Large pre-trained multimodal models have demonstrated significant success in a range of downstream tasks, including image captioning, image-text retrieval, visual question answering (VQA), etc. However, many of these methods rely on image-text pairs collected from the web as pre-training data and unfortunately overlook the need for fine-grained feature alignment between vision and language modalities, which requires detailed understanding of images and language expressions. While integrating VQA and dense captioning (DC) into pre-training can address this issue, acquiring image-question-answer as well as image-location-caption triplets is challenging and time-consuming. Additionally, publicly available datasets for VQA and dense captioning are typically limited in scale due to manual data collection and labeling efforts. In this paper, we propose a novel method called Joint QA and DC GEneration (JADE), which utilizes a pre-trained multimodal model and easily-crawled image-text pairs to automatically generate and filter large-scale VQA and dense captioning datasets. We apply this method to the Conceptual Caption (CC3M) dataset to generate a new dataset called CC3M-QA-DC. Experiments show that when used for pre-training in a multi-task manner, CC3M-QA-DC can improve the performance with various backbones on various downstream tasks. Furthermore, our generated CC3M-QA-DC can be combined with larger image-text datasets (e.g., CC15M) and achieve competitive results compared with models using much more data. Code and dataset will be released.
Text provides a compelling example of unstructured data that can be used to motivate and explore classification problems. Challenges arise regarding the representation of features of text and student linkage between text representations as character strings and identification of features that embed connections with underlying phenomena. In order to observe how students reason with text data in scenarios designed to elicit certain aspects of the domain, we employed a task-based interview method using a structured protocol with six pairs of undergraduate students. Our goal was to shed light on students' understanding of text as data using a motivating task to classify headlines as "clickbait" or "news". Three types of features (function, content, and form) surfaced, the majority from the first scenario. Our analysis of the interviews indicates that this sequence of activities engaged the participants in thinking at both the human-perception level and the computer-extraction level and conceptualizing connections between them.
Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years. Most of the existing methods either transfer the knowledge of image-text pretraining model to video-text retrieval task without fully exploring the multi-modal information of videos, or simply fuse multi-modal features in a brute force manner without explicit guidance. In this paper, we integrate multi-modal information in an explicit manner by tagging, and use the tags as the anchors for better video-text alignment. Various pretrained experts are utilized for extracting the information of multiple modalities, including object, person, motion, audio, etc. To take full advantage of these information, we propose the TABLE (TAgging Before aLignmEnt) network, which consists of a visual encoder, a tag encoder, a text encoder, and a tag-guiding cross-modal encoder for jointly encoding multi-frame visual features and multi-modal tags information. Furthermore, to strengthen the interaction between video and text, we build a joint cross-modal encoder with the triplet input of [vision, tag, text] and perform two additional supervised tasks, Video Text Matching (VTM) and Masked Language Modeling (MLM). Extensive experimental results demonstrate that the TABLE model is capable of achieving State-Of-The-Art (SOTA) performance on various video-text retrieval benchmarks, including MSR-VTT, MSVD, LSMDC and DiDeMo.
Ensuring that large language models (LMs) are fair, robust and useful requires an understanding of how different modifications to their inputs impact the model's behaviour. In the context of open-text generation tasks, however, such an evaluation is not trivial. For example, when introducing a model with an input text and a perturbed, "contrastive" version of it, meaningful differences in the next-token predictions may not be revealed with standard decoding strategies. With this motivation in mind, we propose Contrastive Input Decoding (CID): a decoding algorithm to generate text given two inputs, where the generated text is likely given one input but unlikely given the other. In this way, the contrastive generations can highlight potentially subtle differences in how the LM output differs for the two inputs in a simple and interpretable manner. We use CID to highlight context-specific biases that are hard to detect with standard decoding strategies and quantify the effect of different input perturbations.
Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are transformed into a learning signal - has recently shown promise in addressing these issues. However, such holistic feedback conveys limited information on long text outputs; it does not indicate which aspects of the outputs influenced user preference; e.g., which parts contain what type(s) of errors. In this paper, we use fine-grained human feedback (e.g., which sentence is false, which sub-sentence is irrelevant) as an explicit training signal. We introduce Fine-Grained RLHF, a framework that enables training and learning from reward functions that are fine-grained in two respects: (1) density, providing a reward after every segment (e.g., a sentence) is generated; and (2) incorporating multiple reward models associated with different feedback types (e.g., factual incorrectness, irrelevance, and information incompleteness). We conduct experiments on detoxification and long-form question answering to illustrate how learning with such reward functions leads to improved performance, supported by both automatic and human evaluation. Additionally, we show that LM behaviors can be customized using different combinations of fine-grained reward models. We release all data, collected human feedback, and codes at https://FineGrainedRLHF.github.io.
