Related papers: Data-Independent Operator: A Training-Free Artifac…

Deepfake detection has gained significant attention across audio, text, and image modalities, with high accuracy in distinguishing real from fake. However, identifying the exact source--such as the system or model behind a deepfake--remains…

Recent advances in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) have enabled diverse retrieval methods. However, existing retrieval methods often fail to accurately retrieve results for negation and exclusion…

In recent years, there have been significant improvements in various forms of image outlier detection. However, outlier detection performance under adversarial settings lags far behind that in standard settings. This is due to the lack of…

Recently, operator learning, or learning mappings between infinite-dimensional function spaces, has garnered significant attention, notably in relation to learning partial differential equations from data. Conceptually clear when outlined…

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data. Omni-supervised learning is lower-bounded by…

Unsupervised 3D object detection serves as an important solution for offline 3D object annotation. However, due to the data sparsity and limited views, the clustering-based label fitting in unsupervised object detection often generates…

Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always needs to be collected and manually labeled, an expensive, time…

Finetuning-free personalized image generation can synthesize customized images without test-time finetuning, attracting wide research interest owing to its high efficiency. Current finetuning-free methods simply adopt a single training…

Over the last few decades, artificial intelligence research has made tremendous strides, but it still heavily relies on fixed datasets in stationary environments. Continual learning is a growing field of research that examines how AI…

Large training sets have become a cornerstone of machine learning and are the foundation for recent advances in language modeling and multimodal learning. While data curation for pre-training is often still ad-hoc, one common paradigm is to…

Obtaining compact and discriminative features is one of the major challenges in many of the real-world image classification tasks such as face verification and object recognition. One possible approach is to represent input image on the…

Recent deep learning based approaches have outperformed classical stereo matching methods. However, current deep learning based end-to-end stereo matching methods adopt a generic encoder-decoder style network with skip connections. To limit…

Vision foundation models are renowned for the generalization ability due to massive training data. Nevertheless, they demand tremendous training resources, and the training data is often inaccessible, e.g., CLIP, DINOv2, posing great…

Image classification problems are typically addressed by first collecting examples with candidate labels, second cleaning the candidate labels manually, and third training a deep neural network on the clean examples. The manual labeling…

The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization…

A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new…

Digital image correlation (DIC) has become a valuable tool to monitor and evaluate mechanical experiments of cracked specimen, but the automatic detection of cracks is often difficult due to inherent noise and artefacts. Machine learning…

Diffusion models have recently achieved remarkable photorealism, making it increasingly difficult to distinguish real images from generated ones, raising significant privacy and security concerns. In response, we present a key finding:…

Deepfakes are becoming increasingly credible, posing a significant threat given their potential to facilitate fraud or bypass access control systems. This has motivated the development of deepfake detection methods, in which deep learning…

The extraordinary ability of generative models enabled the generation of images with such high quality that human beings cannot distinguish Artificial Intelligence (AI) generated images from real-life photographs. The development of…