Houdong Hu

Chunyuan Li, Haotian Liu, Liunian Harold Li et al.

Learning visual representations from natural language supervision has recently shown great promise in a number of pioneering works. In general, these language-augmented visual models demonstrate strong transferability to a variety of datasets and tasks. However, it remains challenging to evaluate the transferablity of these models due to the lack of easy-to-use evaluation toolkits and public benchmarks. To tackle this, we build ELEVATER (Evaluation of Language-augmented Visual Task-level Transfer), the first benchmark and toolkit for evaluating(pre-trained) language-augmented visual models. ELEVATER is composed of three components. (i) Datasets. As downstream evaluation suites, it consists of 20 image classification datasets and 35 object detection datasets, each of which is augmented with external knowledge. (ii) Toolkit. An automatic hyper-parameter tuning toolkit is developed to facilitate model evaluation on downstream tasks. (iii) Metrics. A variety of evaluation metrics are used to measure sample-efficiency (zero-shot and few-shot) and parameter-efficiency (linear probing and full model fine-tuning). ELEVATER is a platform for Computer Vision in the Wild (CVinW), and is publicly released at at https://computer-vision-in-the-wild.github.io/ELEVATER/

Bin Xiao, Haiping Wu, Weijian Xu et al.

We introduce Florence-2, a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks. While existing large vision models excel in transfer learning, they struggle to perform a diversity of tasks with simple instructions, a capability that implies handling the complexity of various spatial hierarchy and semantic granularity. Florence-2 was designed to take text-prompt as task instructions and generate desirable results in text forms, whether it be captioning, object detection, grounding or segmentation. This multi-task learning setup demands large-scale, high-quality annotated data. To this end, we co-developed FLD-5B that consists of 5.4 billion comprehensive visual annotations on 126 million images, using an iterative strategy of automated image annotation and model refinement. We adopted a sequence-to-sequence structure to train Florence-2 to perform versatile and comprehensive vision tasks. Extensive evaluations on numerous tasks demonstrated Florence-2 to be a strong vision foundation model contender with unprecedented zero-shot and fine-tuning capabilities.

Juan Manuel Zambrano Chaves, Shih-Cheng Huang, Yanbo Xu et al. · microsoft-research

The scaling laws and extraordinary performance of large foundation models motivate the development and utilization of such models in biomedicine. However, despite early promising results on some biomedical benchmarks, there are still major challenges that need to be addressed before these models can be used in real-world clinics. Frontier general-domain models such as GPT-4V still have significant performance gaps in multimodal biomedical applications. More importantly, less-acknowledged pragmatic issues, including accessibility, model cost, and tedious manual evaluation make it hard for clinicians to use state-of-the-art large models directly on private patient data. Here, we explore training open-source small multimodal models (SMMs) to bridge competency gaps for unmet clinical needs in radiology. To maximize data efficiency, we adopt a modular approach by incorporating state-of-the-art pre-trained models for image and text modalities, and focusing on training a lightweight adapter to ground each modality to the text embedding space, as exemplified by LLaVA-Med. For training, we assemble a large dataset of over 697 thousand radiology image-text pairs. For evaluation, we propose CheXprompt, a GPT-4-based metric for factuality evaluation, and demonstrate its parity with expert evaluation. For best practice, we conduct a systematic ablation study on various choices in data engineering and multimodal training. The resulting LlaVA-Rad (7B) model attains state-of-the-art results on standard radiology tasks such as report generation and cross-modal retrieval, even outperforming much larger models such as GPT-4V and Med-PaLM M (84B). The inference of LlaVA-Rad is fast and can be performed on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.

Xiaotian Han, Jianwei Yang, Houdong Hu et al.

There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection. Due to the lack of a good benchmark, the reported results of different scene graph generation models are not directly comparable, impeding the research progress. We have developed a much-needed scene graph generation benchmark based on the maskrcnn-benchmark and several popular models. This paper presents main features of our benchmark and a comprehensive ablation study of scene graph generation models using the Visual Genome and OpenImages Visual relationship detection datasets. Our codebase is made publicly available at https://github.com/microsoft/scene_graph_benchmark.

Luowei Zhou, Hamid Palangi, Lei Zhang et al.

This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and (2) it uses a shared multi-layer transformer network for both encoding and decoding, which differs from many existing methods where the encoder and decoder are implemented using separate models. The unified VLP model is pre-trained on a large amount of image-text pairs using the unsupervised learning objectives of two tasks: bidirectional and sequence-to-sequence (seq2seq) masked vision-language prediction. The two tasks differ solely in what context the prediction conditions on. This is controlled by utilizing specific self-attention masks for the shared transformer network. To the best of our knowledge, VLP is the first reported model that achieves state-of-the-art results on both vision-language generation and understanding tasks, as disparate as image captioning and visual question answering, across three challenging benchmark datasets: COCO Captions, Flickr30k Captions, and VQA 2.0. The code and the pre-trained models are available at https://github.com/LuoweiZhou/VLP.

Kuang-Huei Lee, Xi Chen, Gang Hua et al.

