Parameter-Free Logit Distillation via Sorting Mechanism

Deep architecture can improve performance of neural networks whereas it increases the computational complexity. Compressing networks is the key to solve this problem. The framework Knowledge Distilling (KD) compresses cumbersome networks well. It improved mimic learning, enabling knowledge to be transferred from cumbersome networks to compressed networks without constraint of architectures. Inspired by AlphaGo Zero, this paper proposed an algorithm combining KD with reinforcement learning to compress networks on changing datasets. In this algorithm, the compressed networks interact with the environment made by KD to produce datasets that are appropriate w.r.t the model. Monte Carlo Tree Search (MCTS) of AlphaGo Zero is used to produce the datasets by making a trade-off between the prediction of compressed networks and the knowledge. In experiments, the algorithm proved to be effective in compressing networks by training ResNet on CIFAR datasets, with mean squared error as the object function.

Knowledge distillation has been used to transfer knowledge learned by a sophisticated model (teacher) to a simpler model (student). This technique is widely used to compress model complexity. However, in most applications the compressed student model suffers from an accuracy gap with its teacher. We propose extracurricular learning, a novel knowledge distillation method, that bridges this gap by (1) modeling student and teacher output distributions; (2) sampling examples from an approximation to the underlying data distribution; and (3) matching student and teacher output distributions over this extended set including uncertain samples. We conduct rigorous evaluations on regression and classification tasks and show that compared to the standard knowledge distillation, extracurricular learning reduces the gap by 46% to 68%. This leads to major accuracy improvements compared to the empirical risk minimization-based training for various recent neural network architectures: 16% regression error reduction on the MPIIGaze dataset, +3.4% to +9.1% improvement in top-1 classification accuracy on the CIFAR100 dataset, and +2.9% top-1 improvement on the ImageNet dataset.

Breast cancer is the most common invasive cancer in women and the second main cause of cancer death in females, which can be classified benign or malignant. Research and prevention on breast cancer have attracted more concern of researchers in recent years. On the other hand, the development of data mining methods provides an effective way to extract more useful information from complex databases, and some prediction, classification, and clustering can be made according to the extracted information. The generic notion of knowledge distillation is that a network of higher capacity acts as a teacher and a network of lower capacity acts as a student. There are different pipelines of knowledge distillation known. However, previous work on knowledge distillation using label smoothing regularization produces experiments and results that break this general notion and prove that knowledge distillation also works when a student model distils a teacher model, i.e., reverse knowledge distillation. Not only this, but it is also proved that a poorly trained teacher model trains a student model to reach equivalent results. Building on the ideas from those works, we propose a novel bilateral knowledge distillation regime that enables multiple interactions between teacher and student models, i.e., teaching and distilling each other, eventually improving each other's performance and evaluating our results on BACH histopathology image dataset on breast cancer. The pretrained ResNeXt29 and MobileNetV2 models which are already tested on ImageNet dataset are used for “transfer learning” in our dataset, and we obtain a final accuracy of more than 96% using this novel approach of bilateral KD.

Knowledge distillation is a widely used neural network model compression technique. In general, the knowledge distillation transfer the knowledge from a large pre-trained teacher network with superior performance to a small student network enables the student network to achieve better performance. This paper proposes a triplet knowledge distillation framework (abbreviated as TKD), which introduces a smaller assistant network into the knowledge distillation structure. The performance of the assistant network is lower than that of the student network. During the training of the TKD, by minimizing the Mean Squared Error(MSE) loss function, the output of the student network will closer to the output of the teacher network and further from that of the assistant network. Therefore, the student network can learn more expressive knowledge from the teacher network while throwing away mistaken knowledge in the assistant network. Finally, the student network achieves a surprising performance even superior to the teacher network. We have demonstrated the effectiveness of TKD by extensive experiments on benchmark datasets(CIFAR-10, CIFAR-100, SVHN, STL-10). When using VGGNet as an experimental model, the student network VGGNet13 achieving 94.29%, 75.30%, 95.53%, and 87.61% accuracy on the CIFAR-10, CIFAR-100, SVHN, and STL-10 datasets, improved by 1.24%, 2.81%, 0.40%, and 2.32%, respectively.

