Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge distillation to improve the generalization ability of CNN models for image classification under the data-deficient setting. The first phase is to learn a teacher model which possesses rich and generalizable visual representations via self-supervised learning, and the second phase is to distill the representations into a student model in a self-distillation manner, and meanwhile fine-tune the student model for the image classification task. We also propose a novel margin loss for the self-supervised contrastive learning proxy task to better learn the representation under the data-deficient scenario. Together with other tricks, we achieve competitive performance in the VIPriors image classification challenge.
University of Tübingen（蒂宾根大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Heidelberg（海德堡大学）
Recent advances have indicated the strengths of self-supervised pre-training for improving representation learning on downstream tasks. Existing works often utilize self-supervised pre-trained models by fine-tuning on downstream tasks. However, fine-tuning does not generalize to the case when one needs to build a customized model architecture different from the self-supervised model. In this work, we formulate a new knowledge distillation framework to transfer the knowledge from self-supervised pre-trained models to any other student network by a novel approach named Embedding Graph Alignment.…
University of Tübingen（蒂宾根大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；Tencent PCG（腾讯平台与内容事业群）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to transfer knowledge across heterogeneous modalities, even though these data modalities may not be semantically correlated. Rather than directly aligning the representations of different modalities, we compose audio, image, and video representations across modalities to uncover richer multi-modal knowledge. Our main idea is to learn a compositional embedding that closes the cross-modal semantic gap and captures the task…
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机科学与技术系（注：此处原机构为南京大学，具体实验室为 Novel Software Technology 重点实验室，按要求提取到大学级别））；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与技术学院）
We tackle the long-tailed visual recognition problem from the knowledge distillation perspective by proposing a Distill the Virtual Examples (DiVE) method. Specifically, by treating the predictions of a teacher model as virtual examples, we prove that distilling from these virtual examples is equivalent to label distribution learning under certain constraints. We show that when the virtual example distribution becomes flatter than the original input distribution, the under-represented tail classes will receive significant improvements, which is crucial in long-tailed recognition. The proposed …
Crowd counting aims to learn the crowd density distributions and estimate the number of objects (e.g. persons) in images. The perspective effect, which significantly influences the distribution of data points, plays an important role in crowd counting. In this paper, we propose a novel perspective-aware approach called PANet to address the perspective problem. Based on the observation that the size of the objects varies greatly in one image due to the perspective effect, we propose the dynamic receptive fields (DRF) framework. The framework is able to adjust the receptive field by the dilated …
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…
Xidian University（西安电子科技大学）；University of Sydney（悉尼大学）；Tencent AI Lab（腾讯人工智能实验室）
Due to the high storage and search efficiency, hashing has become prevalent for large-scale similarity search. Particularly, deep hashing methods have greatly improved the search performance under supervised scenarios. In contrast, unsupervised deep hashing models can hardly achieve satisfactory performance due to the lack of reliable supervisory similarity signals. To address this issue, we propose a novel deep unsupervised hashing model, dubbed DistillHash, which can learn a distilled data set consisted of data pairs, which have confidence similarity signals. Specifically, we investigate the…
University of Amsterdam（阿姆斯特丹大学）；Eindhoven University of Technology（埃因霍温理工大学）
What can neural networks learn about the visual world when provided with only a single image as input? While any image obviously cannot contain the multitudes of all existing objects, scenes and lighting conditions - within the space of all 256^(3x224x224) possible 224-sized square images, it might still provide a strong prior for natural images. To analyze this `augmented image prior' hypothesis, we develop a simple framework for training neural networks from scratch using a single image and augmentations using knowledge distillation from a supervised pretrained teacher. With this, we find th…
Distilling Vision Transformers for Distortion-Robust Representation Learning
Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Greece（希腊雅典国家与卡波迪斯蒂亚纳大学信息与电信系）；National Observatory of Athens, Greece（希腊雅典国家天文台）；Information Management Systems Institute, Athena Research Center, Greece（希腊阿提卡研究中心信息管理系统研究所）
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）
The University of Hong Kong（香港大学）；Tencent AI Lab（腾讯AI实验室）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Tencent Data Platform（腾讯数据平台）
