相关论文: SigLino: Efficient Multi-Teacher Distillation for …

Large Vision-Language Foundation Models (VLFM), such as CLIP, ALIGN and Florence, are trained on large-scale datasets of image-caption pairs and achieve superior transferability and robustness on downstream tasks, but they are difficult to…

Very low-resolution face recognition is challenging due to the serious loss of informative facial details in resolution degradation. In this paper, we propose a generative-discriminative representation distillation approach that combines…

Adapting pretrained language models (LMs) into vision-language models (VLMs) can degrade their native linguistic capability due to representation shift and cross-modal interference introduced during multimodal adaptation. Such loss is…

Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for…

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…

Large-scale visual learning is increasingly limited by training cost. Existing knowledge distillation methods transfer from a stronger teacher to a weaker student for compression or final-accuracy improvement. We instead investigate…

3D vision-language grounding faces a fundamental data bottleneck: while 2D models train on billions of images, 3D models have access to only thousands of labeled scenes--a six-order-of-magnitude gap that severely limits performance. We…

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

Recent multi-teacher distillation methods have unified the encoders of multiple foundation models into a single encoder, achieving competitive performance on core vision tasks like classification, segmentation, and depth estimation. This…

Model merging offers an effective way to integrate the capabilities of multiple fine-tuned models. However, the performance degradation of the merged model remains a challenge, particularly when none or few data are available. This paper…

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…

Dataset distillation reduces the network training cost by synthesizing small and informative datasets from large-scale ones. Despite the success of the recent dataset distillation algorithms, three drawbacks still limit their wider…

EEG foundation models (EFMs) achieve strong cross-subject and cross-task generalization through large-scale pretraining and downstream fine-tuning. Through empirical analysis, we observe that (i) task-adapted EFMs provide strong decoding…

Image-text contrastive models like CLIP have wide applications in zero-shot classification, image-text retrieval, and transfer learning. However, they often struggle on compositional visio-linguistic tasks (e.g., attribute-binding or…

Multi-view camera-based 3D object detection has become popular due to its low cost, but accurately inferring 3D geometry solely from camera data remains challenging and may lead to inferior performance. Although distilling precise 3D…

Multimodal transfer learning aims to transform pretrained representations of diverse modalities into a common domain space for effective multimodal fusion. However, conventional systems are typically built on the assumption that all…

Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation and depth prediction. However, a fundamental capability…

Vision Language Models (VLMs), pre-trained on large-scale image-text datasets, enable zero-shot predictions for unseen data but may underperform on specific unseen tasks. Continual learning (CL) can help VLMs effectively adapt to new data…

Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this paper, we introduce Refined Logit Distillation (RLD) to address…