TIPS: Text-Image Pretraining with Spatial Awareness

• URL: http://arxiv.org/abs/2410.16512v1
• Date: Mon, 21 Oct 2024 21:05:04 GMT
• Title: TIPS: Text-Image Pretraining with Spatial Awareness
• Authors: Kevis-Kokitsi Maninis, Kaifeng Chen, Soham Ghosh, Arjun Karpur, Koert Chen, Ye Xia, Bingyi Cao, Daniel Salz, Guangxing Han, Jan Dlabal, Dan Gnanapragasam, Mojtaba Seyedhosseini, Howard Zhou, Andre Araujo,
• Abstract summary: Self-supervised image-only pretraining is still the go-to method for many vision applications. We propose a novel general-purpose image-text model, which can be effectively used off-the-shelf for dense and global vision tasks.
• Score: 13.38247732379754
• License:
• Abstract: While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised image-only pretraining is still the go-to method for many dense vision applications (e.g. depth estimation, semantic segmentation), despite the lack of explicit supervisory signals. In this paper, we close this gap between image-text and self-supervised learning, by proposing a novel general-purpose image-text model, which can be effectively used off-the-shelf for dense and global vision tasks. Our method, which we refer to as Text-Image Pretraining with Spatial awareness (TIPS), leverages two simple and effective insights. First, on textual supervision: we reveal that replacing noisy web image captions by synthetically generated textual descriptions boosts dense understanding performance significantly, due to a much richer signal for learning spatially aware representations. We propose an adapted training method that combines noisy and synthetic captions, resulting in improvements across both dense and global understanding tasks. Second, on the learning technique: we propose to combine contrastive image-text learning with self-supervised masked image modeling, to encourage spatial coherence, unlocking substantial enhancements for downstream applications. Building on these two ideas, we scale our model using the transformer architecture, trained on a curated set of public images. Our experiments are conducted on 8 tasks involving 16 datasets in total, demonstrating strong off-the-shelf performance on both dense and global understanding, for several image-only and image-text tasks.

Related papers

• Compositional Entailment Learning for Hyperbolic Vision-Language Models [54.41927525264365]
  We show how to fully leverage the innate hierarchical nature of hyperbolic embeddings by looking beyond individual image-text pairs. We propose Compositional Entailment Learning for hyperbolic vision-language models. Empirical evaluation on a hyperbolic vision-language model trained with millions of image-text pairs shows that the proposed compositional learning approach outperforms conventional Euclidean CLIP learning.
  arXiv  Detail & Related papers  (2024-10-09T14:12:50Z)
• Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality [50.48859793121308]
  Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning. Recent research has highlighted severe limitations in their ability to perform compositional reasoning over objects, attributes, and relations.
  arXiv  Detail & Related papers  (2023-05-23T08:28:38Z)
• Multi-Modal Representation Learning with Text-Driven Soft Masks [48.19806080407593]
  We propose a visual-linguistic representation learning approach within a self-supervised learning framework. We generate diverse features for the image-text matching (ITM) task via soft-masking the regions in an image. We identify the relevant regions to each word by computing the word-conditional visual attention using multi-modal encoder.
  arXiv  Detail & Related papers  (2023-04-03T05:07:49Z)
• Universal Multimodal Representation for Language Understanding [110.98786673598015]
  This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of images either from a light topic-image lookup table extracted over the existing sentence-image pairs. Then, the text and images are encoded by a Transformer encoder and convolutional neural network, respectively.
  arXiv  Detail & Related papers  (2023-01-09T13:54:11Z)
• Fine-Grained Semantically Aligned Vision-Language Pre-Training [151.7372197904064]
  Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks. Existing methods mainly model the cross-modal alignment by the similarity of the global representations of images and texts. We introduce LO, a fine-grained semantically aLigned visiOn-langUage PrE-training framework, which learns fine-grained semantic alignment from the novel perspective of game-theoretic interactions.
  arXiv  Detail & Related papers  (2022-08-04T07:51:48Z)
• Self-Supervised Image-to-Text and Text-to-Image Synthesis [23.587581181330123]
  We propose a novel self-supervised deep learning based approach towards learning the cross-modal embedding spaces. In our approach, we first obtain dense vector representations of images using StackGAN-based autoencoder model and also dense vector representations on sentence-level utilizing LSTM based text-autoencoder.
  arXiv  Detail & Related papers  (2021-12-09T13:54:56Z)
• FILIP: Fine-grained Interactive Language-Image Pre-Training [106.19474076935363]
  Fine-grained Interactive Language-Image Pre-training achieves finer-level alignment through a cross-modal late interaction mechanism. We construct a new large-scale image-text pair dataset called FILIP300M for pre-training. Experiments show that FILIP achieves state-of-the-art performance on multiple downstream vision-language tasks.
  arXiv  Detail & Related papers  (2021-11-09T17:15:38Z)
• Scene Text Synthesis for Efficient and Effective Deep Network Training [62.631176120557136]
  We develop an innovative image synthesis technique that composes annotated training images by embedding foreground objects of interest into background images. The proposed technique consists of two key components that in principle boost the usefulness of the synthesized images in deep network training. Experiments over a number of public datasets demonstrate the effectiveness of our proposed image synthesis technique.
  arXiv  Detail & Related papers  (2019-01-26T10:15:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.