相关论文: Adaptive Offline Quintuplet Loss for Image-Text Ma…

In deep metric learning, the Triplet Loss has emerged as a popular method to learn many computer vision and natural language processing tasks such as facial recognition, object detection, and visual-semantic embeddings. One issue that…

Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge…

We review the current schemes of text-image matching models and propose improvements for both training and inference. First, we empirically show limitations of two popular loss (sum and max-margin loss) widely used in training text-image…

The global reach of social media has amplified the spread of hateful content, including implicit sexism, which is often overlooked by conventional detection methods. In this work, we introduce an Adaptive Supervised Contrastive lEarning…

Securing a sufficient amount of paired data is important to train an image-text retrieval (ITR) model, but collecting paired data is very expensive. To address this issue, in this paper, we propose an active learning algorithm for ITR that…

The latest trend in the bottom-up perspective for arbitrary-shape scene text detection is to reason the links between text segments using Graph Convolutional Network (GCN). Notwithstanding, the performance of the best performing bottom-up…

Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…

Large-scale pre-trained Vision-Language Models (VLMs) have exhibited impressive zero-shot performance and transferability, allowing them to adapt to downstream tasks in a data-efficient manner. However, when only a few labeled samples are…

Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the quality of the offline dataset, such pre-trained agents may…

Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to…

Unsupervised image translation using adversarial learning has been attracting attention to improve the image quality of medical images. However, adversarial training based on the global evaluation values of discriminators does not provide…

Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model. Existing techniques for loss function learning have shown promising results, often…

In recent years, the explosion of web videos makes text-video retrieval increasingly essential and popular for video filtering, recommendation, and search. Text-video retrieval aims to rank relevant text/video higher than irrelevant ones.…

Though much work has been done in the domain of improving the adversarial robustness of facial recognition systems, a surprisingly small percentage of it has focused on self-supervised approaches. In this work, we present an approach that…

Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks…

In this paper, we introduce a model designed to improve the prediction of image-text alignment, targeting the challenge of compositional understanding in current visual-language models. Our approach focuses on generating high-quality…

How can you sample good negative examples for contrastive learning? We argue that, as with metric learning, contrastive learning of representations benefits from hard negative samples (i.e., points that are difficult to distinguish from an…

Open-set logo recognition is commonly solved by first detecting possible logo regions and then matching the detected parts against an ever-evolving dataset of cropped logo images. The matching model, a metric learning problem, is especially…

Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection. However, they are vulnerable to adversarial attacks, which can cause incorrect…

Text embedding models play a crucial role in natural language processing, particularly in information retrieval, and their importance is further highlighted with the recent utilization of RAG (Retrieval- Augmented Generation). This study…