In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we propose a transformer-based model for OVS, termed as OVSegmentor, which only exploits web-crawled image-text pairs for pre-training without using any mask annotations. OVSegmentor assembles the image pixels into a set of learnable group tokens via a slot-attention based binding module, and aligns the group tokens to the corresponding caption embedding. Second, we propose two proxy tasks for training, namely masked entity completion and cross-image mask consistency. The former aims to infer all masked entities in the caption given the group tokens, that enables the model to learn fine-grained alignment between visual groups and text entities. The latter enforces consistent mask predictions between images that contain shared entities, which encourages the model to learn visual invariance. Third, we construct CC4M dataset for pre-training by filtering CC12M with frequently appeared entities, which significantly improves training efficiency. Fourth, we perform zero-shot transfer on three benchmark datasets, PASCAL VOC 2012, PASCAL Context, and COCO Object. Our model achieves superior segmentation results over the state-of-the-art method by using only 3\% data (4M vs 134M) for pre-training. Code and pre-trained models will be released for future research.
5G is the 5th generation cellular network protocol. It is the state-of-the-art global wireless standard that enables an advanced kind of network designed to connect virtually everyone and everything with increased speed and reduced latency. Therefore, its development, analysis, and security are critical. However, all approaches to the 5G protocol development and security analysis, e.g., property extraction, protocol summarization, and semantic analysis of the protocol specifications and implementations are completely manual. To reduce such manual effort, in this paper, we curate SPEC5G the first-ever public 5G dataset for NLP research. The dataset contains 3,547,586 sentences with 134M words, from 13094 cellular network specifications and 13 online websites. By leveraging large-scale pre-trained language models that have achieved state-of-the-art results on NLP tasks, we use this dataset for security-related text classification and summarization. Security-related text classification can be used to extract relevant security-related properties for protocol testing. On the other hand, summarization can help developers and practitioners understand the high level of the protocol, which is itself a daunting task. Our results show the value of our 5G-centric dataset in 5G protocol analysis automation. We believe that SPEC5G will enable a new research direction into automatic analyses for the 5G cellular network protocol and numerous related downstream tasks. Our data and code are publicly available.
A deployed question answering (QA) model can easily fail when the test data has a distribution shift compared to the training data. Robustness tuning (RT) methods have been widely studied to enhance model robustness against distribution shifts before model deployment. However, can we improve a model after deployment? To answer this question, we evaluate test-time adaptation (TTA) to improve a model after deployment. We first introduce COLDQA, a unified evaluation benchmark for robust QA against text corruption and changes in language and domain. We then evaluate previous TTA methods on COLDQA and compare them to RT methods. We also propose a novel TTA method called online imitation learning (OIL). Through extensive experiments, we find that TTA is comparable to RT methods, and applying TTA after RT can significantly boost the performance on COLDQA. Our proposed OIL improves TTA to be more robust to variation in hyper-parameters and test distributions over time.
Recommendation systems have become popular and effective tools to help users discover their interesting items by modeling the user preference and item property based on implicit interactions (e.g., purchasing and clicking). Humans perceive the world by processing the modality signals (e.g., audio, text and image), which inspired researchers to build a recommender system that can understand and interpret data from different modalities. Those models could capture the hidden relations between different modalities and possibly recover the complementary information which can not be captured by a uni-modal approach and implicit interactions. The goal of this survey is to provide a comprehensive review of the recent research efforts on the multimodal recommendation. Specifically, it shows a clear pipeline with commonly used techniques in each step and classifies the models by the methods used. Additionally, a code framework has been designed that helps researchers new in this area to understand the principles and techniques, and easily runs the SOTA models. Our framework is located at: https://github.com/enoche/MMRec
Automatically converting text descriptions into images using transformer architectures has recently received considerable attention. Such advances have implications for many applied design disciplines across fashion, art, architecture, urban planning, landscape design and the future tools available to such disciplines. However, a detailed analysis capturing the capabilities of such models, specifically with a focus on the built environment, has not been performed to date. In this work, we investigate the capabilities and biases of such text-to-image methods as it applies to the built environment in detail. We use a systematic grammar to generate queries related to the built environment and evaluate resulting generated images. We generate 1020 different images and find that text to image transformers are robust at generating realistic images across different domains for this use-case. Generated imagery can be found at the github: https://github.com/sachith500/DALLEURBAN
Denoising diffusion models have spurred significant gains in density modeling and image generation, precipitating an industrial revolution in text-guided AI art generation. We introduce a new mathematical foundation for diffusion models inspired by classic results in information theory that connect Information with Minimum Mean Square Error regression, the so-called I-MMSE relations. We generalize the I-MMSE relations to exactly relate the data distribution to an optimal denoising regression problem, leading to an elegant refinement of existing diffusion bounds. This new insight leads to several improvements for probability distribution estimation, including theoretical justification for diffusion model ensembling. Remarkably, our framework shows how continuous and discrete probabilities can be learned with the same regression objective, avoiding domain-specific generative models used in variational methods. Code to reproduce experiments is provided at http://github.com/kxh001/ITdiffusion and simplified demonstration code is at http://github.com/gregversteeg/InfoDiffusionSimple.
