Related papers: Towards Bridging the Performance Gaps of Joint Ene…
In this paper, we consider the problem of automatic modulation classification with multiple sensors in the presence of unknown time offset, phase offset and received signal amplitude. We develop a novel hybrid maximum likelihood (HML)…
Federated Learning (FL) has revolutionized how we train deep neural networks by enabling decentralized collaboration while safeguarding sensitive data and improving model performance. However, FL faces two crucial challenges: the diverse…
The rapid evolution of multimodal foundation model has demonstrated significant progresses in vision-language understanding and generation, e.g., our previous work SEED-LLaMA. However, there remains a gap between its capability and the…
We present UniGen-1.5, a unified multimodal large language model (MLLM) for advanced image understanding, generation and editing. Building upon UniGen, we comprehensively enhance the model architecture and training pipeline to strengthen…
The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely…
This paper presents a novel method to deal with the challenging task of generating photographic images conditioned on semantic image descriptions. Our method introduces accompanying hierarchical-nested adversarial objectives inside the…
Fine-grained open-set recognition (FineOSR) aims to recognize images belonging to classes with subtle appearance differences while rejecting images of unknown classes. A recent trend in OSR shows the benefit of generative models to…
Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two sub-tasks: mixup generation and classification. However, the recent dominant online training method confines mixup to supervised learning (SL), and the…
Despite substantial progress in no-reference image quality assessment (NR-IQA), previous training models often suffer from over-fitting due to the limited scale of used datasets, resulting in model performance bottlenecks. To tackle this…
Sharpness-aware minimization (SAM) has received increasing attention in computer vision since it can effectively eliminate the sharp local minima from the training trajectory and mitigate generalization degradation. However, SAM requires…
As a crucial part of the spectral filter array (SFA)-based multispectral imaging process, spectral demosaicing has exploded with the proliferation of deep learning techniques. However, (1) bothering by the difficulty of capturing…
Current generative networks are increasingly proficient in generating high-resolution realistic images. These generative networks, especially the conditional ones, can potentially become a great tool for providing new image datasets. This…
Given the inherent class imbalance issue within student performance datasets, samples belonging to the edges of the target class distribution pose a challenge for predictive machine learning algorithms to learn. In this paper, we introduce…
Detecting glass regions is a challenging task due to the inherent ambiguity in their transparency and reflective characteristics. Current solutions in this field remain rooted in conventional deep learning paradigms, requiring the…
Medical image classification is one of the most critical problems in the image recognition area. One of the major challenges in this field is the scarcity of labelled training data. Additionally, there is often class imbalance in datasets…
Medical images usually suffer from image degradation in clinical practice, leading to decreased performance of deep learning-based models. To resolve this problem, most previous works have focused on filtering out degradation-causing…
Energy-based models (EBMs) are generative models that are usually trained via maximum likelihood estimation. This approach becomes challenging in generic situations where the trained energy is non-convex, due to the need to sample the Gibbs…
With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images. However, discrepancies with the real data acquired from various…
Unified Multimodal Models (UMMs) integrate both visual understanding and generation within a single framework. Their ultimate aspiration is to create a cycle where understanding and generation mutually reinforce each other. While recent…
Semi-supervised learning has emerged as a powerful paradigm for leveraging large amounts of unlabeled data to improve the performance of machine learning models when labeled data are scarce. Among existing approaches, methods derived from…