Related papers: Generating Enhanced Negatives for Training Languag…
Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-level features that humans deem non-semantic. This dependency…
Discriminative pre-trained language models (PLMs) learn to predict original texts from intentionally corrupted ones. Taking the former text as positive and the latter as negative samples, the PLM can be trained effectively for…
Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine…
Today text classification models have been widely used. However, these classifiers are found to be easily fooled by adversarial examples. Fortunately, standard attacking methods generate adversarial texts in a pair-wise way, that is, an…
We examine the ability of large language models (LLMs) to generate salient (interesting) negative statements about real-world entities; an emerging research topic of the last few years. We probe the LLMs using zero- and k-shot unconstrained…
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…
Current vision-language detection and grounding models predominantly focus on prompts with positive semantics and often struggle to accurately interpret and ground complex expressions containing negative semantics. A key reason for this…
Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…
Deep Learning models are incredibly data-hungry and require very large labeled datasets for supervised learning. As a consequence, these models often suffer from overfitting, limiting their ability to generalize to real-world examples.…
This paper explores object detection in the small data regime, where only a limited number of annotated bounding boxes are available due to data rarity and annotation expense. This is a common challenge today with machine learning being…
Over the last few years, Contextualized Pre-trained Neural Language Models, such as BERT, GPT, have shown significant gains in various NLP tasks. To enhance the robustness of existing pre-trained models, one way is adversarial examples…
Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse…
Generative Adversarial Networks (GANs) have experienced a recent surge in popularity, performing competitively in a variety of tasks, especially in computer vision. However, GAN training has shown limited success in natural language…
We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer training images than required for competing discriminative…
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and…
Generative Adversarial Networks (GANs) have known a tremendous success for many continuous generation tasks, especially in the field of image generation. However, for discrete outputs such as language, optimizing GANs remains an open…
One of the most significant challenges in statistical signal processing and machine learning is how to obtain a generative model that can produce samples of large-scale data distribution, such as images and speeches. Generative Adversarial…
Neural text generation models conditioning on given input (e.g. machine translation and image captioning) are usually trained by maximum likelihood estimation of target text. However, the trained models suffer from various types of errors…
The pre-trained text-image discriminative models, such as CLIP, has been explored for open-vocabulary semantic segmentation with unsatisfactory results due to the loss of crucial localization information and awareness of object shapes.…
The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We…