This paper presents an end-to-end high-quality singing voice synthesis (SVS) system that uses bidirectional encoder representation from Transformers (BERT) derived semantic embeddings to improve the expressiveness of the synthesized singing voice. Based on the main architecture of recently proposed VISinger, we put forward several specific designs for expressive singing voice synthesis. First, different from the previous SVS models, we use text representation of lyrics extracted from pre-trained BERT as additional input to the model. The representation contains information about semantics of the lyrics, which could help SVS system produce more expressive and natural voice. Second, we further introduce an energy predictor to stabilize the synthesized voice and model the wider range of energy variations that also contribute to the expressiveness of singing voice. Last but not the least, to attenuate the off-key issues, the pitch predictor is re-designed to predict the real to note pitch ratio. Both objective and subjective experimental results indicate that the proposed SVS system can produce singing voice with higher-quality outperforming VISinger.
We present DiffBIR, which leverages pretrained text-to-image diffusion models for blind image restoration problem. Our framework adopts a two-stage pipeline. In the first stage, we pretrain a restoration module across diversified degradations to improve generalization capability in real-world scenarios. The second stage leverages the generative ability of latent diffusion models, to achieve realistic image restoration. Specifically, we introduce an injective modulation sub-network -- LAControlNet for finetuning, while the pre-trained Stable Diffusion is to maintain its generative ability. Finally, we introduce a controllable module that allows users to balance quality and fidelity by introducing the latent image guidance in the denoising process during inference. Extensive experiments have demonstrated its superiority over state-of-the-art approaches for both blind image super-resolution and blind face restoration tasks on synthetic and real-world datasets. The code is available at https://github.com/XPixelGroup/DiffBIR.
Cross-modal garment synthesis and manipulation will significantly benefit the way fashion designers generate garments and modify their designs via flexible linguistic interfaces.Current approaches follow the general text-to-image paradigm and mine cross-modal relations via simple cross-attention modules, neglecting the structural correspondence between visual and textual representations in the fashion design domain. In this work, we instead introduce DiffCloth, a diffusion-based pipeline for cross-modal garment synthesis and manipulation, which empowers diffusion models with flexible compositionality in the fashion domain by structurally aligning the cross-modal semantics. Specifically, we formulate the part-level cross-modal alignment as a bipartite matching problem between the linguistic Attribute-Phrases (AP) and the visual garment parts which are obtained via constituency parsing and semantic segmentation, respectively. To mitigate the issue of attribute confusion, we further propose a semantic-bundled cross-attention to preserve the spatial structure similarities between the attention maps of attribute adjectives and part nouns in each AP. Moreover, DiffCloth allows for manipulation of the generated results by simply replacing APs in the text prompts. The manipulation-irrelevant regions are recognized by blended masks obtained from the bundled attention maps of the APs and kept unchanged. Extensive experiments on the CM-Fashion benchmark demonstrate that DiffCloth both yields state-of-the-art garment synthesis results by leveraging the inherent structural information and supports flexible manipulation with region consistency.
In many parameter estimation problems, the exact model is unknown and is assumed to belong to a set of candidate models. In such cases, a predetermined data-based selection rule selects a parametric model from a set of candidates before the parameter estimation. The existing framework for estimation under model misspecification does not account for the selection process that led to the misspecified model. Moreover, in post-model-selection estimation, there are multiple candidate models chosen based on the observations, making the interpretation of the assumed model in the misspecified setting non-trivial. In this work, we present three interpretations to address the problem of non-Bayesian post-model-selection estimation as an estimation under model misspecification problem: the naive interpretation, the normalized interpretation, and the selective inference interpretation, and discuss their properties. For each of these interpretations, we developed the corresponding misspecified maximum likelihood estimator and the misspecified Cram$\acute{\text{e}}$r-Rao-type lower bound. The relations between the estimators and the performance bounds, as well as their properties, are discussed. Finally, we demonstrate the performance of the proposed estimators and bounds via simulations of estimation after channel selection. We show that the proposed performance bounds are more informative than the oracle Cram$\acute{\text{e}}$r-Rao Bound (CRB), where the third interpretation (selective inference) results in the lowest mean-squared-error (MSE) among the estimators.
The five-dollar model is a lightweight text-to-image generative architecture that generates low dimensional images from an encoded text prompt. This model can successfully generate accurate and aesthetically pleasing content in low dimensional domains, with limited amounts of training data. Despite the small size of both the model and datasets, the generated images are still able to maintain the encoded semantic meaning of the textual prompt. We apply this model to three small datasets: pixel art video game maps, video game sprite images, and down-scaled emoji images and apply novel augmentation strategies to improve the performance of our model on these limited datasets. We evaluate our models performance using cosine similarity score between text-image pairs generated by the CLIP VIT-B/32 model.