Diffusion models achieve state-of-the-art performance in generating realistic objects and have been successfully applied to images, text, and videos. Recent work has shown that diffusion can also be defined on graphs, including graph representations of drug-like molecules. Unfortunately, it remains difficult to perform conditional generation on graphs in a way which is interpretable and controllable. In this work, we propose GraphGUIDE, a novel framework for graph generation using diffusion models, where edges in the graph are flipped or set at each discrete time step. We demonstrate GraphGUIDE on several graph datasets, and show that it enables full control over the conditional generation of arbitrary structural properties without relying on predefined labels. Our framework for graph diffusion can have a large impact on the interpretable conditional generation of graphs, including the generation of drug-like molecules with desired properties in a way which is informed by experimental evidence.
Formality is an important characteristic of text documents. The automatic detection of the formality level of a text is potentially beneficial for various natural language processing tasks, such as retrieval of texts with a desired formality level, integration in language learning and document editing platforms, or evaluating the desired conversation tone by chatbots. Recently two large-scale datasets were introduced for multiple languages featuring formality annotation. However, they were primarily used for the training of style transfer models. However, detection text formality on its own may also be a useful application. This work proposes the first systematic study of formality detection methods based on current (and more classic) machine learning methods and delivers the best-performing models for public usage. We conducted three types of experiments -- monolingual, multilingual, and cross-lingual. The study shows the overcome of BiLSTM-based models over transformer-based ones for the formality classification task. We release formality detection models for several languages yielding state of the art results and possessing tested cross-lingual capabilities.
Referring image segmentation aims to segment the image region of interest according to the given language expression, which is a typical multi-modal task. One of the critical challenges of this task is to align semantic representations for different modalities including vision and language. To achieve this, previous methods perform cross-modal interactions to update visual features but ignore the role of integrating fine-grained visual features into linguistic features. We present AlignFormer, an end-to-end framework for referring image segmentation. Our AlignFormer views the linguistic feature as the center embedding and segments the region of interest by pixels grouping based on the center embedding. For achieving the pixel-text alignment, we design a Vision-Language Bidirectional Attention module (VLBA) and resort contrastive learning. Concretely, the VLBA enhances visual features by propagating semantic text representations to each pixel and promotes linguistic features by fusing fine-grained image features. Moreover, we introduce the cross-modal instance contrastive loss to alleviate the influence of pixel samples in ambiguous regions and improve the ability to align multi-modal representations. Extensive experiments demonstrate that our AlignFormer achieves a new state-of-the-art performance on RefCOCO, RefCOCO+, and RefCOCOg by large margins.
Videos contain multi-modal content, and exploring multi-level cross-modal interactions with natural language queries can provide great prominence to text-video retrieval task (TVR). However, new trending methods applying large-scale pre-trained model CLIP for TVR do not focus on multi-modal cues in videos. Furthermore, the traditional methods simply concatenating multi-modal features do not exploit fine-grained cross-modal information in videos. In this paper, we propose a multi-level multi-modal hybrid fusion (M2HF) network to explore comprehensive interactions between text queries and each modality content in videos. Specifically, M2HF first utilizes visual features extracted by CLIP to early fuse with audio and motion features extracted from videos, obtaining audio-visual fusion features and motion-visual fusion features respectively. Multi-modal alignment problem is also considered in this process. Then, visual features, audio-visual fusion features, motion-visual fusion features, and texts extracted from videos establish cross-modal relationships with caption queries in a multi-level way. Finally, the retrieval outputs from all levels are late fused to obtain final text-video retrieval results. Our framework provides two kinds of training strategies, including an ensemble manner and an end-to-end manner. Moreover, a novel multi-modal balance loss function is proposed to balance the contributions of each modality for efficient end-to-end training. M2HF allows us to obtain state-of-the-art results on various benchmarks, eg, Rank@1 of 64.9\%, 68.2\%, 33.2\%, 57.1\%, 57.8\% on MSR-VTT, MSVD, LSMDC, DiDeMo, and ActivityNet, respectively.