Tag: multimodality

Information in the real world usually comes as different modalities. For example, images are usually associated with tags and text explanations; text contains images to more clearly express the main idea of the article. Different modalities are characterized by different statistical properties. For instance, images are usually represented as pixel intensities or outputs of feature extractors, while texts are represented as discrete word count vectors. Due to the distinct statistical properties of different information resources, it is important to discover the relationship between different modalities. Multimodal learning is a good model to represent the joint representations of different modalities. The multimodal learning model is also capable of supplying a missing modality based on observed ones.

• BLIP-Diffusion Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing (21 Aug 2023)
  

  This is my reading note for BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing. The paper proposes a method for generating an image with text prompt and target visual concept. To do that the paper trained blip model to align visual features with text prompt and then concatenate the visual embedding to the text prompt to generate the need. Code and models will be released at https://github.com/salesforce/LAVIS/tree/main/projects/blip-diffusion. Project page at https://dxli94.github.io/BLIP-Diffusion-website/.

• DALL-E, DALL-E2 and StoryDALL-E (30 Sep 2022)
  

  This my reading note on Zero-Shot Text-to-Image Generation (aka, DALL-E), its extension Hierarchical Text-Conditional Image Generation with CLIP Latents (aka, DALLE-2 or unCLIP) and StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation. DALL-E is a transformer generating image given captions, by autoregressively modeling the text and image tokens as a single stream of data. StoryDALL-E extends DALL-E by generating a sequence of images for a sequence of caption to complete a story.

• Pix2seq A Language Modeling Framework for Object Detection (28 Sep 2022)
  

  Pix2seq: A Language Modeling Framework for Object Detection casts object detection as a language modeling task conditioned on the observed pixel inputs. Object descriptions (e.g., bounding boxes and class labels) are expressed as sequences of discrete tokens, and we train a neural network to perceive the image and generate the desired sequence. Our approach is based mainly on the intuition that if a neural network knows about where and what the objects are, we just need to teach it how to read them out. Experiment results are shown in Table 1, which indicates Pix2seq achieves state of art result on coco.

• CLIP Learning Transferable Visual Models From Natural Language Supervision (27 Sep 2022)
  

  This my reading note on Learning Transferable Visual Models From Natural Language Supervision. The proposed method is called Contrastive Language-Image Pre-training or CLIP. State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. We demonstrate that the simple pre-training task of predicting which caption (freeform text instead of strict labeling) goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks.

• unCLIP-Hierarchical Text-Conditional Image Generation with CLIP Latents (23 Sep 2022)
  

  This is my reading note on Hierarchical Text-Conditional Image Generation with CLIP Latents. This paper proposes a two-stage model (unCLIP): a prior that generates a CLIP image embedding given a text caption, and a decoder that generates an image conditioned on the image embedding, for generating images from text.