{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/classifying-textual-data-with-pre-trained","title":"Classifying Textual Data with Pre-trained Vision Models through Transfer Learning and Data Transformations","arxiv_id":"2106.12479","date":"2021-06-23","proceeding":null,"authors":["Charaf Eddine Benarab"],"abstract":"Knowledge is acquired by humans through experience, and no boundary is set between the kinds of knowledge or skill levels we can achieve on different tasks at the same time. When it comes to Neural Networks, that is not the case. The breakthroughs in the field are extremely task and domain-specific. Vision and language are dealt with in separate manners, using separate methods and different datasets. Current text classification methods, mostly rely on obtaining contextual embeddings for input text samples, then training a classifier on the embedded dataset. Transfer learning in Language-related tasks in general, is heavily used in obtaining the contextual text embeddings for the input samples. In this work, we propose to use the knowledge acquired by benchmark Vision Models which are trained on ImageNet to help a much smaller architecture learn to classify text. A data transformation technique is used to create a new image dataset, where each image represents a sentence embedding from the last six layers of BERT, projected on a 2D plane using a t-SNE based method. We trained five models containing early layers sliced from vision models which are pretrained on ImageNet, on the created image dataset for the IMDB dataset embedded with the last six layers of BERT. Despite the challenges posed by the very different datasets, experimental results achieved by this approach which links large pretrained models on both language and vision, are very promising, without employing compute resources. Specifically, Sentiment Analysis is achieved by five different models on the same image dataset obtained after BERT embeddings are transformed into gray scale images. Index Terms: BERT, Convolutional Neural Networks, Domain Adaptation, image classification, Natural Language Processing, t-SNE, text classification, Transfer Learning","url_abs":"https://arxiv.org/abs/2106.12479v4","url_pdf":"https://arxiv.org/pdf/2106.12479v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"classifying-textual-data-with-pre-trained","repo_url":"https://github.com/EddCBen/Classifying-Textual-Data-with-pretrained-Vision-Models-through-Transfer-Learning-and-Data-Transforms","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embedding","task_name":"Sentence Embedding"},{"task_slug":"sentence-embedding-1","task_name":"Sentence-Embedding"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"AlexNet [alexnet]","rank_in_archive_order":45,"of":49,"metrics":{"Accuracy":"87"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"VGG16 [vgg16]","rank_in_archive_order":46,"of":49,"metrics":{"Accuracy":"86"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"ResNext[resnext]","rank_in_archive_order":47,"of":49,"metrics":{"Accuracy":"85"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}