Pixel-based language models process text rendered as images, which allows them to handle any script, making them a promising approach to open vocabulary language modelling. However, recent approaches use text renderers that produce a large set of almost-equivalent input patches, which may prove sub-optimal for downstream tasks, due to redundancy in the input representations. In this paper, we investigate four approaches to rendering text in the PIXEL model (Rust et al., 2023), and find that simple character bigram rendering brings improved performance on sentence-level tasks without compromising performance on token-level or multilingual tasks. This new rendering strategy also makes it possible to train a more compact model with only 22M parameters that performs on par with the original 86M parameter model. Our analyses show that character bigram rendering leads to a consistently better model but with an anisotropic patch embedding space, driven by a patch frequency bias, highlighting the connections between image patch- and tokenization-based language models.

Pretrained machine learning models are known to perpetuate and even amplify existing biases in data, which can result in unfair outcomes that ultimately impact user experience. Therefore, it is crucial to understand the mechanisms behind those prejudicial biases to ensure that model performance does not result in discriminatory behaviour toward certain groups or populations. In this work, we define gender bias as our case study. We quantify bias amplification in pretraining and after fine-tuning on three families of vision-and-language models. We investigate the connection, if any, between the two learning stages, and evaluate how bias amplification reflects on model performance. Overall, we find that bias amplification in pretraining and after fine-tuning are independent. We then examine the effect of continued pretraining on gender-neutral data, finding that this reduces group disparities, i.e., promotes fairness, on VQAv2 and retrieval tasks without significantly compromising task performance.

Multilingual image captioning has recently been tackled by training with large-scale machine translated data, which is an expensive, noisy, and time-consuming process. Without requiring any multilingual caption data, we propose LMCap, an image-blind few-shot multilingual captioning model that works by prompting a language model with retrieved captions. Specifically, instead of following the standard encoder-decoder paradigm, given an image, LMCap first retrieves the captions of similar images using a multilingual CLIP encoder. These captions are then combined into a prompt for an XGLM decoder, in order to generate captions in the desired language. In other words, the generation model does not directly process the image, instead processing retrieved captions. Experiments on the XM3600 dataset of geographically diverse images show that our model is competitive with fully-supervised multilingual captioning models, without requiring any supervised training on any captioning data.

Recent advances in image captioning are mainly driven by large-scale vision-language pretraining, relying heavily on computational resources and increasingly large multimodal datasets. Instead of scaling up pretraining data, we ask whether it is possible to improve performance by improving the quality of the samples in existing datasets. We pursue this question through two approaches to data curation: one that assumes that some examples should be avoided due to mismatches between the image and caption, and one that assumes that the mismatch can be addressed by replacing the image, for which we use the state-of-the-art Stable Diffusion model. These approaches are evaluated using the BLIP model on MS COCO and Flickr30K in both finetuning and few-shot learning settings. Our simple yet effective approaches consistently outperform baselines, indicating that better image captioning models can be trained by curating existing resources. Finally, we conduct a human study to understand the errors made by the Stable Diffusion model and highlight directions for future work in text-to-image generation.

Language models are defined over a finite set of inputs, which creates a vocabulary bottleneck when we attempt to scale the number of supported languages. Tackling this bottleneck results in a trade-off between what can be represented in the embedding matrix and computational issues in the output layer. This paper introduces PIXEL, the Pixel-based Encoder of Language, which suffers from neither of these issues. PIXEL is a pretrained language model that renders text as images, making it possible to transfer representations across languages based on orthographic similarity or the co-activation of pixels. PIXEL is trained to reconstruct the pixels of masked patches instead of predicting a distribution over tokens. We pretrain the 86M parameter PIXEL model on the same English data as BERT and evaluate on syntactic and semantic tasks in typologically diverse languages, including various non-Latin scripts. We find that PIXEL substantially outperforms BERT on syntactic and semantic processing tasks on scripts that are not found in the pretraining data, but PIXEL is slightly weaker than BERT when working with Latin scripts. Furthermore, we find that PIXEL is more robust than BERT to orthographic attacks and linguistic code-switching, further confirming the benefits of modelling language with pixels.