Explainability-based knowledge distillation

Knowledge distillation aims to distill knowledge from teacher networks to train student networks. Distilling intermediate features has attracted much attention in recent years as it can be flexibly applied in various fields such as image classification, object detection and semantic segmentation. A critical obstacle of feature-based knowledge distillation is the dimension gap between the intermediate features of teacher and student, and plenty of methods have been proposed to resolve this problem. However, these works usually implement feature uniformization in an unsupervised way, lacking guidance to help the student network learn meaningful mapping functions in the uniformization process. Moreover, the dimension uniformization process of the student and teacher network is usually not equivalent as the mapping functions are different. To this end, some factors of the feature are discarded during parametric feature alignment, or some factors are blended in some non-parametric operations. In this paper, we propose a novel semantic-aware knowledge distillation scheme to solve these problems. We build a standalone feature-based classification branch to extract semantic-aware knowledge for better guiding the learning process of the student network. In addition, to avoid the inequivalence of feature uniformization between teacher and student, we design a novel parameter-free self-attention operation that can convert features of different dimensions into vectors of the same length. Experimental results show that the proposed knowledge distillation scheme outperforms existing feature-based distillation methods on the widely used CIFAR-100 and CINIC-10 datasets.

Improving adversarial robustness using knowledge distillation guided by attention information bottleneck

Logit-based knowledge distillation (KD) is commonly used to mitigate catastrophic forgetting in class-incremental learning (CIL) caused by data distribution shifts. However, the strict match of logit values between student and teacher models conflicts with the cross-entropy (CE) loss objective of learning new classes, leading to significant recency bias (i.e. unfairness). To address this issue, we rethink the overlooked limitations of KD-based methods through empirical analysis. Inspired by our findings, we introduce a plug-and-play pre-process method that normalizes the logits of both the student and teacher across all classes, rather than just the old classes, before distillation. This approach allows the student to focus on both old and new classes, capturing intrinsic inter-class relations from the teacher. By doing so, our method avoids the inherent conflict between KD and CE, maintaining fairness between old and new classes. Additionally, recognizing that overconfident teacher predictions can hinder the transfer of inter-class relations (i.e., dark knowledge), we extend our method to capture intra-class relations among different instances, ensuring fairness within old classes. Our method integrates seamlessly with existing logit-based KD approaches, consistently enhancing their performance across multiple CIL benchmarks without incurring additional training costs.

Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones. Although great success has been achieved by prior distillation methods via delicately designing various types of knowledge, they overlook the functional properties of neural networks, which makes the process of applying those techniques to new tasks unreliable and non-trivial. To alleviate such problem, in this paper, we initially leverage Lipschitz continuity to better represent the functional characteristic of neural networks and guide the knowledge distillation process. In particular, we propose a novel Lipschitz Continuity Guided Knowledge Distillation framework to faithfully distill knowledge by minimizing the distance between two neural networks’ Lipschitz constants, which enables teacher networks to better regularize student networks and improve the corresponding performance. We derive an explainable approximation algorithm with an explicit theoretical derivation to address the NP-hard problem of calculating the Lipschitz constant. Experimental results have shown that our method outperforms other benchmarks over several knowledge distillation tasks (e.g., classification, segmentation and object detection) on CIFAR-100, ImageNet, and PASCAL VOC datasets. Our code is available at https://github.com/42Shawn/LONDON/tree/master.

