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 use in many practical applications due to their large size, high latency and fixed architectures. Unfortunately, recent work shows training a small custom VLFM for resource-limited applications is currently very difficult using public and smaller-scale data. In this paper, we introduce a new distillation mechanism (DIME-FM) that allows us to transfer the knowledge contained in large VLFMs to smaller, customized foundation models using a relatively small amount of inexpensive, unpaired images and sentences. We transfer the knowledge from the pre-trained CLIP-ViTL/14 model to a ViT-B/32 model, with only 40M public images and 28.4M unpaired public sentences. The resulting model "Distill-ViT-B/32" rivals the CLIP-ViT-B/32 model pre-trained on its private WiT dataset (400M image-text pairs): Distill-ViT-B/32 achieves similar results in terms of zero-shot and linear-probing performance on both ImageNet and the ELEVATER (20 image classification tasks) benchmarks. It also displays comparable robustness when evaluated on five datasets with natural distribution shifts from ImageNet.
Nanjing University of Science and Technology（南京理工大学）
Human multimodal emotion recognition (MER) aims to perceive human emotions via language, visual and acoustic modalities. Despite the impressive performance of previous MER approaches, the inherent multimodal heterogeneities still haunt and the contribution of different modalities varies significantly. In this work, we mitigate this issue by proposing a decoupled multimodal distillation (DMD) approach that facilitates flexible and adaptive crossmodal knowledge distillation, aiming to enhance the discriminative features of each modality. Specially, the representation of each modality is decouple…
In this paper, we introduce the semantic knowledge of medical images from their diagnostic reports to provide an inspirational network training and an interpretable prediction mechanism with our proposed novel multimodal neural network, namely TandemNet. Inside TandemNet, a language model is used to represent report text, which cooperates with the image model in a tandem scheme. We propose a novel dual-attention model that facilitates high-level interactions between visual and semantic information and effectively distills useful features for prediction. In the testing stage, TandemNet can make…
Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions
MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所信息与智能系统研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Zhejiang University（浙江大学）
From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Grounded Open-vocabulary Situation Recognition
National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；Huazhong University of Science and Technology（华中科技大学）；The Hong Kong Polytechnic University（香港理工大学）
Attributes of sound inherent to objects can provide valuable cues to learn rich representations for object detection and tracking. Furthermore, the co-occurrence of audiovisual events in videos can be exploited to localize objects over the image field by solely monitoring the sound in the environment. Thus far, this has only been feasible in scenarios where the camera is static and for single object detection. Moreover, the robustness of these methods has been limited as they primarily rely on RGB images which are highly susceptible to illumination and weather changes. In this work, we present…
Source-Free Domain Adaptation with Frozen Multimodal Foundation Model
University of Shanghai for Science and Technology（上海理工大学）；Universität Hamburg（汉堡大学）；ComOriginMat Inc.（康创矩阵公司）；University of Electronic Science and Technology of China（电子科技大学）；University of Surrey（萨里大学）
From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳校区）；Peng Cheng Laboratory（鹏城实验室）
Many image enhancement or editing operations, such as forward and inverse tone mapping or color grading, do not have a unique solution, but instead a range of solutions, each representing a different style. Despite this, existing learning-based methods attempt to learn a unique mapping, disregarding this style. In this work, we show that information about the style can be distilled from collections of image pairs and encoded into a 2- or 3-dimensional vector. This gives us not only an efficient representation but also an interpretable latent space for editing the image style. We represent the …
Monash University（莫纳什大学）；Inception Institute of Artificial Intelligence（Inception人工智能研究院）
Recently, a lot of automated white blood cells (WBC) or leukocyte classification techniques have been developed. However, all of these methods only utilize a single modality microscopic image i.e. either blood smear or fluorescence based, thus missing the potential of a better learning from multimodal images. In this work, we develop an efficient multimodal architecture based on a first of its kind multimodal WBC dataset for the task of WBC classification. Specifically, our proposed idea is developed in two steps - 1) First, we learn modality specific independent subnetworks inside a single ne…
Distilling Textual Priors from LLM to Efficient Image Fusion
Hefei University of Technology（合肥工业大学）；University of Science and Technology of China（中国科学技术大学）；Hefei Institutes of Physical Science, Chinese Academy of Sciences（中国科学院合肥物质科学研究院）
Temporal Saliency-Guided Distillation: A Scalable Framework for Distilling Video Datasets
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Shanghai Jiao Tong University（上海交通大学）
Recent works on Multimodal 3D Computer-aided diagnosis have demonstrated that obtaining a competitive automatic diagnosis model when a 3D convolution neural network (CNN) brings more parameters and medical images are scarce remains nontrivial and challenging. Considering both consistencies of regions of interest in multimodal images and diagnostic accuracy, we propose a novel mutual attention-based hybrid dimensional network for MultiModal 3D medical image classification (MMNet). The hybrid dimensional network integrates 2D CNN with 3D convolution modules to generate deeper and more informativ…
MorphDistill: Distilling Unified Morphological Knowledge from Pathology Foundation Models for Colorectal Cancer Survival Prediction
Department of Pathology, College of Medicine, The Ohio State University Wexner Medical Center（俄亥俄州立大学医学学院病理学系，韦克斯纳医学中心）；Center for Artificial Intelligence Research, Wake Forest University School of Medicine（威克森林大学医学院人工智能研究中心）
The ability for a human to understand an Artificial Intelligence (AI) model's decision-making process is critical in enabling stakeholders to visualize model behavior, perform model debugging, promote trust in AI models, and assist in collaborative human-AI decision-making. As a result, the research fields of interpretable and explainable AI have gained traction within AI communities as well as interdisciplinary scientists seeking to apply AI in their subject areas. In this paper, we focus on advancing the state-of-the-art in interpreting multimodal models - a class of machine learning methods…
University of Padova（帕多瓦大学）；Padua University Hospital（帕多瓦大学医院）；University of Genova（热那亚大学）
To analyse multimodal 3-dimensional medical images, interpolation is required for resampling which - unavoidably - introduces an interpolation error. In this work we consider three segmented 3-dimensional images resampled with three different neuroimaging software tools for comparing undersampling and oversampling strategies and to identify where the oversampling error lies. The results indicate that undersampling to the lowest image size is advantageous in terms of mean value per segment errors and that the oversampling error is larger where the gradient is steeper, showing a Gibbs effect.
Deep learning has been the subject of growing interest in recent years. Specifically, a specific type called Multimodal learning has shown great promise for solving a wide range of problems in domains such as language, vision, audio, etc. One promising research direction to improve this further has been learning rich and robust low-dimensional data representation of the high-dimensional world with the help of large-scale datasets present on the internet. Because of its potential to avoid the cost of annotating large-scale datasets, self-supervised learning has been the de facto standard for th…
Kyoto University（京都大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；NAVER Corporation（NAVER公司）
Multimodal relational data analysis has become of increasing importance in recent years, for exploring across different domains of data, such as images and their text tags obtained from social networking services (e.g., Flickr). A variety of data analysis methods have been developed for visualization; to give an example, t-Stochastic Neighbor Embedding (t-SNE) computes low-dimensional feature vectors so that their similarities keep those of the observed data vectors. However, t-SNE is designed only for a single domain of data but not for multimodal data; this paper aims at visualizing multimod…
