Related papers: Module-wise Adaptive Distillation for Multimodalit…

Multi-task learning has been widely adopted in many computer vision tasks to improve overall computation efficiency or boost the performance of individual tasks, under the assumption that those tasks are correlated and complementary to each…

Deep learning has contributed greatly to many successes in artificial intelligence in recent years. Today, it is possible to train models that have thousands of layers and hundreds of billions of parameters. Large-scale deep models have…

Model distillation aims to distill the knowledge of a complex model into a simpler one. In this paper, we consider an alternative formulation called dataset distillation: we keep the model fixed and instead attempt to distill the knowledge…

Large Multimodal Models (LMMs) often rely on in-context learning (ICL) to perform new visual question answering (VQA) tasks with minimal supervision. However, ICL performance, especially in smaller LMMs, does not always improve…

Knowledge distillation is an effective way for model compression in deep learning. Given a large model (i.e., teacher model), it aims to improve the performance of a compact model (i.e., student model) by transferring the information from…

Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance. Previous methods mainly focus on two aspects: 1) training the student to…

Multimodal learning has shown great potentials in numerous scenes and attracts increasing interest recently. However, it often encounters the problem of missing modality data and thus suffers severe performance degradation in practice. To…

Training models continually to detect and classify objects, from new classes and new domains, remains an open problem. In this work, we conduct a thorough analysis of why and how object detection models forget catastrophically. We focus on…

Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated…

Multimodal learning integrates diverse modalities but suffers from modality imbalance, where dominant modalities suppress weaker ones due to inconsistent convergence rates. Existing methods predominantly rely on static modulation or…

Recent studies show the promise of large language models (LLMs) for few-shot tabular classification but highlight challenges due to the variability in structured data. To address this, we propose distilling data into actionable insights to…

Imaging inverse problems are commonly addressed by minimizing measurement consistency and signal prior terms. While huge attention has been paid to developing high-performance priors, even the most advanced signal prior may lose its…

Large language models (LLMs) are known to memorize parts of their training data, raising important concerns around privacy and security. While previous research has focused on studying memorization in pre-trained models, much less is known…

Codistillation has been proposed as a mechanism to share knowledge among concurrently trained models by encouraging them to represent the same function through an auxiliary loss. This contrasts with the more commonly used fully-synchronous…

Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that…

This paper addresses the problem of decentralized learning to achieve a high-performance global model by asking a group of clients to share local models pre-trained with their own data resources. We are particularly interested in a specific…

Recent progress in accelerating text-to-image diffusion models enables high-fidelity synthesis within a single denoising step. However, customizing the fast one-step models remains challenging, as existing methods consistently fail to…

In medical healthcare, obtaining detailed annotations is challenging, highlighting the need for robust Vision-Language Models (VLMs). Pretrained VLMs enable fine-tuning on small datasets or zero-shot inference, achieving performance…

Multispectral pedestrian detection has been shown to be effective in improving performance within complex illumination scenarios. However, prevalent double-stream networks in multispectral detection employ two separate feature extraction…

Many real-world applications today like video surveillance and urban governance need to address the recognition of masked faces, where content replacement by diverse masks often brings in incomplete appearance and ambiguous representation,…