相关论文: I$^2$MD: 3D Action Representation Learning with In…

Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. We explore the…

Knowledge Distillation (KD) for object detection aims to train a compact detector by transferring knowledge from a teacher model. Since the teacher model perceives data in a way different from humans, existing KD methods only distill…

In this paper, we propose a simple yet effective contrastive knowledge distillation framework that achieves sample-wise logit alignment while preserving semantic consistency. Conventional knowledge distillation approaches exhibit…

It is currently difficult to distill discrete diffusion models. In contrast, continuous diffusion literature has many distillation approaches methods that can reduce sampling steps to a handful. Our method, Discrete Moment Matching…

Autonomous systems have advanced significantly, but challenges persist in accident-prone environments where robust decision-making is crucial. A single vehicle's limited sensor range and obstructed views increase the likelihood of…

Conventional knowledge distillation (KD) approaches are designed for the student model to predict similar output as the teacher model for each sample. Unfortunately, the relationship across samples with same class is often neglected. In…

Recently, deep learning technology has been successfully introduced into Automatic Modulation Recognition (AMR) tasks. However, the success of deep learning is all attributed to the training on large-scale datasets. Such a large amount of…

Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D detection has brought significant improvement, e.g., Pseudo-LiDAR methods. However, the existing methods usually apply non-end-to-end training strategies and…

In the field of 3D object detection for autonomous driving, the sensor portfolio including multi-modality and single-modality is diverse and complex. Since the multi-modal methods have system complexity while the accuracy of single-modal…

Multi-modal RGB and Depth (RGBD) data are predominant in many domains such as robotics, autonomous driving and remote sensing. The combination of these multi-modal data enhances environmental perception by providing 3D spatial context,…

We introduce MM-Mixing, a multi-modal mixing alignment framework for 3D understanding. MM-Mixing applies mixing-based methods to multi-modal data, preserving and optimizing cross-modal connections while enhancing diversity and improving…

Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-level features like…

High-performance Radar-Camera 3D object detection can be achieved by leveraging knowledge distillation without using LiDAR at inference time. However, existing distillation methods typically transfer modality-specific features directly to…

In-context learning (ICL) allows large language models (LLMs) to solve novel tasks without weight updates. Despite its empirical success, the mechanism behind ICL remains poorly understood, limiting our ability to interpret, improve, and…

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Drug target interaction (DTI) prediction is a cornerstone of computational drug discovery, enabling rational design, repurposing, and mechanistic insights. While deep learning has advanced DTI modeling, existing approaches primarily rely on…

The rapid increase in multimodal data availability has sparked significant interest in cross-modal knowledge distillation (KD) techniques, where richer "teacher" modalities transfer information to weaker "student" modalities during model…

Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We demonstrate that…

Dense visual prediction tasks, such as detection and segmentation, are crucial for time-critical applications (e.g., autonomous driving and video surveillance). While deep models achieve strong performance, their efficiency remains a…

Supervised multi-modal learning involves mapping multiple modalities to a target label. Previous studies in this field have concentrated on capturing in isolation either the inter-modality dependencies (the relationships between different…