Recent progress in deterministic prompt learning has become a promising alternative to various downstream vision tasks, enabling models to learn powerful visual representations with the help of pre-trained vision-language models. However, this approach results in limited performance for dense prediction tasks that require handling more complex and diverse objects, since a single and deterministic description cannot sufficiently represent the entire image. In this paper, we present a novel probabilistic prompt learning to fully exploit the vision-language knowledge in dense prediction tasks. First, we introduce learnable class-agnostic attribute prompts to describe universal attributes across the object class. The attributes are combined with class information and visual-context knowledge to define the class-specific textual distribution. Text representations are sampled and used to guide the dense prediction task using the probabilistic pixel-text matching loss, enhancing the stability and generalization capability of the proposed method. Extensive experiments on different dense prediction tasks and ablation studies demonstrate the effectiveness of our proposed method.
Automated generation of clinically accurate radiology reports can improve patient care. Previous report generation methods that rely on image captioning models often generate incoherent and incorrect text due to their lack of relevant domain knowledge, while retrieval-based attempts frequently retrieve reports that are irrelevant to the input image. In this work, we propose Contrastive X-Ray REport Match (X-REM), a novel retrieval-based radiology report generation module that uses an image-text matching score to measure the similarity of a chest X-ray image and radiology report for report retrieval. We observe that computing the image-text matching score with a language-image model can effectively capture the fine-grained interaction between image and text that is often lost when using cosine similarity. X-REM outperforms multiple prior radiology report generation modules in terms of both natural language and clinical metrics. Human evaluation of the generated reports suggests that X-REM increased the number of zero-error reports and decreased the average error severity compared to the baseline retrieval approach. Our code is available at: https://github.com/rajpurkarlab/X-REM
Exploiting fine-grained correspondence and visual-semantic alignments has shown great potential in image-text matching. Generally, recent approaches first employ a cross-modal attention unit to capture latent region-word interactions, and then integrate all the alignments to obtain the final similarity. However, most of them adopt one-time forward association or aggregation strategies with complex architectures or additional information, while ignoring the regulation ability of network feedback. In this paper, we develop two simple but quite effective regulators which efficiently encode the message output to automatically contextualize and aggregate cross-modal representations. Specifically, we propose (i) a Recurrent Correspondence Regulator (RCR) which facilitates the cross-modal attention unit progressively with adaptive attention factors to capture more flexible correspondence, and (ii) a Recurrent Aggregation Regulator (RAR) which adjusts the aggregation weights repeatedly to increasingly emphasize important alignments and dilute unimportant ones. Besides, it is interesting that RCR and RAR are plug-and-play: both of them can be incorporated into many frameworks based on cross-modal interaction to obtain significant benefits, and their cooperation achieves further improvements. Extensive experiments on MSCOCO and Flickr30K datasets validate that they can bring an impressive and consistent R@1 gain on multiple models, confirming the general effectiveness and generalization ability of the proposed methods. Code and pre-trained models are available at: https://github.com/Paranioar/RCAR.
This short technical report demonstrates a simple technique that yields state of the art results in medical image-text matching tasks. We analyze the use of OpenAI's CLIP, a general image-text matching model, and observe that CLIP's limited textual input size has negative impact on downstream performance in the medical domain where encoding longer textual contexts is often required. We thus train and release ClipMD, which is trained with a simple sliding window technique to encode textual captions. ClipMD was tested on two medical image-text datasets and compared with other image-text matching models. The results show that ClipMD outperforms other models on both datasets by a large margin. We make our code and pretrained model publicly available.
Text-to-image person retrieval aims to identify the target person based on a given textual description query. The primary challenge is to learn the mapping of visual and textual modalities into a common latent space. Prior works have attempted to address this challenge by leveraging separately pre-trained unimodal models to extract visual and textual features. However, these approaches lack the necessary underlying alignment capabilities required to match multimodal data effectively. Besides, these works use prior information to explore explicit part alignments, which may lead to the distortion of intra-modality information. To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision. Specifically, we first design an Implicit Relation Reasoning module in a masked language modeling paradigm. This achieves cross-modal interaction by integrating the visual cues into the textual tokens with a cross-modal multimodal interaction encoder. Secondly, to globally align the visual and textual embeddings, Similarity Distribution Matching is proposed to minimize the KL divergence between image-text similarity distributions and the normalized label matching distributions. The proposed method achieves new state-of-the-art results on all three public datasets, with a notable margin of about 3%-9% for Rank-1 accuracy compared to prior methods.
