Related papers: DAAL: Density-Aware Adaptive Line Margin Loss for …

Existing deepfake detectors face several challenges in achieving robustness and generalization. One of the primary reasons is their limited ability to extract relevant information from forgery videos, especially in the presence of various…

In several supervised learning scenarios, auxiliary losses are used in order to introduce additional information or constraints into the supervised learning objective. For instance, knowledge distillation aims to mimic outputs of a powerful…

Transfer learning aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Since the source and the target domains are usually from different distributions, existing methods mainly focus on…

Image-based brain cancer prediction models, based on radiomics, quantify the radiologic phenotype from magnetic resonance imaging (MRI). However, these features are difficult to reproduce because of variability in acquisition and…

The accurate prediction of protein-ligand binding affinity is important for drug discovery yet remains challenging for multi-domain proteins, where inter-domain dynamics and flexible linkers govern molecular recognition. Current geometric…

Uncertainty estimation is a crucial aspect of deploying dependable deep learning models in safety-critical systems. In this study, we introduce a novel and efficient method for deterministic uncertainty estimation called Discriminant…

Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of…

Sentiment analysis plays a crucial role in various domains, such as business intelligence and financial forecasting. Large language models (LLMs) have become a popular paradigm for sentiment analysis, leveraging multi-task learning to…

Reliable autonomous driving systems require accurate detection of traffic participants. To this end, multi-modal fusion has emerged as an effective strategy. In particular, 4D radar and LiDAR fusion methods based on multi-frame radar point…

Metric learning aims to learn a distance metric such that semantically similar instances are pulled together while dissimilar instances are pushed away. Many existing methods consider maximizing or at least constraining a distance margin in…

Despite the significant progress in multimodal large language models (MLLMs), their high computational cost remains a barrier to real-world deployment. Inspired by the mixture of depths (MoDs) in natural language processing, we aim to…

Dense regression is a widely used approach in computer vision for tasks such as image super-resolution, enhancement, depth estimation, etc. However, the high cost of annotation and labeling makes it challenging to achieve accurate results.…

Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…

In this paper, we explore a new generative approach for learning visual representations. Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We find that training with Mean Squared Error (MSE)…

Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct…

Active learning (AL) strategies aim to train high-performance models with minimal labeling efforts, only selecting the most informative instances for annotation. Current approaches to evaluating data informativeness predominantly focus on…

Recently, deep learning has significantly advanced the performance of point cloud geometry compression. However, the learning-based lossless attribute compression of point clouds with varying densities is under-explored. In this paper, we…

Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly, achieving better per-task performance with fewer parameters than single-task learning. Recently, decoder-focused architectures have…

Deep learning has achieved notable success in 3D object detection with the advent of large-scale point cloud datasets. However, severe performance degradation in the past trained classes, i.e., catastrophic forgetting, still remains a…

Data for face analysis often exhibit highly-skewed class distribution, i.e., most data belong to a few majority classes, while the minority classes only contain a scarce amount of instances. To mitigate this issue, contemporary deep…