Related papers: Rapidly deploying on-device eye tracking by distil…

Machine-learned interatomic potentials have transformed computational research in the physical sciences. Recent atomistic `foundation' models have changed the field yet again: trained on many different chemical elements and domains, these…

We propose DistillNeRF, a self-supervised learning framework addressing the challenge of understanding 3D environments from limited 2D observations in outdoor autonomous driving scenes. Our method is a generalizable feedforward model that…

Face forgery detection (FFD) is devoted to detecting the authenticity of face images. Although current CNN-based works achieve outstanding performance in FFD, they are susceptible to capturing local forgery patterns generated by various…

A common dilemma in 3D object detection for autonomous driving is that high-quality, dense point clouds are only available during training, but not testing. We use knowledge distillation to bridge the gap between a model trained on…

Deep learning-based face recognition continues to face challenges due to its reliance on huge datasets obtained from web crawling, which can be costly to gather and raise significant real-world privacy concerns. To address this issue, we…

Dataset distillation (DD) compresses a large training set into a small synthetic set, reducing storage and training cost, and has shown strong results on general benchmarks. Decoupled DD further improves efficiency by splitting the pipeline…

Recent Mixture-of-Experts (MoE)-based large language models (LLMs) such as Qwen-MoE and DeepSeek-MoE are transforming generative AI in natural language processing. However, these models require vast and diverse training data. Federated…

Existing deepfake detection methods heavily rely on static labeled datasets. However, with the proliferation of generative models, real-world scenarios are flooded with massive amounts of unlabeled fake face data from unknown sources. This…

Model-based deep learning has achieved astounding successes due in part to the availability of large-scale real-world data. However, processing such massive amounts of data comes at a considerable cost in terms of computations, storage,…

Many computer vision tasks rely on labeled data. Rapid progress in generative modeling has led to the ability to synthesize photorealistic images. However, controlling specific aspects of the generation process such that the data can be…

There is substantial interest in developing artificial intelligence systems to support radiologists across tasks ranging from segmentation to report generation. Existing computed tomography (CT) foundation models have largely focused on…

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…

Real-world weather, illumination, and imaging variations often induce severe domain shifts, degrading single-source detectors in unseen environments. Existing single-domain generalized object detection (SDGOD) methods mainly rely on data…

Acquiring aligned visuo-tactile datasets is slow and costly, requiring specialised hardware and large-scale data collection. Synthetic generation is promising, but prior methods are typically single-modality, limiting cross-modal learning.…

The fashion e-commerce industry has witnessed significant growth in recent years, prompting exploring image-based virtual try-on techniques to incorporate Augmented Reality (AR) experiences into online shopping platforms. However, existing…

Training large AI models typically requires large-scale datasets in the machine learning process, making training and parameter-tuning process both time-consuming and costly. Some researchers address this problem by carefully synthesizing a…

Virtual try-on (VTON) has recently achieved impressive visual fidelity, but most existing systems require uploading personal photos to cloud-based GPUs, raising privacy concerns and limiting on-device deployment. To address this, we present…

Self-supervised foundation models have shown great potential in computer vision thanks to the pre-training paradigm of masked autoencoding. Scale is a primary factor influencing the performance of these foundation models. However, these…

In this paper, we propose an efficient and fast object detector which can process hundreds of frames per second. To achieve this goal we investigate three main aspects of the object detection framework: network architecture, loss function…

Deploying medical image segmentation models in routine clinical workflows is often constrained by on-premises infrastructure, where computational resources are fixed and cloud-based inference may be restricted by governance and security…