Image virtual try-on aims to fit a garment image (target clothes) to a person image. Prior methods are heavily based on human parsing. However, slightly-wrong segmentation results would lead to unrealistic try-on images with large artifacts. Inaccurate parsing misleads parser-based methods to produce visually unrealistic results where artifacts usually occur. A recent pioneering work employed knowledge distillation to reduce the dependency of human parsing, where the try-on images produced by a parser-based method are used as supervisions to train a "student" network without relying on segment…
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）；Nanyang Technological University（南洋理工大学）
Visual attention not only improves the performance of image captioners, but also serves as a visual interpretation to qualitatively measure the caption rationality and model transparency. Specifically, we expect that a captioner can fix its attentive gaze on the correct objects while generating the corresponding words. This ability is also known as grounded image captioning. However, the grounding accuracy of existing captioners is far from satisfactory. To improve the grounding accuracy while retaining the captioning quality, it is expensive to collect the word-region alignment as strong supe…
Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill knowledge from one self-supervised ViT to another has not yet been explored. Moreover, the existing self-supervised knowledge distillation (SSKD) methods focus on ConvNet based architectures are suboptimal for ViT knowledge distillation. In this paper, we study knowledge distillation of self-supervised vision transformers (ViT-SSKD). We show that directly dist…
The Graduate Center, The City University of New York（纽约市立大学研究生中心）
Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods…
Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply supervised two-branch architecture, the Multimodal Attentional Translation Embeddings, where the visual features of each branch are driven by a multimodal attentional mechanism that exploits spatio-linguistic similarities in a low-dimensional space. We present a variety of experiments comparing against all related approaches in the literature, as well as by …
City University of Hong Kong（香港城市大学）；Microsoft Research Asia（微软亚洲研究院）
Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different images are pulled apart. In this paper, through visualizing and diagnosing classification errors, we observe that current contrastive models are ineffective at localizing the foreground object, limiting their ability to extract discriminative high-level features. This is due to the fact that view generation process considers pixels in an image uniformly. To addr…
Multi-Level Label Correction by Distilling Proximate Patterns for Semi-supervised Semantic Segmentation
Faculty of Electrical Engineering and Computer Science, Ningbo University（宁波大学电气工程与计算机科学学院）；Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences（中国科学院宁波材料技术与工程研究所）；Hangzhou Shenhao Technology Co., Ltd（杭州申昊科技股份有限公司）
The Hong Kong University of Science and Technology（香港科技大学）；Nanyang Technological University（南洋理工大学）；The Hong Kong University of Science and Technology Shenzhen Research Institute（香港科技大学深圳研究院）
Self-supervised learning has witnessed great progress in vision and NLP; recently, it also attracted much attention to various medical imaging modalities such as X-ray, CT, and MRI. Existing methods mostly focus on building new pretext self-supervision tasks such as reconstruction, orientation, and masking identification according to the properties of medical images. However, the publicly available self-supervision models are not fully exploited. In this paper, we present a powerful yet efficient self-supervision framework for surgical video understanding. Our key insight is to distill knowled…
Weakly-supervised temporal action localization (WTAL) learns to detect and classify action instances with only category labels. Most methods widely adopt the off-the-shelf Classification-Based Pre-training (CBP) to generate video features for action localization. However, the different optimization objectives between classification and localization, make temporally localized results suffer from the serious incomplete issue. To tackle this issue without additional annotations, this paper considers to distill free action knowledge from Vision-Language Pre-training (VLP), since we surprisingly ob…
Weakly-supervised audio-visual violence detection aims to distinguish snippets containing multimodal violence events with video-level labels. Many prior works perform audio-visual integration and interaction in an early or intermediate manner, yet overlooking the modality heterogeneousness over the weakly-supervised setting. In this paper, we analyze the modality asynchrony and undifferentiated instances phenomena of the multiple instance learning (MIL) procedure, and further investigate its negative impact on weakly-supervised audio-visual learning. To address these issues, we propose a modal…
Federal University of Rio Grande do Sul（南里奥格兰德联邦大学）
Weakly supervised object detection (WSOD) aims to tackle the object detection problem using only labeled image categories as supervision. A common approach used in WSOD to deal with the lack of localization information is Multiple Instance Learning, and in recent years methods started adopting Multiple Instance Detection Networks (MIDN), which allows training in an end-to-end fashion. In general, these methods work by selecting the best instance from a pool of candidates and then aggregating other instances based on similarity. In this work, we claim that carefully selecting the aggregation cr…
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）