Current 3D open-vocabulary scene understanding methods mostly utilize well-aligned 2D images as the bridge to learn 3D features with language. However, applying these approaches becomes challenging in scenarios where 2D images are absent. In this work, we introduce a completely new pipeline, namely, OpenIns3D, which requires no 2D image inputs, for 3D open-vocabulary scene understanding at the instance level. The OpenIns3D framework employs a "Mask-Snap-Lookup" scheme. The "Mask" module learns class-agnostic mask proposals in 3D point clouds. The "Snap" module generates synthetic scene-level images at multiple scales and leverages 2D vision language models to extract interesting objects. The "Lookup" module searches through the outcomes of "Snap" with the help of Mask2Pixel maps, which contain the precise correspondence between 3D masks and synthetic images, to assign category names to the proposed masks. This 2D input-free, easy-to-train, and flexible approach achieved state-of-the-art results on a wide range of indoor and outdoor datasets with a large margin. Furthermore, OpenIns3D allows for effortless switching of 2D detectors without re-training. When integrated with state-of-the-art 2D open-world models such as ODISE and GroundingDINO, superb results are observed on open-vocabulary instance segmentation. When integrated with LLM-powered 2D models like LISA, it demonstrates a remarkable capacity to process highly complex text queries, including those that require intricate reasoning and world knowledge. Project page: https://zheninghuang.github.io/OpenIns3D/
Post-hoc explanation methods have often been criticised for abstracting away the decision-making process of deep neural networks. In this work, we would like to provide natural language descriptions for what different layers of a vision backbone have learned. Our DeViL method decodes vision features into language, not only highlighting the attribution locations but also generating textual descriptions of visual features at different layers of the network. We train a transformer network to translate individual image features of any vision layer into a prompt that a separate off-the-shelf language model decodes into natural language. By employing dropout both per-layer and per-spatial-location, our model can generalize training on image-text pairs to generate localized explanations. As it uses a pre-trained language model, our approach is fast to train, can be applied to any vision backbone, and produces textual descriptions at different layers of the vision network. Moreover, DeViL can create open-vocabulary attribution maps corresponding to words or phrases even outside the training scope of the vision model. We demonstrate that DeViL generates textual descriptions relevant to the image content on CC3M surpassing previous lightweight captioning models and attribution maps uncovering the learned concepts of the vision backbone. Finally, we show DeViL also outperforms the current state-of-the-art on the neuron-wise descriptions of the MILANNOTATIONS dataset. Code available at https://github.com/ExplainableML/DeViL
Many of the most commonly explored natural language processing (NLP) information extraction tasks can be thought of as evaluations of declarative knowledge, or fact-based information extraction. Procedural knowledge extraction, i.e., breaking down a described process into a series of steps, has received much less attention, perhaps in part due to the lack of structured datasets that capture the knowledge extraction process from end-to-end. To address this unmet need, we present FlaMB\'e (Flow annotations for Multiverse Biological entities), a collection of expert-curated datasets across a series of complementary tasks that capture procedural knowledge in biomedical texts. This dataset is inspired by the observation that one ubiquitous source of procedural knowledge that is described as unstructured text is within academic papers describing their methodology. The workflows annotated in FlaMB\'e are from texts in the burgeoning field of single cell research, a research area that has become notorious for the number of software tools and complexity of workflows used. Additionally, FlaMB\'e provides, to our knowledge, the largest manually curated named entity recognition (NER) and disambiguation (NED) datasets for tissue/cell type, a fundamental biological entity that is critical for knowledge extraction in the biomedical research domain. Beyond providing a valuable dataset to enable further development of NLP models for procedural knowledge extraction, automating the process of workflow mining also has important implications for advancing reproducibility in biomedical research.
As research on machine translation moves to translating text beyond the sentence level, it remains unclear how effective automatic evaluation metrics are at scoring longer translations. In this work, we first propose a method for creating paragraph-level data for training and meta-evaluating metrics from existing sentence-level data. Then, we use these new datasets to benchmark existing sentence-level metrics as well as train learned metrics at the paragraph level. Interestingly, our experimental results demonstrate that using sentence-level metrics to score entire paragraphs is equally as effective as using a metric designed to work at the paragraph level. We speculate this result can be attributed to properties of the task of reference-based evaluation as well as limitations of our datasets with respect to capturing all types of phenomena that occur in paragraph-level translations.
Natural Language Explanations (NLE) aim at supplementing the prediction of a model with human-friendly natural text. Existing NLE approaches involve training separate models for each downstream task. In this work, we propose Uni-NLX, a unified framework that consolidates all NLE tasks into a single and compact multi-task model using a unified training objective of text generation. Additionally, we introduce two new NLE datasets: 1) ImageNetX, a dataset of 144K samples for explaining ImageNet categories, and 2) VQA-ParaX, a dataset of 123K samples for explaining the task of Visual Question Answering (VQA). Both datasets are derived leveraging large language models (LLMs). By training on the 1M combined NLE samples, our single unified framework is capable of simultaneously performing seven NLE tasks including VQA, visual recognition and visual reasoning tasks with 7X fewer parameters, demonstrating comparable performance to the independent task-specific models in previous approaches, and in certain tasks even outperforming them. Code is at https://github.com/fawazsammani/uni-nlx