Recent Large Vision-Language Models (LVLMs) demonstrate impressive abilities on numerous image understanding and reasoning tasks. The task of fine-grained object classification (e.g., distinction between animal species), however, has been probed insufficiently, despite its downstream importance. We fill this evaluation gap by creating FOCI (Fine-grained Object ClassIfication), a difficult multiple-choice benchmark for fine-grained object classification, from existing object classification datasets: (1) multiple-choice avoids ambiguous answers associated with casting classification as open-ended QA task; (2) we retain classification difficulty by mining negative labels with a CLIP model. FOCI complements five popular classification datasets with four domain-specific subsets from ImageNet-21k. We benchmark 12 public LVLMs on and show that it tests for a complementary skill to established image understanding and reasoning benchmarks. Crucially, CLIP models exhibit dramatically better performance than LVLMs. Since the image encoders of LVLMs come from these CLIP models, this points to inadequate alignment for fine-grained object distinction between the encoder and the LLM and warrants (pre)training data with more fine-grained annotation. We release our code at ANONYMIZED.

Large vision-language models (LVLMs) have recently dramatically pushed the state of the art in image captioning and many image understanding tasks (e.g., visual question answering). LVLMs, however, often hallucinate and produce captions that mention concepts that cannot be found in the image. These hallucinations erode the trustworthiness of LVLMs and are arguably among the main obstacles to their ubiquitous adoption. Recent work suggests that addition of grounding objectives—those that explicitly align image regions or objects to text spans—reduces the amount of LVLM hallucination. Although intuitive, this claim is not empirically justified as the reduction effects have been established, we argue, with flawed evaluation protocols that (i) rely on data (i.e., MSCOCO) that has been extensively used in LVLM training and (ii) measure hallucination via question answering rather than open-ended caption generation.In this work, in contrast, we offer the first systematic analysis of the effect of fine-grained object grounding on LVLM hallucination under an evaluation protocol that more realistically captures LVLM hallucination in open generation. Our extensive experiments over three backbone LLMs reveal that grounding objectives have little to no effect on object hallucination in open caption generation.

Modular vision-language models (Vision-LLMs) align pretrained image encoders with (frozen) large language models (LLMs) and post-hoc condition LLMs to ‘understand’ the image input. With the abundance of readily available high-quality English image-text data as well as strong monolingual English LLMs, the research focus has been on English-only Vision-LLMs. Multilingual vision-language models are still predominantly obtained via expensive end-to-end pretraining, resulting in comparatively smaller models, trained on limited multilingual image data supplemented with text-only multilingual corpora. We present mBLIP, the first Vision-LLM leveraging multilingual LLMs, which we obtain in a computationally efficient manner on consumer-level hardware. To this end, we re-align an image encoder previously tuned to an English LLM to a new, multilingual LLM using only a few million multilingual training examples derived from a mix of vision-and-language tasks, which we obtain by machine-translating high-quality English data to 95 languages. On the IGLUE benchmark and XM3600, mBLIP yields results competitive with state-of-the-art models and it greatly outperforms strong English-only Vision-LLMs like Llava 1.5. We release our model, code, and train data at https://github.com/gregor-ge/mBLIP.

Large-scale pretraining of vision-language (VL) models brought dramatic improvements across numerous tasks, from visual question-answering to cross-modal retrieval but these gains are mostly limited to English. Massively multilingual VL encoder models (mVLMs) hold promise for other languages: after fine-tuning on only English task data, they can perform the task in other languages in what is termed zero-shot cross-lingual transfer (ZS-XLT). Still, ZS-XLT sees a large performance gap to English, especially for low-resource languages. In this work, we reduce this gap with a fine-tuning strategy known as Scheduled Unfreezing (SUF): instead of updating all parameters from the start, we begin with the top layer(s) of the vision-language encoder and gradually unfreeze (i.e., update) its layers top to bottom. SUF forces reliance on encoder’s representations from higher layers: the fact that in multilingual models these representations encode higher-level semantics rather than low-level language-specific idiosyncrasies, we hypothesize, should render SUF beneficial for ZS-XLT. Experiments with two mVLMs (UC2 & CCLM) on three downstream tasks (xGQA, XVNLI, xFlickrCo) show that SUF brings consistent gains in ZS-XLT, especially for visual Q&A (xGQA) by up to 10 points.

Vision-and-language (VL) models with separate encoders for each modality (e.g., CLIP) have become the go-to models for zero-shot image classification and image-text retrieval. They are, however, mostly evaluated in English as multilingual benchmarks are limited in availability. We introduce Babel-ImageNet, a massively multilingual benchmark that offers (partial) translations of ImageNet labels to 100 languages, built without machine translation or manual annotation. We instead automatically obtain reliable translations by linking them – via shared WordNet synsets – to BabelNet, a massively multilingual lexico-semantic network. We evaluate 11 public multilingual CLIP models on zero-shot image classification (ZS-IC) on our benchmark, demonstrating a significant gap between English ImageNet performance and that of high-resource languages (e.g., German or Chinese), and an even bigger gap for low-resource languages (e.g., Sinhala or Lao). Crucially, we show that the models’ ZS-IC performance highly correlates with their performance in image-text retrieval, validating the use of Babel-imageNet to evaluate multilingual models for the vast majority of languages without gold image-text data. Finally, we show that the performance of multilingual CLIP can be drastically improved for low-resource languages with parameter-efficient language-specific training. We make our code and data publicly available: https://github.com/gregor-ge/Babel-ImageNet

Current multimodal models, aimed at solving Vision and Language (V+L) tasks, predominantly repurpose Vision Encoders (VE) as feature extractors. While many VEs—of different architectures, trained on different data and objectives—are publicly available, they are not designed for the downstream V+L tasks. Nonetheless, most current work assumes that a single pre-trained VE can serve as a general-purpose encoder. In this work, we focus on analysis and aim to understand whether the information stored within different VEs is complementary, i.e. if providing the model with features from multiple VEs can improve the performance on a target task, and how they are combined. We exhaustively experiment with three popular VEs on six downstream V+L tasks and analyze the attention and VE-dropout patterns. Our analyses suggest that diverse VEs complement each other, resulting in improved downstream V+L task performance, where the improvements are not due to simple ensemble effects (i.e. the performance does not always improve when increasing the number of encoders). We demonstrate that future VEs, which are not repurposed, but explicitly designed for V+L tasks, have the potential of improving performance on the target V+L tasks.

Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e.g., extractive, abstractive), require different model architectures (e.g., generative, discriminative), and setups (e.g., with or without retrieval). Despite having a large number of powerful, specialized QA pipelines (which we refer to as Skills) that consider a single domain, model or setup, there exists no framework where users can easily explore and compare such pipelines and can extend them according to their needs. To address this issue, we present UKP-SQuARE, an extensible online QA platform for researchers which allows users to query and analyze a large collection of modern Skills via a user-friendly web interface and integrated behavioural tests. In addition, QA researchers can develop, manage, and share their custom Skills using our microservices that support a wide range of models (Transformers, Adapters, ONNX), datastores and retrieval techniques (e.g., sparse and dense). UKP-SQuARE is available on https://square.ukp-lab.de

Real-world politically-opinionated memes often rely on figurative language to cloak propaganda and radical ideas to help them spread. It is not only a scientific challenge to develop machine learning models to recognize them in memes, but also sociologically beneficial to understand hidden meanings at scale and raise awareness. These memes are fast-evolving (in both topics and visuals) and it remains unclear whether current multimodal machine learning models are robust to such distribution shifts. To enable future research into this area, we first present FigMemes, a dataset for figurative language classification in politically-opinionated memes. We evaluate the performance of state-of-the-art unimodal and multimodal models and provide comprehensive benchmark results. The key contributions of this proposed dataset include annotations of six commonly used types of figurative language in politically-opinionated memes, and a wide range of topics and visual styles.We also provide analyses on the ability of multimodal models to generalize across distribution shifts in memes. Our dataset poses unique machine learning challenges and our results show that current models have significant room for improvement in both performance and robustness to distribution shifts.

Recent advances in multimodal vision and language modeling have predominantly focused on the English language, mostly due to the lack of multilingual multimodal datasets to steer modeling efforts. In this work, we address this gap and provide xGQA, a new multilingual evaluation benchmark for the visual question answering task. We extend the established English GQA dataset to 7 typologically diverse languages, enabling us to detect and explore crucial challenges in cross-lingual visual question answering. We further propose new adapter-based approaches to adapt multimodal transformer-based models to become multilingual, and—vice versa—multilingual models to become multimodal. Our proposed methods outperform current state-of-the-art multilingual multimodal models (e.g., M3P) in zero-shot cross-lingual settings, but the accuracy remains low across the board; a performance drop of around 38 accuracy points in target languages showcases the difficulty of zero-shot cross-lingual transfer for this task. Our results suggest that simple cross-lingual transfer of multimodal models yields latent multilingual multimodal misalignment, calling for more sophisticated methods for vision and multilingual language modeling.

Current state-of-the-art approaches to cross- modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While offering unmatched retrieval performance, such models: 1) are typically pretrained from scratch and thus less scalable, 2) suffer from huge retrieval latency and inefficiency issues, which makes them impractical in realistic applications. To address these crucial gaps towards both improved and efficient cross- modal retrieval, we propose a novel fine-tuning framework that turns any pretrained text-image multi-modal model into an efficient retrieval model. The framework is based on a cooperative retrieve-and-rerank approach that combines: 1) twin networks (i.e., a bi-encoder) to separately encode all items of a corpus, enabling efficient initial retrieval, and 2) a cross-encoder component for a more nuanced (i.e., smarter) ranking of the retrieved small set of items. We also propose to jointly fine- tune the two components with shared weights, yielding a more parameter-efficient model. Our experiments on a series of standard cross-modal retrieval benchmarks in monolingual, multilingual, and zero-shot setups, demonstrate improved accuracy and huge efficiency benefits over the state-of-the-art cross- encoders.1

This paper presents our submissions to the WMT2021 Shared Task on Quality Estimation, Task 1 Sentence-Level Direct Assessment. While top-performing approaches utilize massively multilingual Transformer-based language models which have been pre-trained on all target languages of the task, the resulting insights are limited, as it is unclear how well the approach performs on languages unseen during pre-training; more problematically, these approaches do not provide any solutions for extending the model to new languages or unseen scripts—arguably one of the objectives of this shared task. In this work, we thus focus on utilizing massively multilingual language models which only partly cover the target languages during their pre-training phase. We extend the model to new languages and unseen scripts using recent adapter-based methods and achieve on par performance or even surpass models pre-trained on the respective languages.

Transformer models are expensive to fine-tune, slow for inference, and have large storage requirements. Recent approaches tackle these shortcomings by training smaller models, dynamically reducing the model size, and by training light-weight adapters. In this paper, we propose AdapterDrop, removing adapters from lower transformer layers during training and inference, which incorporates concepts from all three directions. We show that AdapterDrop can dynamically reduce the computational overhead when performing inference over multiple tasks simultaneously, with minimal decrease in task performances. We further prune adapters from AdapterFusion, which improves the inference efficiency while maintaining the task performances entirely.