Improves text-to-image generation with bidirectional capabilities.
problem Generating realistic images from text descriptions.
method Integrates text and image modalities using MMVR architecture with n-gram cost function and multiple sentences.
result Significant improvement in image quality over existing methods (over 20%).
Scene text magnifier enhances readability for visually impaired.
problem Helps visually impaired read natural scene text.
method Four CNN-based networks: character erasing, extraction, magnify, synthesis.
result Effective text magnification without background alteration.
StoryGen uses images to generate coherent text from multiple images.
problem Generating coherent text from multiple images.
method Designing a Relational Text Data Generator algorithm to relate features from plural images.
result The model can generate meaningful paragraphs containing extracted features from input images.
Single-stage neural architecture improves text-to-image synthesis.
problem Combining text and image generation is challenging.
method Used deep residual networks and sentence interpolation.
result Achieved state-of-the-art performance with single-stage training.
Improves text-to-image translation by using GANs and captioning networks.
problem Generating images that accurately reflect the meaning of a sentence.
method Uses cycle consistent adversarial networks and captioning networks to improve image generation.
result Significantly improved image quality compared to existing methods.
Generates coherent storybooks from plain text using diffusion models.
problem Ensuring coherency in a sequence of images for storytelling applications.
method Combines pre-trained LLM and text-guided Latent Diffusion Model for zero-shot generation.
result Outperforms state-of-the-art image editing baselines in generating coherent storybooks.
Develops a deep model for joint image-text learning.
problem Bidirectional joint image-text modeling.
method Variational hetero-encoder randomized GAN (VHE-GAN).
result Achieves state-of-the-art performance in image-text learning and generation.
HW2MP-GAN tackles ancient handwritten text recognition.
problem Automatic text recognition from ancient handwritten records.
method Conditional Generative Adversarial Network (HW2MP-GAN) with Sliced Wasserstein distance and U-Net architectures.
result HW2MP-GAN outperforms state-of-the-art models in image-to-image translation and handwritten recognition.
Paper proposes method to generate images from text using GANs trained on uncaptioned images.
problem Limited captioned image datasets for text-to-image synthesis.
method Conditional GANs trained on uncaptioned images with an Image Captioning Module.
result Promising preliminary results compared to unconditional GANs.
DreamFusion uses text-to-image diffusion models to create 3D images efficiently.
problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.
New method evaluates text-to-image synthesis for realism, variety, and semantic accuracy.
problem Lack of metrics revealing semantic accuracy in text-to-image synthesis.
method Uses Inception network representations and t-SNE visualization for semantic evaluation.
result Classification accuracy of generated images to real images' visual concepts correlates with semantic accuracy.
Generates garden paintings from text descriptions using deep learning.
problem Lack of firsthand material for traditional Chinese garden reconstruction.
method Deep learning model trained on text and paintings of Ming Dynasty gardens.
result Model generates garden paintings in Ming Dynasty style based on textual descriptions.
Predicts whether an image is an abstraction of text or vice versa.
problem Understanding semantic cross-modal relations between images and text.
method Introduces a new metric (ABS) and a deep learning autoencoder approach to predict it.
result Demonstrates feasibility of predicting the relative abstractness level of image-text pairs.
ZegOT uses optimal transport to zero-shot segment images with text prompts.
problem Zero-shot semantic segmentation with limited image-text alignment knowledge.
method ZegOT uses optimal transport to match multiple text prompts with frozen image embeddings.
result ZegOT achieves state-of-the-art performance in zero-shot semantic segmentation.
Multimodal bitransformer boosts image-text classification.
problem Combining text and image modalities for improved classification.
method Supervised multimodal bitransformer model integrating text and image encoders.
result State-of-the-art performance on multimodal classification benchmarks.
Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing text-to-image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In…
Improved text-to-image alignment using iterative VQA feedback.
problem Misalignment between text prompts and generated images, especially for complex inputs.
method Decompose complex prompts into assertions, evaluate each using VQA, combine scores iteratively.
result Significantly higher correlation with human ratings compared to CLIP, BLIP scores.
