As a pioneering vision-language model, CLIP (Contrastive Language-Image Pre-training) has achieved significant success across various domains and a wide range of downstream vision-language tasks. However, the text encoders in popular CLIP models are limited to processing only 77 text tokens, which constrains their ability to effectively handle longer, detail-rich captions. Additionally, CLIP models often struggle to effectively capture detailed visual and textual information, which hampers their performance on tasks that require fine-grained analysis. To address these limitations, we present a novel approach, \textbf{FineLIP}, that extends the capabilities of CLIP. FineLIP enhances cross-modal text-image mapping by incorporating \textbf{Fine}-grained alignment with \textbf{L}onger text input within the CL\textbf{IP}-style framework. FineLIP first extends the positional embeddings to handle longer text, followed by the dynamic aggregation of local image and text tokens. The aggregated results are then used to enforce fine-grained token-to-token cross-modal alignment. We validate our model on datasets with long, detailed captions across two tasks: zero-shot cross-modal retrieval and text-to-image generation. Quantitative and qualitative experimental results demonstrate the effectiveness of FineLIP, outperforming existing state-of-the-art approaches. Furthermore, comprehensive ablation studies validate the benefits of key design elements within FineLIP.
Foundation models have had a significant impact across various AI applications, enabling use cases that were previously impossible. Contrastive Visual Language Models (VLMs), in particular, have outperformed other techniques in many tasks. However, their prevalence in remote sensing (RS) is still limited, due to the scarcity of diverse remote-sensing visual-language datasets. In this work we introduce two novel image-caption datasets for training of remote sensing foundation models. The first dataset pairs aerial and satellite imagery with captions generated by Gemini using landmarks extracted from Google Maps. The second dataset utilizes public web images and their corresponding alt-text, filtered for the remote sensing domain, resulting in a diverse dataset with greater breadth in image styles and subject matter. These datasets are used to pre-train the MaMMUT~\citep{kuo2023mammutsimplearchitecturejoint} VLM architecture, resulting in state-of-the-art generalization performance in zero-shot cross-modal retrieval on well-known public benchmarks. Finally, we present our ongoing research to distill image-level knowledge gained in the VLM contrastive training procedure to enhance the model's localization ability. Specifically, we iteratively generate pseudo-labels for image regions based on the model's attention maps and use these labels for further training. To mitigate noisy attention maps and create robust segmentation masks, we introduce a novel attention-pooling mechanism called the Smooth-Attention-Operation.
Vision-Language Models (VLMs) trained with contrastive loss have achieved significant advancements in various vision and language tasks. However, the global nature of the contrastive loss makes VLMs focus predominantly on foreground objects, neglecting other crucial information in the image, which limits their effectiveness in downstream tasks. To address these challenges, we propose COSMOS: CrOSs-MOdality Self-distillation for vision-language pre-training that integrates a novel text-cropping strategy and cross-attention module into a self-supervised learning framework. We create global and local views of images and texts (i.e., multi-modal augmentations), which are essential for self-distillation in VLMs. We further introduce a cross-attention module, enabling COSMOS to learn comprehensive cross-modal representations optimized via a cross-modality self-distillation loss. COSMOS consistently outperforms previous strong baselines on various zero-shot downstream tasks, including retrieval, classification, and semantic segmentation. Additionally, it surpasses CLIP-based models trained on larger datasets in visual perception and contextual understanding tasks. Code is available at https://github.com/ExplainableML/cosmos.