As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space. To achieve this, massive and correctly aligned data pairs are required for model training. However, unlike unimodal datasets, multimodal datasets are extremely harder to collect and annotate precisely. As an alternative, the co-occurred data pairs (e.g., image-text pairs) collected from the Internet have been widely exploited in the area. Unfortunately, the cheaply collected dataset unavoidably contains many mismatched data pairs, which have been proven to be harmful to the model's performance. To address this, we propose a general framework called BiCro (Bidirectional Cross-modal similarity consistency), which can be easily integrated into existing cross-modal matching models and improve their robustness against noisy data. Specifically, BiCro aims to estimate soft labels for noisy data pairs to reflect their true correspondence degree. The basic idea of BiCro is motivated by that -- taking image-text matching as an example -- similar images should have similar textual descriptions and vice versa. Then the consistency of these two similarities can be recast as the estimated soft labels to train the matching model. The experiments on three popular cross-modal matching datasets demonstrate that our method significantly improves the noise-robustness of various matching models, and surpass the state-of-the-art by a clear margin.
Fine-grained supervision based on object annotations has been widely used for vision and language pre-training (VLP). However, in real-world application scenarios, aligned multi-modal data is usually in the image-caption format, which only provides coarse-grained supervision. It is not only cost-expensive but also compute-expensive to collect object annotations and build object annotation pre-extractor for different scenarios. In this paper, we propose a fine-grained VLP scheme without object annotations from the linguistic perspective. First, we propose a homonym sentence rewriting (HSR) algorithm to provide token-level supervision. The algorithm replaces a verb/noun/adjective/quantifier word of the caption with its homonyms from WordNet. Correspondingly, we propose refined vision-language modeling (RVLM) framework to exploit the token-level supervision. Three refined tasks, i.e., refined image-text contrastive (RITC), refined image-text matching (RITM), and replace language modeling (RLM) are proposed to learn the fine-grained alignment. Extensive experiments on several downstream tasks demonstrate the superior performance of the proposed method.
Recently, a series of Image-Text Matching (ITM) methods achieve impressive performance. However, we observe that most existing ITM models suffer from gradients vanishing at the beginning of training, which makes these models prone to falling into local minima. Most ITM models adopt triplet loss with Hard Negative mining (HN) as the optimization objective. We find that optimizing an ITM model using only the hard negative samples can easily lead to gradient vanishing. In this paper, we derive the condition under which the gradient vanishes during training. When the difference between the positive pair similarity and the negative pair similarity is close to 0, the gradients on both the image and text encoders will approach 0. To alleviate the gradient vanishing problem, we propose a Selectively Hard Negative Mining (SelHN) strategy, which chooses whether to mine hard negative samples according to the gradient vanishing condition. SelHN can be plug-and-play applied to existing ITM models to give them better training behavior. To further ensure the back-propagation of gradients, we construct a Residual Visual Semantic Embedding model with SelHN, denoted as RVSE++. Extensive experiments on two ITM benchmarks demonstrate the strength of RVSE++, achieving state-of-the-art performance.
Semantic consistency recognition aims to detect and judge whether the semantics of two text sentences are consistent with each other. However, the existing methods usually encounter the challenges of synonyms, polysemy and difficulty to understand long text. To solve the above problems, this paper proposes a co-driven semantic consistency recognition method based on the fusion of Transformer and HowNet sememes knowledge. Multi-level encoding of internal sentence structures via data-driven is carried out firstly by Transformer, sememes knowledge base HowNet is introduced for knowledge-driven to model the semantic knowledge association among sentence pairs. Then, interactive attention calculation is carried out utilizing soft-attention and fusion the knowledge with sememes matrix. Finally, bidirectional long short-term memory network (BiLSTM) is exploited to encode the conceptual semantic information and infer the semantic consistency. Experiments are conducted on two financial text matching datasets (BQ, AFQMC) and a cross-lingual adversarial dataset (PAWSX) for paraphrase identification. Compared with lightweight models including DSSM, MwAN, DRCN, and pre-training models such as ERNIE etc., the proposed model can not only improve the accuracy of semantic consistency recognition effectively (by 2.19%, 5.57% and 6.51% compared with the DSSM, MWAN and DRCN models on the BQ dataset), but also reduce the number of model parameters (to about 16M). In addition, driven by the HowNet sememes knowledge, the proposed method is promising to adapt to scenarios with long text.
Same-style products retrieval plays an important role in e-commerce platforms, aiming to identify the same products which may have different text descriptions or images. It can be used for similar products retrieval from different suppliers or duplicate products detection of one supplier. Common methods use the image as the detected object, but they only consider the visual features and overlook the attribute information contained in the textual descriptions, and perform weakly for products in image less important industries like machinery, hardware tools and electronic component, even if an additional text matching module is added. In this paper, we propose a unified vision-language modeling method for e-commerce same-style products retrieval, which is designed to represent one product with its textual descriptions and visual contents. It contains one sampling skill to collect positive pairs from user click log with category and relevance constrained, and a novel contrastive loss unit to model the image, text, and image+text representations into one joint embedding space. It is capable of cross-modal product-to-product retrieval, as well as style transfer and user-interactive search. Offline evaluations on annotated data demonstrate its superior retrieval performance, and online testings show it can attract more clicks and conversions. Moreover, this model has already been deployed online for similar products retrieval in alibaba.com, the largest B2B e-commerce platform in the world.
Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years. Most of the existing methods either transfer the knowledge of image-text pretraining model to video-text retrieval task without fully exploring the multi-modal information of videos, or simply fuse multi-modal features in a brute force manner without explicit guidance. In this paper, we integrate multi-modal information in an explicit manner by tagging, and use the tags as the anchors for better video-text alignment. Various pretrained experts are utilized for extracting the information of multiple modalities, including object, person, motion, audio, etc. To take full advantage of these information, we propose the TABLE (TAgging Before aLignmEnt) network, which consists of a visual encoder, a tag encoder, a text encoder, and a tag-guiding cross-modal encoder for jointly encoding multi-frame visual features and multi-modal tags information. Furthermore, to strengthen the interaction between video and text, we build a joint cross-modal encoder with the triplet input of [vision, tag, text] and perform two additional supervised tasks, Video Text Matching (VTM) and Masked Language Modeling (MLM). Extensive experimental results demonstrate that the TABLE model is capable of achieving State-Of-The-Art (SOTA) performance on various video-text retrieval benchmarks, including MSR-VTT, MSVD, LSMDC and DiDeMo.
Zero-shot action recognition, which recognizes actions in videos without having received any training examples, is gaining wide attention considering it can save labor costs and training time. Nevertheless, the performance of zero-shot learning is still unsatisfactory, which limits its practical application. To solve this problem, this study proposes a framework to improve zero-shot action recognition using human instructions with text descriptions. The proposed framework manually describes video contents, which incurs some labor costs; in many situations, the labor costs are worth it. We manually annotate text features for each action, which can be a word, phrase, or sentence. Then by computing the matching degrees between the video and all text features, we can predict the class of the video. Furthermore, the proposed model can also be combined with other models to improve its accuracy. In addition, our model can be continuously optimized to improve the accuracy by repeating human instructions. The results with UCF101 and HMDB51 showed that our model achieved the best accuracy and improved the accuracies of other models.
Fake news often involves multimedia information such as text and image to mislead readers, proliferating and expanding its influence. Most existing fake news detection methods apply the co-attention mechanism to fuse multimodal features while ignoring the consistency of image and text in co-attention. In this paper, we propose multimodal matching-aware co-attention networks with mutual knowledge distillation for improving fake news detection. Specifically, we design an image-text matching-aware co-attention mechanism which captures the alignment of image and text for better multimodal fusion. The image-text matching representation can be obtained via a vision-language pre-trained model. Additionally, based on the designed image-text matching-aware co-attention mechanism, we propose to build two co-attention networks respectively centered on text and image for mutual knowledge distillation to improve fake news detection. Extensive experiments on three benchmark datasets demonstrate that our proposed model achieves state-of-the-art performance on multimodal fake news detection.
Masked Language Modeling (MLM) has proven to be an essential component of Vision-Language (VL) pretraining. To implement MLM, the researcher must make two design choices: the masking strategy, which determines which tokens to mask, and the masking rate, which determines how many tokens to mask. Previous work has focused primarily on the masking strategy while setting the masking rate at a default of 15\%. In this paper, we show that increasing this masking rate improves downstream performance while simultaneously reducing performance gap among different masking strategies, rendering the uniform masking strategy competitive to other more complex ones. Surprisingly, we also discover that increasing the masking rate leads to gains in Image-Text Matching (ITM) tasks, suggesting that the role of MLM goes beyond language modeling in VL pretraining.
This paper presents SimVTP: a Simple Video-Text Pretraining framework via masked autoencoders. We randomly mask out the spatial-temporal tubes of input video and the word tokens of input text and then feed them into a unified autencoder to reconstruct the missing pixels and words. Our SimVTP has several properties: 1) Thanks to the unified autoencoder, SimVTP reconstructs the masked signal of one modality with the help from another modality, which implicitly learns the cross-modal alignment between video tubes and text tokens. 2) SimVTP not only benefits from a high video masking ratio (e.g. 90%) due to the temporal redundancy of video, but also needs a high text masking ratio (e.g. 75%), which is much higher than BERT (e.g. 15%), to achieve optimal performance. This is because the aid of video modality makes text reconstruction less challenging, which thus needs a higher mask ratio to make the pretext harder for useful feature learning. 3) Equipping SimVTP with video-text contrastive learning (VTC) and video-text matching (VTM), which are two commonly used cross-modal training strategies, could further improve the transferable performance significantly. 4) SimVTP is dataefficent, e.g., pre-training only on 10% data of WebVid-2M, SimVTP achieves surprisingly good results (43.8 R@1) on MSRVTT, which is far above recent state-of-the-art methods pre-trained on both CC3M and WebVid-2M. We transfer our pre-trained model to various downstream tasks and achieve superior performance. The codes and models will be released at https://github.com/mayuelala/SimVTP.
