相关论文: Masked Video Distillation: Rethinking Masked Featu…

Diffusion-based image super-resolution (SR) methods have shown promise in reconstructing high-resolution images with fine details from low-resolution counterparts. However, these approaches typically require tens or even hundreds of…

Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective…

Feature representation learning is the key recipe for learning-based Multi-View Stereo (MVS). As the common feature extractor of learning-based MVS, vanilla Feature Pyramid Networks (FPNs) suffer from discouraged feature representations for…

Diffusion models for super-resolution (SR) produce high-quality visual results but require expensive computational costs. Despite the development of several methods to accelerate diffusion-based SR models, some (e.g., SinSR) fail to produce…

Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements. However, the huge memory consumption of state-of-the-art models makes it hard to deploy them on vehicles, and the non-trivial latency will…

Recently, machine unlearning approaches have been proposed to remove sensitive information from well-trained large models. However, most existing methods are tailored for LLMs, while MLLM-oriented unlearning remains at its early stage.…

Video Frame Interpolation (VFI) remains a cornerstone in video enhancement, enabling temporal upscaling for tasks like slow-motion rendering, frame rate conversion, and video restoration. While classical methods rely on optical flow and…

Assessing the forensic value of hand images involves the use of unique features and patterns present in an individual's hand. The human hand has distinct characteristics, such as the pattern of veins, fingerprints, and the geometry of the…

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…

Multimodal fusion leverages information across modalities to learn better feature representations with the goal of improving performance in fusion-based tasks. However, multimodal datasets, especially in medical settings, are typically…

Knowledge Distillation (KD) has been considered as a key solution in model compression and acceleration in recent years. In KD, a small student model is generally trained from a large teacher model by minimizing the divergence between the…

Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various…

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

The area of temporally fine-grained video representation learning focuses on generating frame-by-frame representations for temporally dense tasks, such as fine-grained action phase classification and frame retrieval. In this work, we…

Recently, open-source video diffusion models (VDMs), such as WanX, Magic141 and HunyuanVideo, have been scaled to over 10 billion parameters. These large-scale VDMs have demonstrated significant improvements over smaller-scale VDMs across…

As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data. Among these varied…

Video tasks are compute-heavy and thus pose a challenge when deploying in real-time applications, particularly for tasks that require state-of-the-art Vision Transformers (ViTs). Several research efforts have tried to address this challenge…

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…

With the rapid development of vision tasks and the scaling on datasets and models, redundancy reduction in vision datasets has become a key area of research. To address this issue, dataset distillation (DD) has emerged as a promising…

On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. We observe that standard on-policy distillation can improve a student's output quality…