Related papers: SAVeD: Semantic Aware Version Discovery
As large language models (LLMs) achieve strong performance on traditional benchmarks, there is an urgent need for more challenging evaluation frameworks that probe deeper aspects of semantic understanding. We introduce SAGE (Semantic…
Panoramic X-ray is a simple and effective tool for diagnosing dental diseases in clinical practice. When deep learning models are developed to assist dentist in interpreting panoramic X-rays, most of their performance suffers from the…
The aim of this paper is to formalise the task of continual semi-supervised anomaly detection (CSAD), with the aim of highlighting the importance of such a problem formulation which assumes as close to real-world conditions as possible.…
Data-driven fault diagnostics of safety-critical systems often faces the challenge of a complete lack of labeled data associated with faulty system conditions (i.e., fault types) at training time. Since an unknown number and nature of fault…
Inspired by the recent success of deep learning in multiscale information encoding, we introduce a variational autoencoder (VAE) based semi-supervised method for detection of faulty traffic data, which is cast as a classification problem.…
Semantic information has been proved effective in scene text recognition. Most existing methods tend to couple both visual and semantic information in an attention-based decoder. As a result, the learning of semantic features is prone to…
The vast amount of unlabeled multi-temporal and multi-sensor remote sensing data acquired by the many Earth Observation satellites present a challenge for change detection. Recently, many generative model-based methods have been proposed…
Unsupervised visual anomaly detection from multi-view images presents a significant challenge: distinguishing genuine defects from benign appearance variations caused by viewpoint changes. Existing methods, often designed for single-view…
Technological advancements have led to the rise of wearable devices with sensors that continuously monitor user activities, generating vast amounts of unlabeled data. This data is challenging to interpret, and manual annotation is…
Novel class discovery (NCD) aims to infer novel categories in an unlabeled dataset by leveraging prior knowledge of a labeled set comprising disjoint but related classes. Given that most existing literature focuses primarily on utilizing…
Learning from large amounts of unsupervised data and a small amount of supervision is an important open problem in computer vision. We propose a new semi-supervised learning method, Semantic Positives via Pseudo-Labels (SemPPL), that…
We present LatentDiff, a scalable framework for semantic dataset comparison that operates directly in the latent space of pretrained vision encoders. By combining sparse autoencoder-based divergence testing with density ratio estimation,…
Anomaly detection aims to identify data instances that deviate significantly from majority of data, which has been widely used in fraud detection, network security, and industrial quality control. Existing methods struggle with datasets…
To overcome the data-hungry challenge, we have proposed a semi-supervised contrastive learning framework for the task of class-imbalanced semantic segmentation. First and foremost, to make the model operate in a semi-supervised manner, we…
We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…
Complex data mining has wide application value in many fields, especially in the feature extraction and classification tasks of unlabeled data. This paper proposes an algorithm based on self-supervised learning and verifies its…
Image Deepfake Detection (IDD) separates manipulated images from authentic ones by spotting artifacts of synthesis or tampering. Although large vision-language models (LVLMs) offer strong image understanding, adapting them to IDD often…
Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic…
This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…
Visual Semantic Embedding (VSE) aims to extract the semantics of images and their descriptions, and embed them into the same latent space for cross-modal information retrieval. Most existing VSE networks are trained by adopting a hard…