NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation

Despite impressive recent advances in text-to-image diffusion models, obtaining high-quality images often requires prompt engineering by humans who have developed expertise in using them. In this work, we present NeuroPrompts, an adaptive framework that automatically enhances a user's prompt to improve the quality of generations produced by text-to-image models. Our framework utilizes constrained text decoding with a pre-trained language model that has been adapted to generate prompts similar to those produced by human prompt engineers. This approach enables higher-quality text-to-image generations and provides user control over stylistic features via constraint set specification. We demonstrate the utility of our framework by creating an interactive application for prompt enhancement and image generation using Stable Diffusion. Additionally, we conduct experiments utilizing a large dataset of human-engineered prompts for text-to-image generation and show that our approach automatically produces enhanced prompts that result in superior image quality. We make our code, a screencast video demo and a live demo instance of NeuroPrompts publicly available.

ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning

Two-Tower Vision-Language (VL) models have shown promising improvements on various downstream VL tasks. Although the most advanced work improves performance by building bridges between encoders, it suffers from ineffective layer-by-layer utilization of uni-modal representations and cannot flexibly exploit different levels of uni-modal semantic knowledge. In this work, we propose ManagerTower, a novel VL model architecture that gathers and combines the insights of pre-trained uni-modal experts at different levels. The managers introduced in each cross-modal layer can adaptively aggregate uni-modal semantic knowledge to facilitate more comprehensive cross-modal alignment and fusion. ManagerTower outperforms previous strong baselines both with and without Vision-Language Pre-training (VLP). With only 4M VLP data, ManagerTower achieves superior performances on various downstream VL tasks, especially 79.15% accuracy on VQAv2 Test-Std, 86.56% IR@1 and 95.64% TR@1 on Flickr30K. Code and checkpoints are available at https://github.com/LooperXX/ManagerTower.

Bridge-Tower: Building Bridges Between Encoders in Vision-Language Representation Learning

Vision-Language (VL) models with the Two-Tower architecture have dominated visual-language representation learning in recent years. Current VL models either use lightweight uni-modal encoders and learn to extract, align and fuse both modalities simultaneously in a cross-modal encoder, or feed the last-layer uni-modal features directly into the top cross-modal encoder, ignoring the semantic information at the different levels in the deep uni-modal encoders. Both approaches possibly restrict vision-language representation learning and limit model performance. In this paper, we introduce multiple bridge layers that build a connection between the top layers of uni-modal encoders and each layer of the cross-modal encoder. This enables comprehensive bottom-up interactions between visual and textual representations at different semantic levels, resulting in more effective cross-modal alignment and fusion. Our proposed Bridge-Tower, pre-trained with only $4$M images, achieves state-of-the-art performance on various downstream vision-language tasks. On the VQAv2 test-std set, Bridge-Tower achieves an accuracy of $78.73\%$, outperforming the previous state-of-the-art METER model by $1.09\%$ with the same pre-training data and almost no additional parameters and computational cost. Notably, when further scaling the model, Bridge-Tower achieves an accuracy of $81.15\%$, surpassing models that are pre-trained on orders-of-magnitude larger datasets. Code is available at https://github.com/microsoft/BridgeTower.

Relation Extraction as Two-way Span-Prediction

The current supervised relation classification (RC) task uses a single embedding to represent the relation between a pair of entities. We argue that a better approach is to treat the RC task as a Question answering (QA) like span prediction problem. We present a span-prediction based system for RC and evaluate its performance compared to the embedding based system. We achieve state-of-the-art results on the TACRED and SemEval task 8 datasets.

Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data

The process of collecting and annotating training data may introduce distribution artifacts which may limit the ability of models to learn correct generalization behavior. We identify failure modes of SOTA relation extraction (RE) models trained on TACRED, which we attribute to limitations in the data annotation process. We collect and annotate a challenge-set we call Challenging RE (CRE), based on naturally occurring corpus examples, to benchmark this behavior. Our experiments with four state-of-the-art RE models show that they have indeed adopted shallow heuristics that do not generalize to the challenge-set data. Further, we find that alternative question answering modeling performs significantly better than the SOTA models on the challenge-set, despite worse overall TACRED performance. By adding some of the challenge data as training examples, the performance of the model improves. Finally, we provide concrete suggestion on how to improve RE data collection to alleviate this behavior.