With the rapid development of artificial intelligence and computer vision, feature point detection algorithms have emerged as a significant area of research, particularly in applications such as SLAM (Simultaneous Localization and Mapping) and image registration. However, the FAST (Features from Accelerated Segment Test) detection method employed in the ORB (Oriented FAST and Rotated BRIEF) algorithm exhibits limitations in detection accuracy. This paper proposes a feature point detection method based on sequential neural networks and knowledge distillation, aiming to enhance the performance of the FAST algorithm. Firstly, the sequential nature of the data points in the FAST algorithm is analyzed, leading to the development of a binary classification and regression model using a sequential neural network. Considering the significant computational overhead of the model, knowledge distillation techniques are introduced to optimize the efficiency of the neural network. Secondly, the constructed model undergoes performance testing and evaluation, with a detailed comparison against the traditional FAST method. Finally, this paper discusses the future prospects of feature point detection, suggesting potential directions for further optimization.

Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher network. Some recent works introduce multi-teacher distillation to provide more supervision to the student network. However, the effectiveness of multi-teacher distillation methods are accompanied by costly computation resources. To tackle with both the efficiency and the effectiveness of knowledge distillation, we introduce the feature aggregation to imitate the multi-teacher distillation in the single-teacher distillation framework by extracting informative supervision from multiple teacher feature maps. Specifically, we introduce DFA, a two-stage Differentiable Feature Aggregation search method that motivated by DARTS in neural architecture search, to efficiently find the aggregations. In the first stage, DFA formulates the searching problem as a bi-level optimization and leverages a novel bridge loss, which consists of a student-to-teacher path and a teacher-to-student path, to find appropriate feature aggregations. The two paths act as two players against each other, trying to optimize the unified architecture parameters to the opposite directions while guaranteeing both expressivity and learnability of the feature aggregation simultaneously. In the second stage, DFA performs knowledge distillation with the derived feature aggregation. Experimental results show that DFA outperforms existing distillation methods on CIFAR-100 and CINIC-10 datasets under various teacher-student settings, verifying the effectiveness and robustness of the design.KeywordsKnowledge distillationFeature aggregationDifferentiable architecture search

Enhancing marine oil spill detection through dynamic adaptive knowledge distillation with spectral mask superpixel.

Knowledge distillation is a representative technique for model compression and acceleration, which is important for deploying neural networks on resource limited devices. The knowledge transferred from teacher to student is the mapping of teacher model, or represented by all the input-output pairs. However, in practice the student model only learns from data pairs of the dataset that may be biased, and we think this limits the performance of knowledge distillation. In this paper, we first quantitatively define the uniformity of the sampled data for training, providing a unified view for methods that learn from biased data. Then we evaluate the uniformity on real world dataset and show that existing methods actually improve the uniformity of data. We further introduce two uniformity-oriented methods for rectifying the bias of data for knowledge distillation. Extensive experiments conducted on Face Recognition and Person Re-identification have shown the effectiveness of our method. Moreover, we analyze the sampled data on Face Recognition and show that better balance is achieved between races and between easy and hard samples. And this effect can be also confirmed in training the student model from scratch, resulting in a comparable performance with standard knowledge distillation.

Robust knowledge distillation based on feature variance against backdoored teacher model

In our modern world, smart devices, e.g., mobile phones, IoT devices, have become the norm, leading to a vast increase in demand for a smart-ecosystem. Among other technologies that are being researched and applied, there is a trend of embedding Artificial Intelligence modules on these devices. One of the most challenging problems for embedding on smart devices is maintaining good accuracy while reducing the computational cost and speed. State-of-the-art Deep Convolution Neural Networks cannot run on smart devices due to a lack of resources. The need to find such a model is the motivation for our proposal of a lightweight network for landmark recognition using knowledge distillation. Our purpose is not to create a network with higher accuracy; instead, we try to devise a fast and light neural network while keeping approximately similar accuracy of SOTA models by utilizing knowledge distillation. Our proposed student model achieves a decent result with 7.33% accuracy lower than the teacher SOTA model (91.8%), while decreases the processing time by 73.04%. Our experimental results show promising potential for further explorations and research in knowledge distillation. We have also collected a dataset for Vietnam landmarks for our experiments. This data can be used to train a similar network for Vietnam landmarks recognition or other related purposes.