Recent advances in image captioning have focused on scaling the data and model size, substantially increasing the cost of pre-training and finetuning. As an alternative to large models, we present SmallCap, which generates a caption conditioned on an input image and related captions retrieved from a datastore. Our model is lightweight and fast to train, as the only learned parameters are in newly introduced cross-attention layers between a pre-trained CLIP encoder and GPT-2 decoder. SmallCap can transfer to new domains without additional finetuning and can exploit large-scale data in a training-free fashion since the contents of the datastore can be readily replaced. Our experiments show that SmallCap, trained only on COCO, has competitive performance on this benchmark, and also transfers to other domains without retraining, solely through retrieval from target-domain data. Further improvement is achieved through the training-free exploitation of diverse human-labeled and web data, which proves to be effective for a range of domains, including the nocaps benchmark, designed to test generalization to unseen visual concepts.

Inspired by retrieval-augmented language generation and pretrained Vision and Language (V&L) encoders, we present a new approach to image captioning that generates sentences given the input image and a set of captions retrieved from a datastore, as opposed to the image alone. The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions. Experimental results on the COCO dataset show that image captioning can be effectively formulated from this new perspective. Our model, named EXTRA, benefits from using captions retrieved from the training dataset, and it can also benefit from using an external dataset without the need for retraining. Ablation studies show that retrieving a sufficient number of captions (e.g., k=5) can improve captioning quality. Our work contributes towards using pretrained V&L encoders for generative tasks, instead of standard classification tasks.

The design of widespread vision-and-language datasets and pre-trained encoders directly adopts, or draws inspiration from, the concepts and images of ImageNet. While one can hardly overestimate how much this benchmark contributed to progress in computer vision, it is mostly derived from lexical databases and image queries in English, resulting in source material with a North American or Western European bias. Therefore, we devise a new protocol to construct an ImageNet-style hierarchy representative of more languages and cultures. In particular, we let the selection of both concepts and images be entirely driven by native speakers, rather than scraping them automatically. Specifically, we focus on a typologically diverse set of languages, namely, Indonesian, Mandarin Chinese, Swahili, Tamil, and Turkish. On top of the concepts and images obtained through this new protocol, we create a multilingual dataset for {M}ulticultur{a}l {R}easoning over {V}ision and {L}anguage (MaRVL) by eliciting statements from native speaker annotators about pairs of images. The task consists of discriminating whether each grounded statement is true or false. We establish a series of baselines using state-of-the-art models and find that their cross-lingual transfer performance lags dramatically behind supervised performance in English. These results invite us to reassess the robustness and accuracy of current state-of-the-art models beyond a narrow domain, but also open up new exciting challenges for the development of truly multilingual and multicultural systems.

Approaches to Grounded Language Learning typically focus on a single task-based final performance measure that may not depend on desirable properties of the learned hidden representations, such as their ability to predict salient attributes or to generalise to unseen situations. To remedy this, we present GROLLA, an evaluation framework for Grounded Language Learning with Attributes with three sub-tasks: 1) Goal-oriented evaluation; 2) Object attribute prediction evaluation; and 3) Zero-shot evaluation. We also propose a new dataset CompGuessWhat?! as an instance of this framework for evaluating the quality of learned neural representations, in particular concerning attribute grounding. To this end, we extend the original GuessWhat?! dataset by including a semantic layer on top of the perceptual one. Specifically, we enrich the VisualGenome scene graphs associated with the GuessWhat?! images with abstract and situated attributes. By using diagnostic classifiers, we show that current models learn representations that are not expressive enough to encode object attributes (average F1 of 44.27). In addition, they do not learn strategies nor representations that are robust enough to perform well when novel scenes or objects are involved in gameplay (zero-shot best accuracy 50.06%).

Image captioning models are usually evaluated on their ability to describe a held-out set of images, not on their ability to generalize to unseen concepts. We study the problem of compositional generalization, which measures how well a model composes unseen combinations of concepts when describing images. State-of-the-art image captioning models show poor generalization performance on this task. We propose a multi-task model to address the poor performance, that combines caption generation and image--sentence ranking, and uses a decoding mechanism that re-ranks the captions according their similarity to the image. This model is substantially better at generalizing to unseen combinations of concepts compared to state-of-the-art captioning models.