Over 85 million computed tomography (CT) scans are performed annually in the US, of which approximately one quarter focus on the abdomen. Given the current radiologist shortage, there is a large impetus to use artificial intelligence to alleviate the burden of interpreting these complex imaging studies. Prior state-of-the-art approaches for automated medical image interpretation leverage vision language models (VLMs). However, current medical VLMs are generally limited to 2D images and short reports, and do not leverage electronic health record (EHR) data for supervision. We introduce Merlin - a 3D VLM that we train using paired CT scans (6+ million images from 15,331 CTs), EHR diagnosis codes (1.8+ million codes), and radiology reports (6+ million tokens). We evaluate Merlin on 6 task types and 752 individual tasks. The non-adapted (off-the-shelf) tasks include zero-shot findings classification (31 findings), phenotype classification (692 phenotypes), and zero-shot cross-modal retrieval (image to findings and image to impressions), while model adapted tasks include 5-year disease prediction (6 diseases), radiology report generation, and 3D semantic segmentation (20 organs). We perform internal validation on a test set of 5,137 CTs, and external validation on 7,000 clinical CTs and on two public CT datasets (VerSe, TotalSegmentator). Beyond these clinically-relevant evaluations, we assess the efficacy of various network architectures and training strategies to depict that Merlin has favorable performance to existing task-specific baselines. We derive data scaling laws to empirically assess training data needs for requisite downstream task performance. Furthermore, unlike conventional VLMs that require hundreds of GPUs for training, we perform all training on a single GPU.
Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence. Nevertheless, VLM models supporting multi-language, e.g., in both Chinese and English, have lagged due to the relative scarcity of large-scale pretraining datasets. Toward this end, we introduce a comprehensive bilingual (Chinese-English) dataset BM-6B with over 6 billion image-text pairs, aimed at enhancing multimodal foundation models to well understand images in both languages. To handle such a scale of dataset, we propose a novel grouped aggregation approach for image-text contrastive loss computation, which reduces the communication overhead and GPU memory demands significantly, facilitating a 60% increase in training speed. We pretrain a series of bilingual image-text foundation models with an enhanced fine-grained understanding ability on BM-6B, the resulting models, dubbed as $M^2$-Encoders (pronounced "M-Square"), set new benchmarks in both languages for multimodal retrieval and classification tasks. Notably, Our largest $M^2$-Encoder-10B model has achieved top-1 accuracies of 88.5% on ImageNet and 80.7% on ImageNet-CN under a zero-shot classification setting, surpassing previously reported SoTA methods by 2.2% and 21.1%, respectively. The $M^2$-Encoder series represents one of the most comprehensive bilingual image-text foundation models to date, so we are making it available to the research community for further exploration and development.
Vision and text have been fully explored in contemporary video-text foundational models, while other modalities such as audio and subtitles in videos have not received sufficient attention. In this paper, we resort to establish connections between multi-modality video tracks, including Vision, Audio, and Subtitle, and Text by exploring an automatically generated large-scale omni-modality video caption dataset called VAST-27M. Specifically, we first collect 27 million open-domain video clips and separately train a vision and an audio captioner to generate vision and audio captions. Then, we employ an off-the-shelf Large Language Model (LLM) to integrate the generated captions, together with subtitles and instructional prompts into omni-modality captions. Based on the proposed VAST-27M dataset, we train an omni-modality video-text foundational model named VAST, which can perceive and process vision, audio, and subtitle modalities from video, and better support various tasks including vision-text, audio-text, and multi-modal video-text tasks (retrieval, captioning and QA). Extensive experiments have been conducted to demonstrate the effectiveness of our proposed VAST-27M corpus and VAST foundation model. VAST achieves 22 new state-of-the-art results on various cross-modality benchmarks. Code, model and dataset will be released at https://github.com/TXH-mercury/VAST.
The exponential growth of large language models (LLMs) has opened up numerous possibilities for multimodal AGI systems. However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal AGI, has not kept pace with LLMs. In this work, we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on 32 generic visual-linguistic benchmarks including visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems. It has powerful visual capabilities and can be a good alternative to the ViT-22B. We hope that our research could contribute to the development of multi-modal large models. Code and models are available at https://github.com/OpenGVLab/InternVL.
We present Region-aware Open-vocabulary Vision Transformers (RO-ViT) - a contrastive image-text pretraining recipe to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we propose to randomly crop and resize regions of positional embeddings instead of using the whole image positional embeddings. This better matches the use of positional embeddings at region-level in the detection finetuning phase. In addition, we replace the common softmax cross entropy loss in contrastive learning with focal loss to better learn the informative yet difficult examples. Finally, we leverage recent advances in novel object proposals to improve open-vocabulary detection finetuning. We evaluate our full model on the LVIS and COCO open-vocabulary detection benchmarks and zero-shot transfer. RO-ViT achieves a state-of-the-art 34.1 $AP_r$ on LVIS, surpassing the best existing approach by +7.8 points in addition to competitive zero-shot transfer detection. Surprisingly, RO-ViT improves the image-level representation as well and achieves the state of the art on 9 out of 12 metrics on COCO and Flickr image-text retrieval benchmarks, outperforming competitive approaches with larger models.
Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into $N\times N$ blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates the visual grounding task into a fill-in-the-blank problem given a PTP by encouraging the model to predict the objects in the given blocks or regress the blocks of a given object, e.g. filling `P" or ``O" in aPTP ``The block P has a O". This mechanism improves the visual grounding capability of VLP models and thus helps them better handle various downstream tasks. By introducing PTP into several state-of-the-art VLP frameworks, we observe consistently significant improvements across representative cross-modal learning model architectures and several benchmarks, e.g. zero-shot Flickr30K Retrieval (+4.8 in average recall@1) for ViLT \cite{vilt} baseline, and COCO Captioning (+5.3 in CIDEr) for SOTA BLIP \cite{blip} baseline. Moreover, PTP achieves comparable results with object-detector based methods, and much faster inference speed since PTP discards its object detector for inference while the later cannot. Our code and pre-trained weight will be released at \url{https://github.com/sail-sg/ptp}.
Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments are becoming increasingly expensive. However, previous work on scaling laws has primarily used private data \& models or focused on uni-modal language or vision learning. To address these limitations, we investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source OpenCLIP repository. Our large-scale experiments involve models trained on up to two billion image-text pairs and identify power law scaling for multiple downstream tasks including zero-shot classification, retrieval, linear probing, and end-to-end fine-tuning. We find that the training distribution plays a key role in scaling laws as the OpenAI and OpenCLIP models exhibit different scaling behavior despite identical model architectures and similar training recipes. We open-source our evaluation workflow and all models, including the largest public CLIP models, to ensure reproducibility and make scaling laws research more accessible. Source code and instructions to reproduce this study will be available at https://github.com/LAION-AI/scaling-laws-openclip
In this work, we present a conceptually simple and effective method to train a strong bilingual/multilingual multimodal representation model. Starting from the pre-trained multimodal representation model CLIP released by OpenAI, we altered its text encoder with a pre-trained multilingual text encoder XLM-R, and aligned both languages and image representations by a two-stage training schema consisting of teacher learning and contrastive learning. We validate our method through evaluations of a wide range of tasks. We set new state-of-the-art performances on a bunch of tasks including ImageNet-CN, Flicker30k-CN, COCO-CN and XTD. Further, we obtain very close performances with CLIP on almost all tasks, suggesting that one can simply alter the text encoder in CLIP for extended capabilities such as multilingual understanding. Our models and code are available at https://github.com/FlagAI-Open/FlagAI.
Recent Vision-Language Pre-trained (VLP) models based on dual encoder have attracted extensive attention from academia and industry due to their superior performance on various cross-modal tasks and high computational efficiency. They attempt to learn cross-modal representation using contrastive learning on image-text pairs, however, the built inter-modal correlations only rely on a single view for each modality. Actually, an image or a text contains various potential views, just as humans could capture a real-world scene via diverse descriptions or photos. In this paper, we propose ERNIE-ViL 2.0, a Multi-View Contrastive learning framework to build intra-modal and inter-modal correlations between diverse views simultaneously, aiming at learning a more robust cross-modal representation. Specifically, we construct multiple views within each modality to learn the intra-modal correlation for enhancing the single-modal representation. Besides the inherent visual/textual views, we construct sequences of object tags as a special textual view to narrow the cross-modal semantic gap on noisy image-text pairs. Pre-trained with 29M publicly available datasets, ERNIE-ViL 2.0 achieves competitive results on English cross-modal retrieval. Additionally, to generalize our method to Chinese cross-modal tasks, we train ERNIE-ViL 2.0 through scaling up the pre-training datasets to 1.5B Chinese image-text pairs, resulting in significant improvements compared to previous SOTA results on Chinese cross-modal retrieval. We release our pre-trained models in https://github.com/PaddlePaddle/ERNIE.