Contrastive Language-Image Pretraining (CLIP) has demonstrated great zero-shot performance for matching images and text. However, it is still challenging to adapt vision-lanaguage pretrained models like CLIP to compositional image and text matching -- a more challenging image and text matching task requiring the model understanding of compositional word concepts and visual components. Towards better compositional generalization in zero-shot image and text matching, in this paper, we study the problem from a causal perspective: the erroneous semantics of individual entities are essentially confounders that cause the matching failure. Therefore, we propose a novel \textbf{\textit{training-free}} compositional CLIP model (ComCLIP). ComCLIP disentangles input images into subjects, objects, and action sub-images and composes CLIP's vision encoder and text encoder to perform evolving matching over compositional text embedding and sub-image embeddings. In this way, ComCLIP can mitigate spurious correlations introduced by the pretrained CLIP models and dynamically evaluate the importance of each component. Experiments on four compositional image-text matching datasets: SVO, ComVG, Winoground, and VL-checklist, and two general image-text retrieval datasets: Flick30K, and MSCOCO demonstrate the effectiveness of our plug-and-play method, which boosts the \textbf{\textit{zero-shot}} inference ability of CLIP, SLIP, and BLIP2 even without further training or fine-tuning. Our codes can be found at https://github.com/eric-ai-lab/ComCLIP.
Medical image visual question answering (VQA) is a task to answer clinical questions, given a radiographic image, which is a challenging problem that requires a model to integrate both vision and language information. To solve medical VQA problems with a limited number of training data, pretrain-finetune paradigm is widely used to improve the model generalization. In this paper, we propose a self-supervised method that applies Masked image modeling, Masked language modeling, Image text matching and Image text alignment via contrastive learning (M2I2) for pretraining on medical image caption dataset, and finetunes to downstream medical VQA tasks. The proposed method achieves state-of-the-art performance on all the three public medical VQA datasets. Our codes and models are available at https://github.com/pengfeiliHEU/M2I2.
End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. In this paper, we present DeepSolo, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection and recognition simultaneously. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations, thus can be further decoded to the center line, boundary, script, and confidence of text via very simple prediction heads in parallel. Besides, we also introduce a text-matching criterion to deliver more accurate supervisory signals, thus enabling more efficient training. Quantitative experiments on public benchmarks demonstrate that DeepSolo outperforms previous state-of-the-art methods and achieves better training efficiency. In addition, DeepSolo is also compatible with line annotations, which require much less annotation cost than polygons. The code is available at https://github.com/ViTAE-Transformer/DeepSolo.
Natural language processing methods have several applications in automated auditing, including document or passage classification, information retrieval, and question answering. However, training such models requires a large amount of annotated data which is scarce in industrial settings. At the same time, techniques like zero-shot and unsupervised learning allow for application of models pre-trained using general domain data to unseen domains. In this work, we study the efficiency of unsupervised text matching using Sentence-Bert, a transformer-based model, by applying it to the semantic similarity of financial passages. Experimental results show that this model is robust to documents from in- and out-of-domain data.
Diffusion generative models have recently greatly improved the power of text-conditioned image generation. Existing image generation models mainly include text conditional diffusion model and cross-modal guided diffusion model, which are good at small scene image generation and complex scene image generation respectively. In this work, we propose a simple yet effective approach, namely UPainting, to unify simple and complex scene image generation, as shown in Figure 1. Based on architecture improvements and diverse guidance schedules, UPainting effectively integrates cross-modal guidance from a pretrained image-text matching model into a text conditional diffusion model that utilizes a pretrained Transformer language model as the text encoder. Our key findings is that combining the power of large-scale Transformer language model in understanding language and image-text matching model in capturing cross-modal semantics and style, is effective to improve sample fidelity and image-text alignment of image generation. In this way, UPainting has a more general image generation capability, which can generate images of both simple and complex scenes more effectively. To comprehensively compare text-to-image models, we further create a more general benchmark, UniBench, with well-written Chinese and English prompts in both simple and complex scenes. We compare UPainting with recent models and find that UPainting greatly outperforms other models in terms of caption similarity and image fidelity in both simple and complex scenes. UPainting project page \url{https://upainting.github.io/}.