In this paper, we study the problem of image-text matching. Inferring the latent semantic alignment between objects or other salient stuff (e.g. snow, sky, lawn) and the corresponding words in sentences allows to capture fine-grained interplay between vision and language, and makes image-text matching more interpretable. Prior work either simply aggregates the similarity of all possible pairs of regions and words without attending differentially to more and less important words or regions, or uses a multi-step attentional process to capture limited number of semantic alignments which is less interpretable. In this paper, we present Stacked Cross Attention to discover the full latent alignments using both image regions and words in a sentence as context and infer image-text similarity. Our approach achieves the state-of-the-art results on the MS-COCO and Flickr30K datasets. On Flickr30K, our approach outperforms the current best methods by 22.1% relatively in text retrieval from image query, and 18.2% relatively in image retrieval with text query (based on Recall@1). On MS-COCO, our approach improves sentence retrieval by 17.8% relatively and image retrieval by 16.6% relatively (based on Recall@1 using the 5K test set). Code has been made available at: https://github.com/kuanghuei/SCAN.

Xiaotian Han, Quanzeng You, Chunyu Wang et al.

Multi-camera tracking systems are gaining popularity in applications that demand high-quality tracking results, such as frictionless checkout because monocular multi-object tracking (MOT) systems often fail in cluttered and crowded environments due to occlusion. Multiple highly overlapped cameras can significantly alleviate the problem by recovering partial 3D information. However, the cost of creating a high-quality multi-camera tracking dataset with diverse camera settings and backgrounds has limited the dataset scale in this domain. In this paper, we provide a large-scale densely-labeled multi-camera tracking dataset in five different environments with the help of an auto-annotation system. The system uses overlapped and calibrated depth and RGB cameras to build a high-performance 3D tracker that automatically generates the 3D tracking results. The 3D tracking results are projected to each RGB camera view using camera parameters to create 2D tracking results. Then, we manually check and correct the 3D tracking results to ensure the label quality, which is much cheaper than fully manual annotation. We have conducted extensive experiments using two real-time multi-camera trackers and a person re-identification (ReID) model with different settings. This dataset provides a more reliable benchmark of multi-camera, multi-object tracking systems in cluttered and crowded environments. Also, our results demonstrate that adapting the trackers and ReID models on this dataset significantly improves their performance. Our dataset will be publicly released upon the acceptance of this work.

Lu Yuan, Dongdong Chen, Yi-Ling Chen et al.

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.

Xiujun Li, Xi Yin, Chunyuan Li et al.

Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the model to be pre-trained and use self-attention to learn image-text semantic alignments in a brute force manner, in this paper, we propose a new learning method Oscar (Object-Semantics Aligned Pre-training), which uses object tags detected in images as anchor points to significantly ease the learning of alignments. Our method is motivated by the observation that the salient objects in an image can be accurately detected, and are often mentioned in the paired text. We pre-train an Oscar model on the public corpus of 6.5 million text-image pairs, and fine-tune it on downstream tasks, creating new state-of-the-arts on six well-established vision-language understanding and generation tasks.

Kyle Xiao, Houdong Hu, Yan Wang

Query reformulation is the process by which a input search query is refined by the user to match documents outside the original top-n results. On average, roughly 50% of text search queries involve some form of reformulation, and term suggestion tools are used 35% of the time when offered to users. As prevalent as text search queries are, however, such a feature has yet to be explored at scale for visual search. This is because reformulation for images presents a novel challenge to seamlessly transform visual features to match user intent within the context of a typical user session. In this paper, we present methods of semantically transforming visual queries, such as utilizing operations in the latent space of a generative adversarial model for the scenarios of fashion and product search.

Kuang-Huei Lee, Hamid Palangi, Xi Chen et al.

Grounding language to visual relations is critical to various language-and-vision applications. In this work, we tackle two fundamental language-and-vision tasks: image-text matching and image captioning, and demonstrate that neural scene graph generators can learn effective visual relation features to facilitate grounding language to visual relations and subsequently improve the two end applications. By combining relation features with the state-of-the-art models, our experiments show significant improvement on the standard Flickr30K and MSCOCO benchmarks. Our experimental results and analysis show that relation features improve downstream models' capability of capturing visual relations in end vision-and-language applications. We also demonstrate the importance of learning scene graph generators with visually relevant relations to the effectiveness of relation features.

Ning Ma, Alexey Volkov, Aleksandr Livshits et al.

We propose a new framework to rank image attractiveness using a novel pairwise deep network trained with a large set of side-by-side multi-labeled image pairs from a web image index. The judges only provide relative ranking between two images without the need to directly assign an absolute score, or rate any predefined image attribute, thus making the rating more intuitive and accurate. We investigate a deep attractiveness rank net (DARN), a combination of deep convolutional neural network and rank net, to directly learn an attractiveness score mean and variance for each image and the underlying criteria the judges use to label each pair. The extension of this model (DARN-V2) is able to adapt to individual judge's personal preference. We also show the attractiveness of search results are significantly improved by using this attractiveness information in a real commercial search engine. We evaluate our model against other state-of-the-art models on our side-by-side web test data and another public aesthetic data set. With much less judgments (1M vs 50M), our model outperforms on side-by-side labeled data, and is comparable on data labeled by absolute score.

Houdong Hu, Yan Wang, Linjun Yang et al.

In this paper, we introduce a web-scale general visual search system deployed in Microsoft Bing. The system accommodates tens of billions of images in the index, with thousands of features for each image, and can respond in less than 200 ms. In order to overcome the challenges in relevance, latency, and scalability in such large scale of data, we employ a cascaded learning-to-rank framework based on various latest deep learning visual features, and deploy in a distributed heterogeneous computing platform. Quantitative and qualitative experiments show that our system is able to support various applications on Bing website and apps.