Weakly Supervised Vision-and-Language Pre-training with Relative Representations

• URL: http://arxiv.org/abs/2305.15483v1
• Date: Wed, 24 May 2023 18:10:24 GMT
• Title: Weakly Supervised Vision-and-Language Pre-training with Relative Representations
• Authors: Chi Chen, Peng Li, Maosong Sun, Yang Liu
• Abstract summary: Weakly supervised vision-and-language pre-training has been shown to effectively reduce the data cost of pre-training. Current methods use only local descriptions of images, i.e., object tags, as cross-modal anchors to construct weakly-aligned image-text pairs for pre-training.
• Score: 76.63610760577214
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Weakly supervised vision-and-language pre-training (WVLP), which learns cross-modal representations with limited cross-modal supervision, has been shown to effectively reduce the data cost of pre-training while maintaining decent performance on downstream tasks. However, current WVLP methods use only local descriptions of images, i.e., object tags, as cross-modal anchors to construct weakly-aligned image-text pairs for pre-training. This affects the data quality and thus the effectiveness of pre-training. In this paper, we propose to directly take a small number of aligned image-text pairs as anchors, and represent each unaligned image and text by its similarities to these anchors, i.e., relative representations. We build a WVLP framework based on the relative representations, namely RELIT, which collects high-quality weakly-aligned image-text pairs from large-scale image-only and text-only data for pre-training through relative representation-based retrieval and generation. Experiments on four downstream tasks show that RELIT achieves new state-of-the-art results under the weakly supervised setting.

Related papers

• Debiasing Vison-Language Models with Text-Only Training [15.069736314663352]
  We propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases. To address the limitations, we propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases.
  arXiv  Detail & Related papers  (2024-10-12T04:34:46Z)
• Variational Distribution Learning for Unsupervised Text-to-Image Generation [42.3246826401366]
  We propose a text-to-image generation algorithm based on deep neural networks when text captions for images are unavailable during training. We employ a pretrained CLIP model, which is capable of properly aligning embeddings of images and corresponding texts in a joint space. We optimize a text-to-image generation model by maximizing the data log-likelihood conditioned on pairs of image-text CLIP embeddings.
  arXiv  Detail & Related papers  (2023-03-28T16:18:56Z)
• Generative Negative Text Replay for Continual Vision-Language Pretraining [95.2784858069843]
  Vision-language pre-training has attracted increasing attention recently. Massive data are usually collected in a streaming fashion. We propose a multi-modal knowledge distillation between images and texts to align the instance-wise prediction between old and new models.
  arXiv  Detail & Related papers  (2022-10-31T13:42:21Z)
• 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)
• Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone [170.85076677740292]
  We present FIBER (Fusion-In-the-Backbone-basedER), a new model architecture for vision-language (VL) pre-training. Instead of having dedicated transformer layers for fusion after the uni-modal backbones, FIBER pushes multimodal fusion deep into the model. We conduct comprehensive experiments on a wide range of VL tasks, ranging from VQA, image captioning, and retrieval, to phrase grounding, referring expression comprehension, and object detection.
  arXiv  Detail & Related papers  (2022-06-15T16:41:29Z)
• Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment [66.77841319057299]
  We propose a novel unsupervised Vision-and-Language pre-training curriculum for non-parallel texts and images. We first construct a weakly aligned image-text corpus via a retrieval-based approach, then apply a set of multi-granular alignment pre-training tasks. A comprehensive ablation study shows each granularity is helpful to learn a stronger pre-trained model.
  arXiv  Detail & Related papers  (2022-03-01T05:34:01Z)
• Vision-Language Pre-Training with Triple Contrastive Learning [45.80365827890119]
  We propose triple contrastive learning (TCL) for vision-language pre-training by leveraging both cross-modal and intra-modal self-supervision. Ours is the first work that takes into account local structure information for multi-modality representation learning.
  arXiv  Detail & Related papers  (2022-02-21T17:54:57Z)
• SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels [35.57369098866317]
  Vision-language pre-training on large-scale image-text pairs has witnessed rapid progress for learning cross-modal representations. We propose a new pre-training method which jointly aligns both the low-level and high-level semantics between image and text representations.
  arXiv  Detail & Related papers  (2021-03-14T02:39:14Z)
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision [57.031588264841]
  We leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme.
  arXiv  Detail & Related papers  (2021-02-11T10:08:12Z)

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.