Related papers: I$^2$MD: 3D Action Representation Learning with In…

Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…

Many recommender models have been proposed to investigate how to incorporate multimodal content information into traditional collaborative filtering framework effectively. The use of multimodal information is expected to provide more…

Multi-modal contrastive learning as a self-supervised representation learning technique has achieved great success in foundation model training, such as CLIP~\citep{radford2021learning}. In this paper, we study the theoretical properties of…

Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters. In the feature space, local regions within an individual…

Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality…

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

Multi-modal recommendation systems, which integrate diverse types of information, have gained widespread attention in recent years. However, compared to traditional collaborative filtering-based multi-modal recommendation systems, research…

This paper proposes a new knowledge distillation method tailored for image semantic segmentation, termed Intra- and Inter-Class Knowledge Distillation (I2CKD). The focus of this method is on capturing and transferring knowledge between the…

Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increasingly operate on paired vision-language inputs, multimodal distillation must preserve…

Recent advances in 3D object detection (3DOD) have obtained remarkably strong results for LiDAR-based models. In contrast, surround-view 3DOD models based on multiple camera images underperform due to the necessary view transformation of…

Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL) has emerged as a vital tool for aligning generative models…

In recent years, the rapid development of deep neural networks has brought increased attention to the security and robustness of these models. While existing adversarial attack algorithms have demonstrated success in improving adversarial…

Knowledge distillation is an effective method to improve the performance of a lightweight neural network (i.e., student model) by transferring the knowledge of a well-performed neural network (i.e., teacher model), which has been widely…

We present XKD, a novel self-supervised framework to learn meaningful representations from unlabelled videos. XKD is trained with two pseudo objectives. First, masked data reconstruction is performed to learn modality-specific…

Multimodal 3D object detectors leverage the strengths of both geometry-aware LiDAR point clouds and semantically rich RGB images to enhance detection performance. However, the inherent heterogeneity between these modalities, including…

Adversarial training significantly improves adversarial robustness, but superior performance is primarily attained with large models. This substantial performance gap for smaller models has spurred active research into adversarial…

Human multimodal emotion recognition (MER) seeks to infer human emotions by integrating information from language, visual, and acoustic modalities. Although existing MER approaches have achieved promising results, they still struggle with…

Lifelong imitation learning for manipulation tasks poses significant challenges due to distribution shifts that occur in incremental learning steps. Existing methods often focus on unsupervised skill discovery to construct an ever-growing…

Multimodal sentiment analysis (MSA) systems leverage information from different modalities to predict human sentiment intensities. Incomplete modality is an important issue that may cause a significant performance drop in MSA systems. By…

In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed…