Scene text detection is a challenging computer vision task due to the high variation in text shapes and ratios. In this work, we propose a scene text detector named Deformable Kernel Expansion (DKE), which incorporates the merits of both segmentation and contour-based detectors. DKE employs a segmentation module to segment the shrunken text region as the text kernel, then expands the text kernel contour to obtain text boundary by regressing the vertex-wise offsets. Generating the text kernel by segmentation enables DKE to inherit the arbitrary-shaped text region modeling capability of segmentation-based detectors. Regressing the kernel contour with some sampled vertices enables DKE to avoid the complicated pixel-level post-processing and better learn contour deformation as the contour-based detectors. Moreover, we propose an Optimal Bipartite Graph Matching Loss (OBGML) that measures the matching error between the predicted contour and the ground truth, which efficiently minimizes the global contour matching distance. Extensive experiments on CTW1500, Total-Text, MSRA-TD500, and ICDAR2015 demonstrate that DKE achieves a good tradeoff between accuracy and efficiency in scene text detection.
With direct access to human-written reference as memory, retrieval-augmented generation has achieved much progress in a wide range of text generation tasks. Since better memory would typically prompt better generation~(we define this as primal problem), previous works mainly focus on how to retrieve better memory. However, one fundamental limitation exists for current literature: the memory is retrieved from a fixed corpus and is bounded by the quality of the corpus. Due to the finite retrieval space, bounded memory would greatly limit the potential of the memory-augmented generation model. In this paper, by exploring the duality of the primal problem: better generation also prompts better memory, we propose a framework called Selfmem, which iteratively adopts a retrieval-augmented generator itself to generate an unbounded memory pool and uses a memory selector to pick one generated memory for the next generation round. By combining the primal and dual problem, a retrieval-augmented generation model could lift itself up with its own output in the infinite generation space. To verify our framework, we conduct extensive experiments across various text generation scenarios including neural machine translation, abstractive summarization and dialogue generation over seven datasets and achieve state-of-the-art results in JRC-Acquis(four directions), XSum(50.3 ROUGE-1) and BigPatent(62.9 ROUGE-1).
We propose a text-to-image generation algorithm based on deep neural networks when text captions for images are unavailable during training. In this work, instead of simply generating pseudo-ground-truth sentences of training images using existing image captioning methods, we employ a pretrained CLIP model, which is capable of properly aligning embeddings of images and corresponding texts in a joint space and, consequently, works well on zero-shot recognition tasks. We optimize a text-to-image generation model by maximizing the data log-likelihood conditioned on pairs of image-text CLIP embeddings. To better align data in the two domains, we employ a principled way based on a variational inference, which efficiently estimates an approximate posterior of the hidden text embedding given an image and its CLIP feature. Experimental results validate that the proposed framework outperforms existing approaches by large margins under unsupervised and semi-supervised text-to-image generation settings.
Medicine, by its nature, is a multifaceted domain that requires the synthesis of information across various modalities. Medical generative vision-language models (VLMs) make a first step in this direction and promise many exciting clinical applications. However, existing models typically have to be fine-tuned on sizeable down-stream datasets, which poses a significant limitation as in many medical applications data is scarce, necessitating models that are capable of learning from few examples in real-time. Here we propose Med-Flamingo, a multimodal few-shot learner adapted to the medical domain. Based on OpenFlamingo-9B, we continue pre-training on paired and interleaved medical image-text data from publications and textbooks. Med-Flamingo unlocks few-shot generative medical visual question answering (VQA) abilities, which we evaluate on several datasets including a novel challenging open-ended VQA dataset of visual USMLE-style problems. Furthermore, we conduct the first human evaluation for generative medical VQA where physicians review the problems and blinded generations in an interactive app. Med-Flamingo improves performance in generative medical VQA by up to 20\% in clinician's rating and firstly enables multimodal medical few-shot adaptations, such as rationale generation. We release our model, code, and evaluation app under https://github.com/snap-stanford/med-flamingo.
In-context vision and language models like Flamingo support arbitrarily interleaved sequences of images and text as input. This format not only enables few-shot learning via interleaving independent supervised (image, text) examples, but also, more complex prompts involving interaction between images, e.g., "What do image A and image B have in common?" To support this interface, pretraining occurs over web corpora that similarly contain interleaved images+text. To date, however, large-scale data of this form have not been publicly available. We release Multimodal C4 (mmc4), an augmentation of the popular text-only c4 corpus with images interleaved. We use a linear assignment algorithm to place images into longer bodies of text using CLIP features, a process that we show outperforms alternatives. mmc4 spans everyday topics like cooking, travel, technology, etc. A manual inspection of a random sample of documents shows that a vast majority (90%) of images are topically relevant, and that linear assignment frequently selects individual sentences specifically well-aligned with each image (78%). After filtering NSFW images, ads, etc., the corpus contains 103M documents containing 585M images interleaved with 43B English tokens.
We compare phone labels and articulatory features as input for cross-lingual transfer learning in text-to-speech (TTS) for low-resource languages (LRLs). Experiments with FastSpeech 2 and the LRL West Frisian show that using articulatory features outperformed using phone labels in both intelligibility and naturalness. For LRLs without pronunciation dictionaries, we propose two novel approaches: a) using a massively multilingual model to convert grapheme-to-phone (G2P) in both training and synthesizing, and b) using a universal phone recognizer to create a makeshift dictionary. Results show that the G2P approach performs largely on par with using a ground-truth dictionary and the phone recognition approach, while performing generally worse, remains a viable option for LRLs less suitable for the G2P approach. Within each approach, using articulatory features as input outperforms using phone labels.
Reinforcement learning (RL) has been shown to learn sophisticated control policies for complex tasks including games, robotics, heating and cooling systems and text generation. The action-perception cycle in RL, however, generally assumes that a measurement of the state of the environment is available at each time step without a cost. In applications such as materials design, deep-sea and planetary robot exploration and medicine, however, there can be a high cost associated with measuring, or even approximating, the state of the environment. In this paper, we survey the recently growing literature that adopts the perspective that an RL agent might not need, or even want, a costly measurement at each time step. Within this context, we propose the Deep Dynamic Multi-Step Observationless Agent (DMSOA), contrast it with the literature and empirically evaluate it on OpenAI gym and Atari Pong environments. Our results, show that DMSOA learns a better policy with fewer decision steps and measurements than the considered alternative from the literature. The corresponding code is available at: \url{https://github.com/cbellinger27/Learning-when-to-observe-in-RL
Contrastive learning based vision-language joint pre-training has emerged as a successful representation learning strategy. In this paper, we present a prototype representation learning framework incorporating both global and local alignment between medical images and reports. In contrast to standard global multi-modality alignment methods, we employ a local alignment module for fine-grained representation. Furthermore, a cross-modality conditional reconstruction module is designed to interchange information across modalities in the training phase by reconstructing masked images and reports. For reconstructing long reports, a sentence-wise prototype memory bank is constructed, enabling the network to focus on low-level localized visual and high-level clinical linguistic features. Additionally, a non-auto-regressive generation paradigm is proposed for reconstructing non-sequential reports. Experimental results on five downstream tasks, including supervised classification, zero-shot classification, image-to-text retrieval, semantic segmentation, and object detection, show the proposed method outperforms other state-of-the-art methods across multiple datasets and under different dataset size settings. The code is available at https://github.com/QtacierP/PRIOR.
Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks. While the chain-of-thought (CoT) technique has gained considerable attention, the existing ScienceQA dataset, which focuses on multimodal scientific questions and explanations from elementary and high school textbooks, lacks a comprehensive evaluation of diverse approaches. To address this gap, we present COCO Multi-Modal Reasoning Dataset(COCO-MMRD), a novel dataset that encompasses an extensive collection of open-ended questions, rationales, and answers derived from the large object dataset COCO. Unlike previous datasets that rely on multiple-choice questions, our dataset pioneers the use of open-ended questions in the context of multimodal CoT, introducing a more challenging problem that effectively assesses the reasoning capability of CoT models. Through comprehensive evaluations and detailed analyses, we provide valuable insights and propose innovative techniques, including multi-hop cross-modal attention and sentence-level contrastive learning, to enhance the image and text encoders. Extensive experiments demonstrate the efficacy of the proposed dataset and techniques, offering novel perspectives for advancing multimodal reasoning.
Large language models such as ChatGPT-3.5 and GPT-4.0 are ubiquitous and dominate the current discourse. Their transformative capabilities have led to a paradigm shift in how we interact with and utilize (text-based) information. Each day, new possibilities to leverage the capabilities of these models emerge. This paper presents findings on the performance of different large language models in a university of applied sciences' undergraduate computer science degree program. Our primary objective is to assess the effectiveness of these models within the curriculum by employing them as educational aids. By prompting the models with lecture material, exercise tasks, and past exams, we aim to evaluate their proficiency across different computer science domains. We showcase the strong performance of current large language models while highlighting limitations and constraints within the context of such a degree program. We found that ChatGPT-3.5 averaged 79.9% of the total score in 10 tested modules, BingAI achieved 68.4%, and LLaMa, in the 65 billion parameter variant, 20%. Despite these convincing results, even GPT-4.0 would not pass the degree program - due to limitations in mathematical calculations.