Video-and-language understanding has a variety of applications in the industry, such as video question answering, text-video retrieval and multi-label classification. Existing video-and-language understanding methods generally adopt heavy multi-modal encoders and feature fusion modules, which consume large amounts of GPU memory. Especially, they have difficulty dealing with dense video frames or long text that are prevalent in industrial applications. In this paper, we propose MuLTI, a highly accurate and memory-efficient video-and-language understanding model that achieves efficient and effective feature fusion through feature sampling and attention modules. Therefore, MuLTI can handle longer sequences with limited GPU memory. Then, we introduce an attention-based adapter to the encoders, which finetunes the shallow features to improve the model's performance with low GPU memory consumption. Finally, to further improve the model's performance, we introduce a new pretraining task named Multiple Choice Modeling to bridge the task gap between pretraining and downstream tasks and enhance the model's ability to align the video and the text. Benefiting from the efficient feature fusion module, the attention-based adapter and the new pretraining task, MuLTI achieves state-of-the-art performance on multiple datasets. Implementation and pretrained models will be released.
With the development of deep generative models, recent years have seen great success of Chinese landscape painting generation. However, few works focus on controllable Chinese landscape painting generation due to the lack of data and limited modeling capabilities. In this work, we propose a controllable Chinese landscape painting generation method named CCLAP, which can generate painting with specific content and style based on Latent Diffusion Model. Specifically, it consists of two cascaded modules, i.e., content generator and style aggregator. The content generator module guarantees the content of generated paintings specific to the input text. While the style aggregator module is to generate paintings of a style corresponding to a reference image. Moreover, a new dataset of Chinese landscape paintings named CLAP is collected for comprehensive evaluation. Both the qualitative and quantitative results demonstrate that our method achieves state-of-the-art performance, especially in artfully-composed and artistic conception. Codes are available at https://github.com/Robin-WZQ/CCLAP.
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-world scenarios, GPT-4 exhibits human-level performance on various professional and academic benchmarks, including passing a simulated bar exam with a score around the top 10% of test takers. GPT-4 is a Transformer-based model pre-trained to predict the next token in a document. The post-training alignment process results in improved performance on measures of factuality and adherence to desired behavior. A core component of this project was developing infrastructure and optimization methods that behave predictably across a wide range of scales. This allowed us to accurately predict some aspects of GPT-4's performance based on models trained with no more than 1/1,000th the compute of GPT-4.
Vision-and-language multi-modal pretraining and fine-tuning have shown great success in visual question answering (VQA). Compared to general domain VQA, the performance of biomedical VQA suffers from limited data. In this paper, we propose a retrieval-augmented pretrain-and-finetune paradigm named RAMM for biomedical VQA to overcome the data limitation issue. Specifically, we collect a new biomedical dataset named PMCPM which offers patient-based image-text pairs containing diverse patient situations from PubMed. Then, we pretrain the biomedical multi-modal model to learn visual and textual representation for image-text pairs and align these representations with image-text contrastive objective (ITC). Finally, we propose a retrieval-augmented method to better use the limited data. We propose to retrieve similar image-text pairs based on ITC from pretraining datasets and introduce a novel retrieval-attention module to fuse the representation of the image and the question with the retrieved images and texts. Experiments demonstrate that our retrieval-augmented pretrain-and-finetune paradigm obtains state-of-the-art performance on Med-VQA2019, Med-VQA2021, VQARAD, and SLAKE datasets. Further analysis shows that the proposed RAMM and PMCPM can enhance biomedical VQA performance compared with previous resources and methods. We will open-source our dataset, codes, and pretrained model.
Multilingual text-video retrieval methods have improved significantly in recent years, but the performance for other languages lags behind English. We propose a Cross-Lingual Cross-Modal Knowledge Distillation method to improve multilingual text-video retrieval. Inspired by the fact that English text-video retrieval outperforms other languages, we train a student model using input text in different languages to match the cross-modal predictions from teacher models using input text in English. We propose a cross entropy based objective which forces the distribution over the student's text-video similarity scores to be similar to those of the teacher models. We introduce a new multilingual video dataset, Multi-YouCook2, by translating the English captions in the YouCook2 video dataset to 8 other languages. Our method improves multilingual text-video retrieval performance on Multi-YouCook2 and several other datasets such as Multi-MSRVTT and VATEX. We also conducted an analysis on the effectiveness of different multilingual text models as teachers.