AI-based text-to-image generation has undergone a significant leap in the production of visually comprehensive and aesthetic imagery over the past year, to the point where differentiating between a man-made piece of art and an AI-generated image is becoming more difficult. Generative Models such as Stable Diffusion, Midjourney and others are expected to affect several major industries in technological and ethical aspects. Striking the balance between raising human standard of life and work vs exploiting one group of people to enrich another is a complex and crucial part of the discussion. Due to the rapid growth of this technology, the way in which its models operate, and gray area legalities, visual and artistic domains - including the video game industry, are at risk of being taken over from creators by AI infrastructure owners. This paper is a literature review examining the concerns facing both AI developers and users today, including identity theft, data laundering and more. It discusses legalization challenges and ethical concerns, and concludes with how AI generative models can be tremendously useful in streamlining the process of visual creativity in both static and interactive media given proper regulation. Keywords: AI text-to-image generation, Midjourney, Stable Diffusion, AI Ethics, Game Design, Digital Art, Data Laundering
Although remarkable progress on the neural table-to-text methods has been made, the generalization issues hinder the applicability of these models due to the limited source tables. Large-scale pretrained language models sound like a promising solution to tackle such issues. However, how to effectively bridge the gap between the structured table and the text input by fully leveraging table information to fuel the pretrained model is still not well explored. Besides, another challenge of integrating the deliberation mechanism into the text-to-text pretrained model for solving the table-to-text task remains seldom studied. In this paper, to implement the table-to-text generation with pretrained language model, we propose a table structure understanding and text deliberating approach, namely TASD. Specifically, we devise a three-layered multi-head attention network to realize the table-structure-aware text generation model with the help of the pretrained language model. Furthermore, a multi-pass decoder framework is adopted to enhance the capability of polishing generated text for table descriptions. The empirical studies, as well as human evaluation, on two public datasets, validate that our approach can generate faithful and fluent descriptive texts for different types of tables.
In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video. Benefiting from fine-grained 3D visual features, the TVG techniques have achieved remarkable progress in recent years. However, the high complexity of 3D convolutional neural networks (CNNs) makes extracting dense 3D visual features time-consuming, which calls for intensive memory and computing resources. Towards efficient TVG, we propose a novel text-visual prompting (TVP) framework, which incorporates optimized perturbation patterns (that we call 'prompts') into both visual inputs and textual features of a TVG model. In sharp contrast to 3D CNNs, we show that TVP allows us to effectively co-train vision encoder and language encoder in a 2D TVG model and improves the performance of crossmodal feature fusion using only low-complexity sparse 2D visual features. The proposed prompts also compensate for the lack of spatiotemporal information in 2D CNNs for visual feature extraction. Further, we propose a TemporalDistance IoU (TDIoU) loss for efficient learning of TVG. Last but not least, extensive experiments on two benchmark datasets, Charades-STA and ActivityNet Captions datasets, empirically show that the proposed TVP significantly boosts the performance of 2D TVG (e.g., 9.79% improvement in Charades-STA and 30.77% improvement in ActivityNet Captions) and achieves 5x inference acceleration over TVG of using 3D visual features. Code and model will be released.
There has been tremendous progress in large-scale text-to-image synthesis driven by diffusion models enabling versatile downstream applications such as 3D object synthesis from texts, image editing, and customized generation. We present a generic approach using latent diffusion models as powerful image priors for various visual synthesis tasks. Existing methods that utilize such priors fail to use these models' full capabilities. To improve this, our core ideas are 1) a feature matching loss between features from different layers of the decoder to provide detailed guidance and 2) a KL divergence loss to regularize the predicted latent features and stabilize the training. We demonstrate the efficacy of our approach on three different applications, text-to-3D, StyleGAN adaptation, and layered image editing. Extensive results show our method compares favorably against baselines.
Recent years have witnessed a rapid growth of deep generative models, with text-to-image models gaining significant attention from the public. However, existing models often generate images that do not align well with human aesthetic preferences, such as awkward combinations of limbs and facial expressions. To address this issue, we collect a dataset of human choices on generated images from the Stable Foundation Discord channel. Our experiments demonstrate that current evaluation metrics for generative models do not correlate well with human choices. Thus, we train a human preference classifier with the collected dataset and derive a Human Preference Score (HPS) based on the classifier. Using the HPS, we propose a simple yet effective method to adapt Stable Diffusion to better align with human aesthetic preferences. Our experiments show that the HPS outperforms CLIP in predicting human choices and has good generalization capability towards images generated from other models. By tuning Stable Diffusion with the guidance of the HPS, the adapted model is able to generate images that are more preferred by human users.