control of local facial regions. Qualitative and quantitative evaluations show that our method provides better local editing than state-of-the-art face editing methods. Our method also performs well in downstream tasks, such as text-driven facial image editing.
Handwritten Chinese text recognition (HCTR) has been an active research topic for decades. However, most previous studies solely focus on the recognition of cropped text line images, ignoring the error caused by text line detection in real-world applications. Although some approaches aimed at page-level text recognition have been proposed in recent years, they either are limited to simple layouts or require very detailed annotations including expensive line-level and even character-level bounding boxes. To this end, we propose PageNet for end-to-end weakly supervised page-level HCTR. PageNet detects and recognizes characters and predicts the reading order between them, which is more robust and flexible when dealing with complex layouts including multi-directional and curved text lines. Utilizing the proposed weakly supervised learning framework, PageNet requires only transcripts to be annotated for real data; however, it can still output detection and recognition results at both the character and line levels, avoiding the labor and cost of labeling bounding boxes of characters and text lines. Extensive experiments conducted on five datasets demonstrate the superiority of PageNet over existing weakly supervised and fully supervised page-level methods. These experimental results may spark further research beyond the realms of existing methods based on connectionist temporal classification or attention. The source code is available at https://github.com/shannanyinxiang/PageNet.
Is it possible for machines to think like humans? And if it is, how should we go about teaching them to do so? As early as 1950, Alan Turing stated that we ought to teach machines in the way of teaching a child. Reinforcement learning with human feedback (RLHF) has emerged as a strong candidate toward allowing agents to learn from human feedback in a naturalistic manner. RLHF is distinct from traditional reinforcement learning as it provides feedback from a human teacher in addition to a reward signal. It has been catapulted into public view by multiple high-profile AI applications, including OpenAI's ChatGPT, DeepMind's Sparrow, and Anthropic's Claude. These highly capable chatbots are already overturning our understanding of how AI interacts with humanity. The wide applicability and burgeoning success of RLHF strongly motivate the need to evaluate its social impacts. In light of recent developments, this paper considers an important question: can RLHF be developed and used without negatively affecting human societies? Our objectives are threefold: to provide a systematic study of the social effects of RLHF; to identify key social and ethical issues of RLHF; and to discuss social impacts for stakeholders. Although text-based applications of RLHF have received much attention, it is crucial to consider when evaluating its social implications the diverse range of areas to which it may be deployed. We describe seven primary ways in which RLHF-based technologies will affect society by positively transforming human experiences with AI. This paper ultimately proposes that RLHF has potential to net positively impact areas of misinformation, AI value-alignment, bias, AI access, cross-cultural dialogue, industry, and workforce. As RLHF raises concerns that echo those of existing AI technologies, it will be important for all to be aware and intentional in the adoption of RLHF.
Large-scale multi-modal pre-training models such as CLIP and PaLI exhibit strong generalization on various visual domains and tasks. However, existing image classification benchmarks often evaluate recognition on a specific domain (e.g., outdoor images) or a specific task (e.g., classifying plant species), which falls short of evaluating whether pre-trained foundational models are universal visual recognizers. To address this, we formally present the task of Open-domain Visual Entity recognitioN (OVEN), where a model need to link an image onto a Wikipedia entity with respect to a text query. We construct OVEN-Wiki by re-purposing 14 existing datasets with all labels grounded onto one single label space: Wikipedia entities. OVEN challenges models to select among six million possible Wikipedia entities, making it a general visual recognition benchmark with the largest number of labels. Our study on state-of-the-art pre-trained models reveals large headroom in generalizing to the massive-scale label space. We show that a PaLI-based auto-regressive visual recognition model performs surprisingly well, even on Wikipedia entities that have never been seen during fine-tuning. We also find existing pretrained models yield different strengths: while PaLI-based models obtain higher overall performance, CLIP-based models are better at recognizing tail entities.
Adopting contextually appropriate, audience-tailored linguistic styles is critical to the success of user-centric language generation systems (e.g., chatbots, computer-aided writing, dialog systems). While existing approaches demonstrate textual style transfer with large volumes of parallel or non-parallel data, we argue that grounding style on audience-independent external factors is innately limiting for two reasons. First, it is difficult to collect large volumes of audience-specific stylistic data. Second, some stylistic objectives (e.g., persuasiveness, memorability, empathy) are hard to define without audience feedback. In this paper, we propose the novel task of style infusion - infusing the stylistic preferences of audiences in pretrained language generation models. Since humans are better at pairwise comparisons than direct scoring - i.e., is Sample-A more persuasive/polite/empathic than Sample-B - we leverage limited pairwise human judgments to bootstrap a style analysis model and augment our seed set of judgments. We then infuse the learned textual style in a GPT-2 based text generator while balancing fluency and style adoption. With quantitative and qualitative assessments, we show that our infusion approach can generate compelling stylized examples with generic text prompts. The code and data are accessible at https://github.com/CrowdDynamicsLab/StyleInfusion.
Retrieval-augmented generation models offer many benefits over standalone language models: besides a textual answer to a given query they provide provenance items retrieved from an updateable knowledge base. However, they are also more complex systems and need to handle long inputs. In this work, we introduce FiD-Light to strongly increase the efficiency of the state-of-the-art retrieval-augmented FiD model, while maintaining the same level of effectiveness. Our FiD-Light model constrains the information flow from the encoder (which encodes passages separately) to the decoder (using concatenated encoded representations). Furthermore, we adapt FiD-Light with re-ranking capabilities through textual source pointers, to improve the top-ranked provenance precision. Our experiments on a diverse set of seven knowledge intensive tasks (KILT) show FiD-Light consistently improves the Pareto frontier between query latency and effectiveness. FiD-Light with source pointing sets substantial new state-of-the-art results on six KILT tasks for combined text generation and provenance retrieval evaluation, while maintaining reasonable efficiency.
Vision-language models can assess visual context in an image and generate descriptive text. While the generated text may be accurate and syntactically correct, it is often overly general. To address this, recent work has used optical character recognition to supplement visual information with text extracted from an image. In this work, we contend that vision-language models can benefit from additional information that can be extracted from an image, but are not used by current models. We modify previous multimodal frameworks to accept relevant information from any number of auxiliary classifiers. In particular, we focus on person names as an additional set of tokens and create a novel image-caption dataset to facilitate captioning with person names. The dataset, Politicians and Athletes in Captions (PAC), consists of captioned images of well-known people in context. By fine-tuning pretrained models with this dataset, we demonstrate a model that can naturally integrate facial recognition tokens into generated text by training on limited data. For the PAC dataset, we provide a discussion on collection and baseline benchmark scores.