There has been great progress in unifying various table-to-text tasks using a single encoder-decoder model trained via multi-task learning (Xie et al., 2022). However, existing methods typically encode task information with a simple dataset name as a prefix to the encoder. This not only limits the effectiveness of multi-task learning, but also hinders the model's ability to generalize to new domains or tasks that were not seen during training, which is crucial for real-world applications. In this paper, we propose compositional task configurations, a set of prompts prepended to the encoder to improve cross-task generalization of unified models. We design the task configurations to explicitly specify the task type, as well as its input and output types. We show that this not only allows the model to better learn shared knowledge across different tasks at training, but also allows us to control the model by composing new configurations that apply novel input-output combinations in a zero-shot manner. We demonstrate via experiments over ten table-to-text tasks that our method outperforms the UnifiedSKG baseline by noticeable margins in both in-domain and zero-shot settings, with average improvements of +0.5 and +12.6 from using a T5-large backbone, respectively.
Sequential recommendation systems utilize the sequential interactions of users with items as their main supervision signals in learning users' preferences. However, existing methods usually generate unsatisfactory results due to the sparsity of user behavior data. To address this issue, we propose a novel pre-training framework, named Multimodal Sequence Mixup for Sequential Recommendation (MSM4SR), which leverages both users' sequential behaviors and items' multimodal content (\ie text and images) for effectively recommendation. Specifically, MSM4SR tokenizes each item image into multiple textual keywords and uses the pre-trained BERT model to obtain initial textual and visual features of items, for eliminating the discrepancy between the text and image modalities. A novel backbone network, \ie Multimodal Mixup Sequence Encoder (M$^2$SE), is proposed to bridge the gap between the item multimodal content and the user behavior, using a complementary sequence mixup strategy. In addition, two contrastive learning tasks are developed to assist M$^2$SE in learning generalized multimodal representations of the user behavior sequence. Extensive experiments on real-world datasets demonstrate that MSM4SR outperforms state-of-the-art recommendation methods. Moreover, we further verify the effectiveness of MSM4SR on other challenging tasks including cold-start and cross-domain recommendation.
Table pretrain-then-finetune paradigm has been proposed and employed at a rapid pace after the success of pre-training in the natural language domain. Despite the promising findings in tabular pre-trained language models (TPLMs), there is an input gap between pre-training and fine-tuning phases. For instance, TPLMs jointly pre-trained with table and text input could be effective for tasks also with table-text joint input like table question answering, but it may fail for tasks with only tables or text as input such as table retrieval. To this end, we propose UTP, an approach that dynamically supports three types of multi-modal inputs: table-text, table, and text. Specifically, UTP is pre-trained with two strategies: (1) We first utilize a universal mask language modeling objective on each kind of input, enforcing the model to adapt various inputs. (2) We then present Cross-Modal Contrastive Regularization (CMCR), which utilizes contrastive learning to encourage the consistency between table-text cross-modality representations via unsupervised instance-wise training signals during pre-training. By these means, the resulting model not only bridges the input gap between pre-training and fine-tuning but also advances in the alignment of table and text. Extensive results show UTP achieves superior results on uni-modal input tasks (e.g., table retrieval) and cross-modal input tasks (e.g., table question answering).
We present SegGPT, a generalist model for segmenting everything in context. We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images. The training of SegGPT is formulated as an in-context coloring problem with random color mapping for each data sample. The objective is to accomplish diverse tasks according to the context, rather than relying on specific colors. After training, SegGPT can perform arbitrary segmentation tasks in images or videos via in-context inference, such as object instance, stuff, part, contour, and text. SegGPT is evaluated on a broad range of tasks, including few-shot semantic segmentation, video object segmentation, semantic segmentation, and panoptic segmentation. Our results show strong capabilities in segmenting in-domain and out-of-domain targets, either qualitatively or quantitatively.
Few-shot class-incremental learning (FSCIL) has recently attracted extensive attention in various areas. Existing FSCIL methods highly depend on the robustness of the feature backbone pre-trained on base classes. In recent years, different Transformer variants have obtained significant processes in the feature representation learning of massive fields. Nevertheless, the progress of the Transformer in FSCIL scenarios has not achieved the potential promised in other fields so far. In this paper, we develop a semantic-visual guided Transformer (SV-T) to enhance the feature extracting capacity of the pre-trained feature backbone on incremental classes. Specifically, we first utilize the visual (image) labels provided by the base classes to supervise the optimization of the Transformer. And then, a text encoder is introduced to automatically generate the corresponding semantic (text) labels for each image from the base classes. Finally, the constructed semantic labels are further applied to the Transformer for guiding its hyperparameters updating. Our SV-T can take full advantage of more supervision information from base classes and further enhance the training robustness of the feature backbone. More importantly, our SV-T is an independent method, which can directly apply to the existing FSCIL architectures for acquiring embeddings of various incremental classes. Extensive experiments on three benchmarks, two FSCIL architectures, and two Transformer variants show that our proposed SV-T obtains a significant improvement in comparison to the existing state-of-the-art FSCIL methods.