- CapsFusion Rethinking Image-Text Data at Scale (30 Oct 2023)
This is my reading note for CapsFusion: Rethinking Image-Text Data at Scale. The paper studies the quality of caption data in vision language dataset and shown the simple caption limits the performance of the trained model. The caption of those dataset is generated synthetic and filter out a lot of real would knowledge. As a result, the paper proposes to use chatGPT to combine the synthetic caption and raw caption to generates a better caption. It’ then results in a much
- A Picture is Worth a Thousand Words Principled Recaptioning Improves Image Generation (28 Oct 2023)
This is my reading note for A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation. The papers found that the text data used to train text to image model is now quality, which is based alt text of images.it proposed to use an image caption model to generate high quality text for the images; then the diffusion model trained from this new text data show much better performance.
- GIT A Generative Image-to-text Transformer for Vision and Language (16 Oct 2023)
This is my reading note for GIT: A Generative Image-to-text Transformer for Vision and Language. This paper proposes a image-text pre-training model. The model contains visual encoder and text decoder; the text decoder is based on self-attention, which takes concatenated text tokens and visual tokens as input.
- Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency (04 Oct 2023)
This is my reading note for Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency. The papers proposes a method to train a multi modality model between text and image. Especially, the paper propose cycle consistency loss to leverage unpaired text and image: use image to generate text and use text to recover image and vice verse. It reminds me cycle-GAN paper.
- An Early Evaluation of GPT-4V(ision) (03 Oct 2023)
This is my reading note for An Early Evaluation of GPT-4V(ision). The highlights of our findings are as follows:
- GPT-4V exhibits impressive performance on English visual-centric benchmarks but fails to recognize simple Chinese texts in the images;
- GPT-4V shows inconsistent refusal behavior when answering questions related to sensitive traits such as gender, race, and age;
- GPT-4V obtains worse results than GPT-4 (API) on language understanding tasks including general language understanding benchmarks and visual commonsense knowledge evaluation benchmarks;
- Few-shot prompting can improve GPT-4V’s performance on both visual understanding and language understanding;
- GPT-4V struggles to find the nuances between two similar images and solve the easy math picture puzzles;
- GPT-4V shows non-trivial performance on the tasks of similar modalities to image, such as video and thermal. O (p. 1)
- CoCa Contrastive Captioners are Image-Text Foundation Models (31 Jul 2023)
This is my reading note for CoCa: Contrastive Captioners are Image-Text Foundation Models. The paper proposes a multi modality model, especially it models the problem as image caption as well as text alignment problem. The model contains three component: a vision encoder, a text decoder (which generates text embedding ) and a multi modality decoder , which generate caption given image and text embedding.
- 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.
- DreamBooth Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation (28 Sep 2022)
This is my reading note on DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. Given as input just a few (3~5) images of a subject, DreamBooth fine-tune a pretrained text-to-image model such that it learns to bind a unique identifier with that specific subject. Once the subject is embedded in the output domain of the model, the unique identifier can then be used to synthesize fully-novel photorealistic images of the subject contextualized in different scenes. By leveraging the semantic prior embedded in the model with a new autogenous class-specific prior preservation loss, DreamBooth enables synthesizing the subject in diverse scenes, poses, views, and lighting conditions that do not appear in the reference images. (check Figure 1 as an example)