Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image Segmentation
Imperial College London（帝国理工学院）；National University of Singapore（新加坡国立大学）；National Institute of Technology Tiruchirappalli（蒂鲁吉拉伯利国家理工学院）；The Chinese University of Hong Kong（香港中文大学）；Shun Hing Institute of Advanced Engineering（信兴高等工程研究所）
Mobarakol Islam, Lalithkumar Seenivasan, S. P. Sharan, V. K. Viekash, Bhavesh Gupta, Ben Glocker, Hongliang Ren
Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods heavily rely on the ability to score the difficulty of data samples, an optimal scoring function is still under exploration. Methodology: Distillation is a knowledge transfer approach where a teacher network guides a student network by feeding a sequence of random samples. We argue that guiding student networks with an efficient curriculum strategy can improve model generalization and robustness. For this purpose, we design an uncertainty-based paced curriculum learning in self distillation for medical image segmentation. We fuse the prediction uncertainty and annotation boundary uncertainty to develop a novel paced-curriculum distillation (PCD). We utilize the teacher model to obtain prediction uncertainty and spatially varying label smoothing with Gaussian kernel to generate segmentation boundary uncertainty from the annotation. We also investigate the robustness of our method by applying various types and severity of image perturbation and corruption. Results: The proposed technique is validated on two medical datasets of breast ultrasound image segmentation and robotassisted surgical scene segmentation and achieved significantly better performance in terms of segmentation and robustness. Conclusion: P-CD improves the performance and obtains better generalization and robustness over the dataset shift. While curriculum learning requires extensive tuning of hyper-parameters for pacing function, the level of performance improvement suppresses this limitation.
National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong（香港中文大学）；National University of Singapore (Suzhou) Research Institute（新加坡国立大学苏州研究院）；Imperial College London（帝国理工学院）
Curriculum learning and self-paced learning are the training strategies that gradually feed the samples from easy to more complex. They have captivated increasing attention due to their excellent performance in robotic vision. Most recent works focus on designing curricula based on difficulty levels in input samples or smoothing the feature maps. However, smoothing labels to control the learning utility in a curriculum manner is still unexplored. In this work, we design a paced curriculum by label smoothing (P-CBLS) using paced learning with uniform label smoothing (ULS) for classification tas…
School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）
Weakly-supervised object detection (WOD) is a challenging problems in computer vision. The key problem is to simultaneously infer the exact object locations in the training images and train the object detectors, given only the training images with weak image-level labels. Intuitively, by simulating the selective attention mechanism of human visual system, saliency detection technique can select attractive objects in scenes and thus is a potential way to provide useful priors for WOD. However, the way to adopt saliency detection in WOD is not trivial since the detected saliency region might be …
University of Bucharest（布加勒斯特大学）；University of Trento（特伦托大学）；Romanian Young Academy（罗马尼亚青年科学院）；SecurifAI
Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object detection results in the cross-domain setting, e.g. by translating images with ground-truth labels from the source domain to the target domain using Cycle-GAN. On top of combining Cycle-GAN transformations and self-paced learning in a smart and efficient way, in this paper, we propose a novel self-paced algorithm that learns from easy to hard. Our method is simple …
Intel Corporation（英特尔公司）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
We propose to learn a curriculum or a syllabus for supervised learning and deep reinforcement learning with deep neural networks by an attachable deep neural network, called ScreenerNet. Specifically, we learn a weight for each sample by jointly training the ScreenerNet and the main network in an end-to-end self-paced fashion. The ScreenerNet neither has sampling bias nor requires to remember the past learning history. We show the networks augmented with the ScreenerNet achieve early convergence with better accuracy than the state-of-the-art curricular learning methods in extensive experiments…
Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Wuhan University（国家多媒体软件工程研究中心、人工智能研究院、计算机科学学院、武汉大学）；Hubei Key Laboratory of Multimedia and Network Communication Engineering（湖北省多媒体与网络通信工程重点实验室）；Zhongguancun Academy, Beijing, China（中关村学院，北京，中国）；School of Computer Science, Wuhan University, Wuhan, China（武汉大学计算机科学学院，武汉，中国）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）
University of Science and Technology of China（中国科学技术大学）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）
Self-paced curriculum learning (SCL) has demonstrated its great potential in computer vision, natural language processing, etc. During training, it implements easy-to-hard sampling based on online estimation of data difficulty. Most SCL methods commonly adopt a loss-based strategy of estimating data difficulty and deweighting the `hard' samples in the early training stage. While achieving success in a variety of applications, SCL stills confront two challenges in a medical image analysis task, such as universal lesion detection, featuring insufficient and highly class-imbalanced data: (i) the …
Dual Teacher-Student Learning for Semi-supervised Medical Image Segmentation
Center for Applied Mathematics, Tianjin University（应用数学中心，天津大学）；Department of Radiology, Tianjin Hospital of Tianjin University（放射科，天津大学医院）；Department of Hip Trauma, Tianjin Hospital of Tianjin University（骨科创伤科，天津大学医院）
CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；Peng Cheng Laboratory (PCL)（鹏城实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
Adaptive Mix for Semi-Supervised Medical Image Segmentation
School of Computer Science and Engineering, Northeastern University（计算机科学与工程学院，东北大学）；Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education（医学图像智能计算重点实验室，教育部）；Alberta Machine Intelligence Institute, University of Alberta（阿尔伯塔人工智能研究所，阿尔伯塔大学）
Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls the discrepancy between two distributions and can faithfully determine the difficulty level of the distillation task. Keeping a constant temperature, i.e., a fixed level of task difficulty, is usually sub-optimal for a growing student during its progressive learning stages. In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledg…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）；Aberystwyth University（阿伯里斯特威斯大学）
In real-world scenarios, data tends to exhibit a long-tailed distribution, which increases the difficulty of training deep networks. In this paper, we propose a novel self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME). Our method is inspired by the observation that networks trained on less imbalanced subsets of the distribution often yield better performances than their jointly-trained counterparts. We refer to these models as 'Experts', and the proposed LFME framework aggregates the knowledge from multiple 'Experts' to learn a unified student model. Spec…
Shenzhen University of Advanced Technology（深圳先进技术大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Xi’an Jiaotong University（西安交通大学）
University of Trento（特伦托大学）；INRIA（法国国家信息与自动化研究所）；Columbia University（哥伦比亚大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
In this paper we address the problem of learning robust cross-domain representations for sketch-based image retrieval (SBIR). While most SBIR approaches focus on extracting low- and mid-level descriptors for direct feature matching, recent works have shown the benefit of learning coupled feature representations to describe data from two related sources. However, cross-domain representation learning methods are typically cast into non-convex minimization problems that are difficult to optimize, leading to unsatisfactory performance. Inspired by self-paced learning, a learning methodology design…
University of Electronic Science and Technology of China（电子科技大学）；Tsinghua University（清华大学）；Sichuan University（四川大学）；University of Florida（佛罗里达大学）
Noisy labels composed of correct and corrupted ones are pervasive in practice. They might significantly deteriorate the performance of convolutional neural networks (CNNs), because CNNs are easily overfitted on corrupted labels. To address this issue, inspired by an observation, deep neural networks might first memorize the probably correct-label data and then corrupt-label samples, we propose a novel yet simple self-paced resistance framework to resist corrupted labels, without using any clean validation data. The proposed framework first utilizes the memorization effect of CNNs to learn a cu…
Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration
School of Computer Science, Peking University, Beijing, China（北京大学计算机科学系）；Center for Health Informatics, Australian Institute of Health Innovation, Macquarie University, Sydney, NSW 2113, Australia（健康信息学中心，澳大利亚健康创新研究所，麦考利大学，悉尼，NSW 2113，澳大利亚）；School of Data Science, University of Virginia, Charlottesville, VA, USA（数据科学学院，弗吉尼亚大学，夏洛特维尔，VA，美国）
Knowledge distillation (KD) is an effective tool for compressing deep classification models for edge devices. However, the performance of KD is affected by the large capacity gap between the teacher and student networks. Recent methods have resorted to a multiple teacher assistant (TA) setting for KD, which sequentially decreases the size of the teacher model to relatively bridge the size gap between these models. This paper proposes a new technique called Curriculum Expert Selection for Knowledge Distillation (CES-KD) to efficiently enhance the learning of a compact student under the capacity…
Sun Yat-sen University（中山大学）；Harbin Institute of Technology（哈尔滨工业大学）；The Hong Kong Polytechnic University（香港理工大学）
This paper aims to develop a novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals. By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert re-certification. We first initialize the classifier using a few annotated samples for each individual, and extract image features using the convolutional neural nets. Then, a…
See Further When Clear: Curriculum Consistency Model
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；SenseTime Research（商汤科技研究院）
Recently, distillation approaches are suggested to extract general knowledge from a teacher network to guide a student network. Most of the existing methods transfer knowledge from the teacher network to the student via feeding the sequence of random mini-batches sampled uniformly from the data. Instead, we argue that the compact student network should be guided gradually using samples ordered in a meaningful sequence. Thus, it can bridge the gap of feature representation between the teacher and student network step by step. In this work, we provide a curriculum learning knowledge distillation…
Universitat Pompeu Fabra（庞培法布拉大学）；ICREA（加泰罗尼亚高级研究学院）；Ecole Centrale de Nantes（南特中央理工学院）；Technische Universität München（慕尼黑工业大学）；LMU München（慕尼黑大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
An adequate classification of proximal femur fractures from X-ray images is crucial for the treatment choice and the patients' clinical outcome. We rely on the commonly used AO system, which describes a hierarchical knowledge tree classifying the images into types and subtypes according to the fracture's location and complexity. In this paper, we propose a method for the automatic classification of proximal femur fractures into 3 and 7 AO classes based on a Convolutional Neural Network (CNN). As it is known, CNNs need large and representative datasets with reliable labels, which are hard to co…
Answering from Sure to Uncertain: Uncertainty-Aware Curriculum Learning for Video Question Answering
School of Computing and Information Systems, The University of Melbourne（墨尔本大学计算与信息系统学院）；Computer Science & Software Engineering, University of Western Australia（西澳大学计算机科学与软件工程系）；School of Computing and Communications, Lancaster University（兰卡斯特大学计算与通讯学院）；Department of Data Science & AI, Monash University（莫纳什大学数据科学与人工智能系）
Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
The Laboratory of Intelligent Collaborative Computing of UESTC, Chengdu, China（UESTC智能协同计算实验室，中国成都）；Monash University, Melbourne, Australia（墨尔本大学，澳大利亚墨尔本）；Guangdong Laboratory of Artificial Intelligence（广东人工智能实验室）
Preview-based Category Contrastive Learning for Knowledge Distillation
School of Computer Science and Technology, Shandong University（山东大学计算机科学与技术学院）；School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）计算机科学与技术学院）；School of Software, Shandong University（山东大学软件学院）；Alibaba Group（阿里巴巴集团）
