Related papers: SCKD: Semi-Supervised Cross-Modality Knowledge Dis…

Domain adaptive person re-identification (re-ID) is a challenging task due to the large discrepancy between the source domain and the target domain. To reduce the domain discrepancy, existing methods mainly attempt to generate pseudo labels…

As one of the automotive sensors that have emerged in recent years, 4D millimeter-wave radar has a higher resolution than conventional 3D radar and provides precise elevation measurements. But its point clouds are still sparse and noisy,…

The LiDAR 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving. However, many existing LiDAR detection models depend on complex feature transformations,…

Vision foundation models (VFMs) such as DINO have led to a paradigm shift in 2D camera-based perception towards extracting generalized features to support many downstream tasks. Recent works introduce self-supervised cross-modal knowledge…

To boost a detector for single-frame 3D object detection, we present a new approach to train it to simulate features and responses following a detector trained on multi-frame point clouds. Our approach needs multi-frame point clouds only…

In this paper, we propose a novel training strategy called SupFusion, which provides an auxiliary feature level supervision for effective LiDAR-Camera fusion and significantly boosts detection performance. Our strategy involves a data…

Deep cascaded architectures for magnetic resonance imaging (MRI) acceleration have shown remarkable success in providing high-quality reconstruction. However, as the number of cascades increases, the improvements in reconstruction tend to…

Knowledge distillation is widely applied in various fundamental vision models to enhance the performance of compact models. Existing knowledge distillation methods focus on designing different distillation targets to acquire knowledge from…

Sequence-level knowledge distillation (SLKD) is a model compression technique that leverages large, accurate teacher models to train smaller, under-parameterized student models. Why does pre-processing MT data with SLKD help us train…

A crucial task in scene understanding is 3D object detection, which aims to detect and localize the 3D bounding boxes of objects belonging to specific classes. Existing 3D object detectors heavily rely on annotated 3D bounding boxes during…

Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains underexplored. To…

Although multi-view 3D object detection based on the Bird's-Eye-View (BEV) paradigm has garnered widespread attention as an economical and deployment-friendly perception solution for autonomous driving, there is still a performance gap…

The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that knowledge distillation (KD), especially the mean-teacher…

Compact models can be effectively trained through Knowledge Distillation (KD), a technique that transfers knowledge from larger, high-performing teacher models. Two key challenges in Knowledge Distillation (KD) are: 1) balancing learning…

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…

The proliferation of foundation models, pretrained on large-scale unlabeled datasets, has emerged as an effective approach in creating adaptable and reusable architectures that can be leveraged for various downstream tasks using satellite…

Existing 3D Human Pose Estimation (HPE) methods achieve high accuracy but suffer from computational overhead and slow inference, while knowledge distillation methods fail to address spatial relationships between joints and temporal…

4D mmWave radar provides weather-robust, velocity-aware measurements and is more cost-effective than LiDAR. However, radar-only 3D detection still trails LiDAR-based systems because radar point clouds are sparse, irregular, and often…

Recent work on 4D point cloud sequences has attracted a lot of attention. However, obtaining exhaustively labeled 4D datasets is often very expensive and laborious, so it is especially important to investigate how to utilize raw unlabeled…

Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…