Taming Data and Transformers for Audio Generation

Generating ambient sounds and effects is a challenging problem due to data scarcity and often insufficient caption quality, making it difficult to employ large-scale generative models for the task. In this work, we tackle the problem by introducing two new models. First, we propose AutoCap, a high-quality and efficient automatic audio captioning model. We show that by leveraging metadata available with the audio modality, we can substantially improve the quality of captions. AutoCap reaches CIDEr score of 83.2, marking a 3.2% improvement from the best available captioning model at four times faster inference speed. We then use AutoCap to caption clips from existing datasets, obtaining 761,000 audio clips with high-quality captions, forming the largest available audio-text dataset. Second, we propose GenAu, a scalable transformer-based audio generation architecture that we scale up to 1.25B parameters and train with our new dataset. When compared to state-of-the-art audio generators, GenAu obtains significant improvements of 15.7% in FAD score, 22.7% in IS, and 13.5% in CLAP score, indicating significantly improved quality of generated audio compared to previous works. This shows that the quality of data is often as important as its quantity. Besides, since AutoCap is fully automatic, new audio samples can be added to the training dataset, unlocking the training of even larger generative models for audio synthesis.

Generative Visual Instruction Tuning

We propose to use machine-generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by curating a new multimodal instruction-following set using GPT-4V and existing datasets for image generation and editing. Using this instruction set and the existing LLaVA-Finetune instruction set for visual understanding tasks, we produce GenLLaVA, a Generative Large Language, and Visual Assistant. GenLLaVA is built through a strategy that combines three types of large pre-trained models through instruction finetuning: LLaMA for language modeling, SigLIP for image-text matching, and StableDiffusion for text-to-image generation. Our model demonstrates visual understanding capabilities on par with LLaVA and additionally demonstrates competitive results with native multimodal models such as Unified-IO 2, paving the way for building advanced general-purpose visual assistants by effectively re-using existing multimodal models. We open-source our dataset, codebase, and model checkpoints to foster further research and application in this domain.

FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image Generation

Controllable text-to-image (T2I) diffusion models generate images conditioned on both text prompts and semantic inputs of other modalities like edge maps. Nevertheless, current controllable T2I methods commonly face challenges related to efficiency and faithfulness, especially when conditioning on multiple inputs from either the same or diverse modalities. In this paper, we propose a novel Flexible and Efficient method, FlexEControl, for controllable T2I generation. At the core of FlexEControl is a unique weight decomposition strategy, which allows for streamlined integration of various input types. This approach not only enhances the faithfulness of the generated image to the control, but also significantly reduces the computational overhead typically associated with multimodal conditioning. Our approach achieves a reduction of 41% in trainable parameters and 30% in memory usage compared with Uni-ControlNet. Moreover, it doubles data efficiency and can flexibly generate images under the guidance of multiple input conditions of various modalities.

PropTest: Automatic Property Testing for Improved Visual Programming

Visual Programming has emerged as an alternative to end-to-end black-box visual reasoning models. This type of methods leverage Large Language Models (LLMs) to decompose a problem and generate the source code for an executable computer program. This strategy has the advantage of offering an interpretable reasoning path and does not require finetuning a model with task-specific data. We propose PropTest, a general strategy that improves visual programming by further using an LLM to generate code that tests for visual properties in an initial round of proposed solutions. Particularly, our method tests for data-type consistency, as well as syntactic and semantic properties in the generated solutions. Our proposed solution outperforms baselines and achieves comparable results to state-of-the-art methods while using smaller and publicly available LLMs (CodeLlama-7B and WizardCoder-15B). This is demonstrated across different benchmarks on visual question answering and referring expression comprehension, showing the efficacy of our approach in enhancing the performance and generalization of visual reasoning tasks. Specifically, PropTest improves ViperGPT by obtaining 48.66% accuracy (+8.3%) on the A-OKVQA benchmark and 52.8% (+3.3%) on the RefCOCO+ benchmark using CodeLlama-7B.

Learning from Models and Data for Visual Grounding

We introduce SynGround, a novel framework that combines data-driven learning and knowledge transfer from various large-scale pretrained models to enhance the visual grounding capabilities of a pretrained vision-and-language model. The knowledge transfer from the models initiates the generation of image descriptions through an image description generator. These descriptions serve dual purposes: they act as prompts for synthesizing images through a text-to-image generator, and as queries for synthesizing text, from which phrases are extracted using a large language model. Finally, we leverage an open-vocabulary object detector to generate synthetic bounding boxes for the synthetic images and texts. We finetune a pretrained vision-and-language model on this dataset by optimizing a mask-attention consistency objective that aligns region annotations with gradient-based model explanations. The resulting model improves the grounding capabilities of an off-the-shelf vision-and-language model. Particularly, SynGround improves the pointing game accuracy of ALBEF on the Flickr30k dataset from 79.38% to 87.26%, and on RefCOCO+ Test A from 69.35% to 79.06% and on RefCOCO+ Test B from 53.77% to 63.67%.