Paper evaluates using app images for classification, improving accuracy.
problem Improving app classification accuracy when text descriptions are missing or inadequate.
method Used OCR, pic2vec, captionbot.ai, and object detection to convert images into text or vectors for classification.
result Improved classification accuracy of 96% for some app categories when images are added.
Survey on adversarial attacks and defenses for images, graphs, and text.
problem Adversarial examples threaten the safety of deep learning applications.
method Review of adversarial attack and defense mechanisms for images, graphs, and text.
result Systematic overview of adversarial attacks and countermeasures.
New method improves image generation for inverse problems using text prompts.
problem Suboptimal performance of existing latent diffusion models for inverse problems.
method Prompt tuning and latent variable projection to optimize text embeddings.
result P2L method outperforms existing methods on various inverse problem tasks.
JECL clusters images and captions by jointly learning representations and assignments.
problem Clustering image-caption pairs with limited structured training data.
method Parallel encoders trained with clustering and alignment objectives, minimizing KL divergence and maximizing Jensen-Shannon divergence, with regularizers.
result JECL outperforms single-view and multi-view methods on large image-caption datasets.
O-GANs improve fashion image generation by conditioning on a hierarchical ontology.
problem Challenges in training GANs to generate images from text descriptions.
method Ontology Generative Adversarial Networks (O-GANs) that condition on a hierarchical fashion ontology.
result O-GANs achieve better image quality and conditioning results compared to standard GANs.
Proposes STN for HDA by aligning domain-shared classifier and subspace.
problem Learning in target domain using knowledge from heterogeneous source domain.
method End-to-end learning of domain-shared classifier and domain-invariant subspace; soft-label strategy for unlabeled data; adaptive coefficient for soft-labels.
result Significantly outperforms state-of-the-art approaches in various transfer tasks.
Improved text-to-image and multimodal understanding through adaptive generation order optimization.
problem Determining optimal generation sequences in text-to-image synthesis and multimodal understanding.
method Introduced a learnable control module trained via Group Relative Policy Optimization (GRPO) to determine the generation order.
result Learning the control block substantially improves text-to-image alignment and multimodal understanding in DLMs.
Gradient-based framework for optimizing text prompts in diffusion models.
problem Efficiently optimizing prompts in text-to-image diffusion models with large domain space and non-differentiable embeddings.
method Formulated as discrete optimization over language space, designed compact subspaces, and introduced shortcut text gradient.
result Empirically discovered prompts that enhance or destroy image faithfulness.
Generative model creates meal images from ingredient descriptions.
problem Synthesize photo-realistic meal images from ingredient descriptions.
method Attention-based ingredients-image association model, cycle-consistent constraint.
result Model generates meal images corresponding to ingredient descriptions.
SeqAttnGAN generates interactive images based on multi-turn text descriptions.
problem Interactive image editing with multi-turn textual commands.
method SeqAttnGAN uses a neural state tracker and GAN framework for sequential image generation and refinement.
result SeqAttnGAN outperforms state-of-the-art models on interactive image editing tasks.
In this project we analysed how much semantic information images carry, and how much value image data can add to sentiment analysis of the text associated with the images. To better understand the contribution from images, we compared models which only made use of image data, models which only made use of text data, an…
New text-to-image diffusion models improve scene understanding for AI agents.
problem Fine-grained scene understanding for AI agents from text and images.
method Pre-trained text-to-image diffusion models optimized for generating images from text prompts.
result Policies learned with Stable Control Representations outperform state-of-the-art approaches on various control tasks.
This research discovers model architecture and training dataset characteristics through strategic input probing.
problem Discovering model architecture and training dataset characteristics in black box models.
method Structured input probes and model outputs are used to train a deep classifier for image and text classification.
result The approach successfully distinguishes between different image and text datasets and architectures.
Improved dataset distillation for images and texts boosts model accuracy.
problem Reducing dataset size for faster and more energy-efficient model training.
method Simultaneous distillation of images and soft labels, extending to text datasets.
result 2-4% increase in accuracy for image classification tasks, 20% reduction in distilled samples.
Tensor networks reveal limitations for efficient text description but suggest potential for images.
problem Efficiently describing large text and image data sets using tensor networks.
method Investigation of mutual information scaling, introduction of mutual information estimators, and use of autoregressive and convolutional neural networks.
result Text data cannot be efficiently described by 1D tensor networks, while images may be better described by 2D tensor networks.
Synthesizing images or texts automatically is a useful research area in the artificial intelligence nowadays. Generative adversarial networks (GANs), which are proposed by Goodfellow in 2014, make this task to be done more efficiently by using deep neural networks. We consider generating corresponding images from an in…
CLIP learns joint image-text representations for zero-shot learning.
problem Understanding and improving zero-shot transfer performance in CLIP.
method Formal study of transferrable representation learning and analysis of zero-shot transfer performance.
result Proposes a new CLIP-type approach that outperforms existing methods.
GANs improve image generation from text and other images.
problem Improving image generation from text and other images.
method Adversarial training to estimate real data distribution and generate synthetic data.
result GANs outperform conventional methods in image generation.
Improves text-to-image diffusion models using GFlowNets.
problem Aligning diffusion models with text descriptions.
method Post-training diffusion models with GFlowNets to generate high-reward images.
result Effective alignment of large-scale text-to-image diffusion models with reward information.
Zero-shot contrastive loss improves text-guided image style transfer without extra training.
problem Stochastic nature of diffusion models leads to trade-offs between style transformation and content preservation.
method Proposes a zero-shot contrastive loss for diffusion models that doesn't require additional fine-tuning or auxiliary networks.
result Method outperforms existing methods while preserving content and requiring no additional training.
Generates realistic faces from detailed textual descriptions.
problem Face generation from fine-grained textual descriptions.
method Conditional GAN model with DC-GAN and GAN-CLS loss, using CelebA dataset with generated captions.
result Promising results in generating diverse face images from fine-grained textual descriptions.
Neural nets analyze Magic: the Gathering cards for text and images.
problem Classify Magic: the Gathering cards into multiple categories.
method Used Convolutional and Recurrent Neural Networks to analyze card text and images.
result Developed a method to generate card text matching an input image.
The multimodal web elements such as text and images are associated with inherent memory costs to store and transfer over the Internet. With the limited network connectivity in developing countries, webpage rendering gets delayed in the presence of high-memory demanding elements such as images (relative to text). To ove…
Simplified image clustering achieves competitive results without text-based embeddings.
problem Complexity and resource requirements of state-of-the-art clustering methods.
method SCP: trains a small cluster head using pre-trained vision model features and positive data pairs.
result SCP achieves highly competitive performance on various benchmark datasets.
Visual question answering is a recently proposed artificial intelligence task that requires a deep understanding of both images and texts. In deep learning, images are typically modeled through convolutional neural networks, and texts are typically modeled through recurrent neural networks. While the requirement for mo…
Efficiently distills pretrained text-to-image models without real data, improving FID and CLIP scores.
problem Slow iterative refinement process of diffusion-based text-to-image models.
method Guided Score identity Distillation with Long and Short Classifier-Free Guidance.
result Achieves state-of-the-art FID performance with competitive CLIP score.
Proposes neural network for causal inference with multimodal data.
problem Estimating causal effects with text and image data as confounders.
method Double machine learning framework adapted to partially linear models, semi-synthetic dataset generation.
result Improved performance in causal effect estimation with multimodal data.
A tree-based dictionary learning model is developed for joint analysis of imagery and associated text. The dictionary learning may be applied directly to the imagery from patches, or to general feature vectors extracted from patches or superpixels (using any existing method for image feature extraction). Each image is …
This work uses image generation models to find vision model bugs.
problem Automatically discovering failures in vision models.
method Conditional text-to-image generation and captioning models.
result Demonstrated utility of large-scale generative models to find vision model bugs.
Paper proposes a faster, higher-quality RL method for text-to-image models.
problem Improving image quality and prompt alignment in RL post-training of text-to-image models.
method Online RL variant that reduces variance by sampling paired trajectories and optimizing flow velocity.
result Method converges faster and yields higher output quality and prompt alignment.
Paper introduces Latent-CLIP for efficient text-image comparison in latent space.
problem Efficiently compare text and images in latent space without costly decoding.
method Trains CLIP model in latent space, uses Latent-CLIP rewards for noise optimization, and guides generation away from harmful content.
result Latent-CLIP matches CLIP performance on text-image classification and harmful content detection.