Monocular depth estimation aims at estimating a pixelwise depth map for a single image, which has wide applications in scene understanding and autonomous driving. Existing supervised and unsupervised methods face great challenges. Supervised methods require large amounts of depth measurement data, which are generally difficult to obtain, while unsupervised methods are usually limited in estimation accuracy. Synthetic data generated by graphics engines provide a possible solution for collecting large amounts of depth data. However, the large domain gaps between synthetic and realistic data make…
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…
University of Electronic Science and Technology of China（电子科技大学）
The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous driving. This paper studies monocular VO from the perspective of Deep Learning (DL). Unlike most current learning-based methods, our approach, called DeepAVO, is established on the intuition that features contribute discriminately to different motion patterns. Specifically, we present a novel four-branch network to learn the rotation and translation by levera…
In recent years, generative adversarial networks (GANs) have been an actively studied topic and shown to successfully produce high-quality realistic images in various domains. The controllable synthesis ability of GAN generators suggests that they maintain informative, disentangled, and explainable image representations, but leveraging and transferring their representations to downstream tasks is largely unexplored. In this paper, we propose to distill knowledge from GAN generators by squeezing and spanning their representations. We squeeze the generator features into representations that are …
University of Surrey（萨里大学）；iFlyTek-Surrey Joint Research Centre on Artificial Intelligence（讯飞-萨里人工智能联合研究中心）
Visual text recognition is undoubtedly one of the most extensively researched topics in computer vision. Great progress have been made to date, with the latest models starting to focus on the more practical "in-the-wild" setting. However, a salient problem still hinders practical deployment -- prior arts mostly struggle with recognising unseen (or rarely seen) character sequences. In this paper, we put forward a novel framework to specifically tackle this "unseen" problem. Our framework is iterative in nature, in that it utilises predicted knowledge of character sequences from a previous itera…
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…
While fine-tuning pre-trained networks has become a popular way to train image segmentation models, such backbone networks for image segmentation are frequently pre-trained using image classification source datasets, e.g., ImageNet. Though image classification datasets could provide the backbone networks with rich visual features and discriminative ability, they are incapable of fully pre-training the target model (i.e., backbone+segmentation modules) in an end-to-end manner. The segmentation modules are left to random initialization in the fine-tuning process due to the lack of segmentation l…
Peking University（北京大学）；Tencent Medical AI Lab（腾讯医疗人工智能实验室）；Peng Cheng Laboratory（鹏城实验室）
Automatically generating radiology reports can improve current clinical practice in diagnostic radiology. On one hand, it can relieve radiologists from the heavy burden of report writing; On the other hand, it can remind radiologists of abnormalities and avoid the misdiagnosis and missed diagnosis. Yet, this task remains a challenging job for data-driven neural networks, due to the serious visual and textual data biases. To this end, we propose a Posterior-and-Prior Knowledge Exploring-and-Distilling approach (PPKED) to imitate the working patterns of radiologists, who will first examine the a…
DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features
NVIDIA Research（英伟达研究院）；University of Toronto（多伦多大学）；University of Southern California（南加州大学）；National University of Singapore（新加坡国立大学）；Stanford University（斯坦福大学）
We propose a semi-supervised learning framework for monocular depth estimation. Compared to existing semi-supervised learning methods, which inherit limitations of both sparse supervised and unsupervised loss functions, we achieve the complementary advantages of both loss functions, by building two separate network branches for each loss and distilling each other through the mutual distillation loss function. We also present to apply different data augmentation to each branch, which improves the robustness. We conduct experiments to demonstrate the effectiveness of our framework over the lates…
Distilling Specialized Orders for Visual Generation
Stony Brook University（石溪大学）；International Laboratory on Learning Systems (ILLS)（国际学习系统实验室（ILLS））；LIVIA, ÉTS Montréal（LIVIA，蒙特利尔高等技术学院）；Mila–Quebec AI Institute（米拉-魁北克人工智能研究所）；ServiceNow Research（ServiceNow研究院）；Université Paris-Saclay, CentraleSupélec（巴黎-萨克雷大学，中央理工-高等电力学院）；Polytechnique Montréal（蒙特利尔综合理工学院）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）
The underlying correlation between audio and visual modalities can be utilized to learn supervised information for unlabeled videos. In this paper, we propose an end-to-end self-supervised framework named Audio-Visual Contrastive Learning (AVCL), to learn discriminative audio-visual representations for action recognition. Specifically, we design an attention based multi-modal fusion module (AMFM) to fuse audio and visual modalities. To align heterogeneous audio-visual modalities, we construct a novel co-correlation guided representation alignment module (CGRA). To learn supervised information …