Grounding Language Models for Visual Entity Recognition

We introduce AutoVER, an Autoregressive model for Visual Entity Recognition. Our model extends an autoregressive Multi-modal Large Language Model by employing retrieval augmented constrained generation. It mitigates low performance on out-of-domain entities while excelling in queries that require visually-situated reasoning. Our method learns to distinguish similar entities within a vast label space by contrastively training on hard negative pairs in parallel with a sequence-to-sequence objective without an external retriever. During inference, a list of retrieved candidate answers explicitly guides language generation by removing invalid decoding paths. The proposed method achieves significant improvements across different dataset splits in the recently proposed Oven-Wiki benchmark. Accuracy on the Entity seen split rises from 32.7% to 61.5%. It also demonstrates superior performance on the unseen and query splits by a substantial double-digit margin.

Improved Visual Grounding through Self-Consistent Explanations

Vision-and-language models trained to match images with text can be combined with visual explanation methods to point to the locations of specific objects in an image. Our work shows that the localization --"grounding"-- abilities of these models can be further improved by finetuning for self-consistent visual explanations. We propose a strategy for augmenting existing text-image datasets with paraphrases using a large language model, and SelfEQ, a weakly-supervised strategy on visual explanation maps for paraphrases that encourages self-consistency. Specifically, for an input textual phrase, we attempt to generate a paraphrase and finetune the model so that the phrase and paraphrase map to the same region in the image. We posit that this both expands the vocabulary that the model is able to handle, and improves the quality of the object locations highlighted by gradient-based visual explanation methods (e.g. GradCAM). We demonstrate that SelfEQ improves performance on Flickr30k, ReferIt, and RefCOCO+ over a strong baseline method and several prior works. Particularly, comparing to other methods that do not use any type of box annotations, we obtain 84.07% on Flickr30k (an absolute improvement of 4.69%), 67.40% on ReferIt (an absolute improvement of 7.68%), and 75.10%, 55.49% on RefCOCO+ test sets A and B respectively (an absolute improvement of 3.74% on average).

ElasticDiffusion: Training-free Arbitrary Size Image Generation

Diffusion models have revolutionized image generation in recent years, yet they are still limited to a few sizes and aspect ratios. We propose ElasticDiffusion, a novel training-free decoding method that enables pretrained text-to-image diffusion models to generate images with various sizes. ElasticDiffusion attempts to decouple the generation trajectory of a pretrained model into local and global signals. The local signal controls low-level pixel information and can be estimated on local patches, while the global signal is used to maintain overall structural consistency and is estimated with a reference image. We test our method on CelebA-HQ (faces) and LAION-COCO (objects/indoor/outdoor scenes). Our experiments and qualitative results show superior image coherence quality across aspect ratios compared to MultiDiffusion and the standard decoding strategy of Stable Diffusion. Code: https://github.com/MoayedHajiAli/ElasticDiffusion-official.git

Characterizing Video Question Answering with Sparsified Inputs

In Video Question Answering, videos are often processed as a full-length sequence of frames to ensure minimal loss of information. Recent works have demonstrated evidence that sparse video inputs are sufficient to maintain high performance. However, they usually discuss the case of single frame selection. In our work, we extend the setting to multiple number of inputs and other modalities. We characterize the task with different input sparsity and provide a tool for doing that. Specifically, we use a Gumbel-based learnable selection module to adaptively select the best inputs for the final task. In this way, we experiment over public VideoQA benchmarks and provide analysis on how sparsified inputs affect the performance. From our experiments, we have observed only 5.2%-5.8% loss of performance with only 10% of video lengths, which corresponds to 2-4 frames selected from each video. Meanwhile, we also observed the complimentary behaviour between visual and textual inputs, even under highly sparsified settings, suggesting the potential of improving data efficiency for video-and-language tasks.

SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data

We propose Subject-Conditional Relation Detection SCoRD, where conditioned on an input subject, the goal is to predict all its relations to other objects in a scene along with their locations. Based on the Open Images dataset, we propose a challenging OIv6-SCoRD benchmark such that the training and testing splits have a distribution shift in terms of the occurrence statistics of $\langle$subject, relation, object$\rangle$ triplets. To solve this problem, we propose an auto-regressive model that given a subject, it predicts its relations, objects, and object locations by casting this output as a sequence of tokens. First, we show that previous scene-graph prediction methods fail to produce as exhaustive an enumeration of relation-object pairs when conditioned on a subject on this benchmark. Particularly, we obtain a recall@3 of 83.8% for our relation-object predictions compared to the 49.75% obtained by a recent scene graph detector. Then, we show improved generalization on both relation-object and object-box predictions by leveraging during training relation-object pairs obtained automatically from textual captions and for which no object-box annotations are available. Particularly, for $\langle$subject, relation, object$\rangle$ triplets for which no object locations are available during training, we are able to obtain a recall@3 of 42.59% for relation-object pairs and 32.27% for their box locations.