相关论文: Image-Text Pre-Training for Logo Recognition

This work investigates three methods for calculating loss for autoencoder-based pretraining of image encoders: The commonly used reconstruction loss, the more recently introduced deep perceptual similarity loss, and a feature prediction…

Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While the problem of…

Existing logo detection benchmarks consider artificial deployment scenarios by assuming that large training data with fine-grained bounding box annotations for each class are available for model training. Such assumptions are often invalid…

In the segmentation of remotely sensed images, deep learning models are typically pre-trained using large image databases like ImageNet before fine-tuned on domain-specific datasets. However, the performance of these fine-tuned models is…

Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or linguistic knowledge learning. In this paper, we propose a…

In recent years, deep learning-based methods have shown promising results in computer vision area. However, a common deep learning model requires a large amount of labeled data, which is labor-intensive to collect and label. What's more,…

Under the flourishing development in performance, current image-text retrieval methods suffer from $N$-related time complexity, which hinders their application in practice. Targeting at efficiency improvement, this paper presents a simple…

Understanding long text is of great demands in practice but beyond the reach of most language-image pre-training (LIP) models. In this work, we empirically confirm that the key reason causing such an issue is that the training images are…

Adapting pre-trained models to open classes is a challenging problem in machine learning. Vision-language models fully explore the knowledge of text modality, demonstrating strong zero-shot recognition performance, which is naturally suited…

A text on an image often stores important information and directly carries high level semantics, makes it as important source of information and become a very active research topic. Many studies have shown that the use of CNN-based neural…

Current logo retrieval research focuses on closed set scenarios. We argue that the logo domain is too large for this strategy and requires an open set approach. To foster research in this direction, a large-scale logo dataset, called Logos…

Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training is to learn text representations that are useful for…

The deep neural networks used in modern computer vision systems require enormous image datasets to train them. These carefully-curated datasets typically have a million or more images, across a thousand or more distinct categories. The…

Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across…

In this paper, we introduce a fully convolutional network for the document layout analysis task. While state-of-the-art methods are using models pre-trained on natural scene images, our method Doc-UFCN relies on a U-shaped model trained…

This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are…

The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive.…

The core problem in zero-shot open vocabulary detection is how to align visual and text features, so that the detector performs well on unseen classes. Previous approaches train the feature pyramid and detection head from scratch, which…

Existing image-text matching approaches typically leverage triplet loss with online hard negatives to train the model. For each image or text anchor in a training mini-batch, the model is trained to distinguish between a positive and the…

State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining. ImageNet classification is the de facto pretraining task for these models. Yet, ImageNet is now nearly ten years old and is by modern…