Related papers: Cross-Modality Knowledge Distillation Network for …

3D object detection from monocular images is an ill-posed problem due to the projective entanglement of depth and scale. To overcome this ambiguity, we present a novel self-supervised method for textured 3D shape reconstruction and pose…

Human activity recognition (HAR) based on multi-modal approach has been recently shown to improve the accuracy performance of HAR. However, restricted computational resources associated with wearable devices, i.e., smartwatch, failed to…

Knowledge distillation (KD) has witnessed its powerful capability in learning compact models in object detection. Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of…

Multi-modal methods based on camera and LiDAR sensors have garnered significant attention in the field of 3D detection. However, many prevalent works focus on single or partial stage fusion, leading to insufficient feature extraction and…

We study data-free knowledge distillation (KD) for monocular depth estimation (MDE), which learns a lightweight model for real-world depth perception tasks by compressing it from a trained teacher model while lacking training data in the…

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…

In this work, we propose Mutual Information Maximization Knowledge Distillation (MIMKD). Our method uses a contrastive objective to simultaneously estimate and maximize a lower bound on the mutual information of local and global feature…

Recently, fusing the LiDAR point cloud and camera image to improve the performance and robustness of 3D object detection has received more and more attention, as these two modalities naturally possess strong complementarity. In this paper,…

Precisely localizing 3D objects from a single image constitutes a central challenge in monocular 3D detection. While DETR-like architectures offer a powerful paradigm, their direct application in this domain encounters inherent limitations,…

Despite the good results that have been achieved in unimodal segmentation, the inherent limitations of individual data increase the difficulty of achieving breakthroughs in performance. For that reason, multi-modal learning is increasingly…

Monocular 3D object detection poses a significant challenge due to the lack of depth information in RGB images. Many existing methods strive to enhance the object depth estimation performance by allocating additional parameters for object…

Periocular biometric, the peripheral area of the ocular, is a collaborative alternative to the face, especially when the face is occluded or masked. However, in practice, sole periocular biometric capture the least salient facial features,…

We introduce Layered Self-Supervised Knowledge Distillation (LSSKD) framework for training compact deep learning models. Unlike traditional methods that rely on pre-trained teacher networks, our approach appends auxiliary classifiers to…

To reduce a model size but retain performance, we often rely on knowledge distillation (KD) which transfers knowledge from a large "teacher" model to a smaller "student" model. However, KD on multimodal datasets such as vision-language…

Multi-view 3D detection with bird's eye view (BEV) is crucial for autonomous driving and robotics, but its robustness in real-world is limited as it struggles to predict accurate depth values. A mainstream solution, cross-modal…

Automatic segmentation of the prostate cancer from the multi-modal magnetic resonance images is of critical importance for the initial staging and prognosis of patients. However, how to use the multi-modal image features more efficiently is…

Pseudo-LiDAR-based methods for monocular 3D object detection have received considerable attention in the community due to the performance gains exhibited on the KITTI3D benchmark, in particular on the commonly reported validation split.…

Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving. In case of monocular vision, successful methods have been mainly based on two ingredients: (i) a network generating…

Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from…

Multi-modal learning is typically performed with network architectures containing modality-specific layers and shared layers, utilizing co-registered images of different modalities. We propose a novel learning scheme for unpaired…