Zero-shot cross-modal retrieval (ZS-CMR) deals with the retrieval problem among heterogenous data from unseen classes. Typically, to guarantee generalization, the pre-defined class embeddings from natural language processing (NLP) models are used to build a common space. In this paper, instead of using an extra NLP model to define a common space beforehand, we consider a totally different way to construct (or learn) a common hamming space from an information-theoretic perspective. We term our model the Information-Theoretic Hashing (ITH), which is composed of two cascading modules: an Adaptive Information Aggregation (AIA) module; and a Semantic Preserving Encoding (SPE) module. Specifically, our AIA module takes the inspiration from the Principle of Relevant Information (PRI) to construct a common space that adaptively aggregates the intrinsic semantics of different modalities of data and filters out redundant or irrelevant information. On the other hand, our SPE module further generates the hashing codes of different modalities by preserving the similarity of intrinsic semantics with the element-wise Kullback-Leibler (KL) divergence. A total correlation regularization term is also imposed to reduce the redundancy amongst different dimensions of hash codes. Sufficient experiments on three benchmark datasets demonstrate the superiority of the proposed ITH in ZS-CMR. Source code is available in the supplementary material.
A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language tasks. Specifically, we advance the big convergence from three aspects: backbone architecture, pretraining task, and model scaling up. We introduce Multiway Transformers for general-purpose modeling, where the modular architecture enables both deep fusion and modality-specific encoding. Based on the shared backbone, we perform masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner. Experimental results show that BEiT-3 obtains state-of-the-art performance on object detection (COCO), semantic segmentation (ADE20K), image classification (ImageNet), visual reasoning (NLVR2), visual question answering (VQAv2), image captioning (COCO), and cross-modal retrieval (Flickr30K, COCO).
Exploring large-scale pretrained foundation models is of significant interest in computer vision because these models can be quickly transferred to many downstream tasks. This paper presents Contrastive Captioner (CoCa), a minimalist design to pretrain an image-text encoder-decoder foundation model jointly with contrastive loss and captioning loss, thereby subsuming model capabilities from contrastive approaches like CLIP and generative methods like SimVLM. In contrast to standard encoder-decoder transformers where all decoder layers attend to encoder outputs, CoCa omits cross-attention in the first half of decoder layers to encode unimodal text representations, and cascades the remaining decoder layers which cross-attend to the image encoder for multimodal image-text representations. We apply a contrastive loss between unimodal image and text embeddings, in addition to a captioning loss on the multimodal decoder outputs which predicts text tokens autoregressively. By sharing the same computational graph, the two training objectives are computed efficiently with minimal overhead. CoCa is pretrained end-to-end and from scratch on both web-scale alt-text data and annotated images by treating all labels simply as text, seamlessly unifying natural language supervision for representation learning. Empirically, CoCa achieves state-of-the-art performance with zero-shot transfer or minimal task-specific adaptation on a broad range of downstream tasks, spanning visual recognition (ImageNet, Kinetics-400/600/700, Moments-in-Time), crossmodal retrieval (MSCOCO, Flickr30K, MSR-VTT), multimodal understanding (VQA, SNLI-VE, NLVR2), and image captioning (MSCOCO, NoCaps). Notably on ImageNet classification, CoCa obtains 86.3% zero-shot top-1 accuracy, 90.6% with a frozen encoder and learned classification head, and new state-of-the-art 91.0% top-1 accuracy on ImageNet with a finetuned encoder.
Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Flamingo, a family of Visual Language Models (VLM) with this ability. We propose key architectural innovations to: (i) bridge powerful pretrained vision-only and language-only models, (ii) handle sequences of arbitrarily interleaved visual and textual data, and (iii) seamlessly ingest images or videos as inputs. Thanks to their flexibility, Flamingo models can be trained on large-scale multimodal web corpora containing arbitrarily interleaved text and images, which is key to endow them with in-context few-shot learning capabilities. We perform a thorough evaluation of our models, exploring and measuring their ability to rapidly adapt to a variety of image and video tasks. These include open-ended tasks such as visual question-answering, where the model is prompted with a question which it has to answer; captioning tasks, which evaluate the ability to describe a scene or an event; and close-ended tasks such as multiple-choice visual question-answering. For tasks lying anywhere on this spectrum, a single Flamingo model can achieve a new state of the art with few-shot learning, simply by prompting the model with task-specific examples. On numerous benchmarks, Flamingo outperforms models fine-tuned on thousands of times more task-specific data.
Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information (MI) between an image and its matched text. However, simply performing cross-modal alignment (CMA) ignores data potential within each modality, which may result in degraded representations. For instance, although CMA-based models are able to map image-text pairs close together in the embedding space, they fail to ensure that similar inputs from the same modality stay close by. This problem can get even worse when the pre-training data is noisy. In this paper, we propose triple contrastive learning (TCL) for vision-language pre-training by leveraging both cross-modal and intra-modal self-supervision. Besides CMA, TCL introduces an intra-modal contrastive objective to provide complementary benefits in representation learning. To take advantage of localized and structural information from image and text input, TCL further maximizes the average MI between local regions of image/text and their global summary. To the best of our knowledge, ours is the first work that takes into account local structure information for multi-modality representation learning. Experimental evaluations show that our approach is competitive and achieves the new state of the art on various common down-stream vision-language tasks such as image-text retrieval and visual question answering.
Automated visual understanding of our diverse and open world demands computer vision models to generalize well with minimal customization for specific tasks, similar to human vision. Computer vision foundation models, which are trained on diverse, large-scale dataset and can be adapted to a wide range of downstream tasks, are critical for this mission to solve real-world computer vision applications. While existing vision foundation models such as CLIP, ALIGN, and Wu Dao 2.0 focus mainly on mapping images and textual representations to a cross-modal shared representation, we introduce a new computer vision foundation model, Florence, to expand the representations from coarse (scene) to fine (object), from static (images) to dynamic (videos), and from RGB to multiple modalities (caption, depth). By incorporating universal visual-language representations from Web-scale image-text data, our Florence model can be easily adapted for various computer vision tasks, such as classification, retrieval, object detection, VQA, image caption, video retrieval and action recognition. Moreover, Florence demonstrates outstanding performance in many types of transfer learning: fully sampled fine-tuning, linear probing, few-shot transfer and zero-shot transfer for novel images and objects. All of these properties are critical for our vision foundation model to serve general purpose vision tasks. Florence achieves new state-of-the-art results in majority of 44 representative benchmarks, e.g., ImageNet-1K zero-shot classification with top-1 accuracy of 83.74 and the top-5 accuracy of 97.18, 62.4 mAP on COCO fine tuning, 80.36 on VQA, and 87.8 on Kinetics-600.
Large-scale vision and language representation learning has shown promising improvements on various vision-language tasks. Most existing methods employ a transformer-based multimodal encoder to jointly model visual tokens (region-based image features) and word tokens. Because the visual tokens and word tokens are unaligned, it is challenging for the multimodal encoder to learn image-text interactions. In this paper, we introduce a contrastive loss to ALign the image and text representations BEfore Fusing (ALBEF) them through cross-modal attention, which enables more grounded vision and language representation learning. Unlike most existing methods, our method does not require bounding box annotations nor high-resolution images. In order to improve learning from noisy web data, we propose momentum distillation, a self-training method which learns from pseudo-targets produced by a momentum model. We provide a theoretical analysis of ALBEF from a mutual information maximization perspective, showing that different training tasks can be interpreted as different ways to generate views for an image-text pair. ALBEF achieves state-of-the-art performance on multiple downstream vision-language tasks. On image-text retrieval, ALBEF outperforms methods that are pre-trained on orders of magnitude larger datasets. On VQA and NLVR$^2$, ALBEF achieves absolute improvements of 2.37% and 3.84% compared to the state-of-the-art, while enjoying faster inference speed. Code and pre-trained models are available at https://github.com/salesforce/ALBEF/.
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.