Modern wearable devices can conveniently record various biosignals in the many different environments of daily living, enabling a rich view of individual health. However, not all biosignals are the same: high-fidelity biosignals, such as photoplethysmogram (PPG), contain more physiological information, but require optical sensors with a high power footprint. Alternatively, a lower-fidelity biosignal such as accelerometry has a significantly smaller power footprint and is available in almost any wearable device. While accelerometry is widely used for activity recognition and fitness, it is less explored for health biomarkers and diagnosis. Here, we show that an accelerometry foundation model can predict a wide variety of health targets. To achieve improved performance, we distill representational knowledge from PPG encoders to accelerometery encoders using 20 million minutes of unlabeled data, collected from ~172K participants in the Apple Heart and Movement Study under informed consent. We observe strong cross-modal alignment on unseen data, e.g., 99.2% top-1 accuracy for retrieving PPG embeddings from accelerometry embeddings. We show that distilled accelerometry encoders have significantly more informative representations compared to self-supervised or supervised encoders trained directly on accelerometry data, observed by at least 23%-49% improved performance for predicting heart rate and heart rate variability. We also show that distilled accelerometry encoders are readily predictive of a wide array of downstream health targets, i.e., they are generalist foundation models. We believe accelerometry foundation models for health may unlock new opportunities for developing digital biomarkers from any wearable device.
Decentralized Federated Learning (DFL) trains models in a collaborative and privacy-preserving manner while removing model centralization risks and improving communication bottlenecks. However, DFL faces challenges in efficient communication management and model aggregation within decentralized environments, especially with heterogeneous data distributions. Thus, this paper introduces ProFe, a novel communication optimization algorithm for DFL that combines knowledge distillation, prototype learning, and quantization techniques. ProFe utilizes knowledge from large local models to train smaller ones for aggregation, incorporates prototypes to better learn unseen classes, and applies quantization to reduce data transmitted during communication rounds. The performance of ProFe has been validated and compared to the literature by using benchmark datasets like MNIST, CIFAR10, and CIFAR100. Results showed that the proposed algorithm reduces communication costs by up to ~40-50% while maintaining or improving model performance. In addition, it adds ~20% training time due to increased complexity, generating a trade-off.
As a cornerstone of blockchain technology in the 3.0 era, smart contracts play a pivotal role in the evolution of blockchain systems. In order to address the limitations of existing smart contract vulnerability detection models with regard to their generalisation capability, an AF-STip smart contract vulnerability detection framework incorporating efficient knowledge migration is proposed. AF-STip employs the teacher network as the main model and migrates the knowledge processed by the smart contract to the student model using a data-free knowledge distillation method. The student model utilises this knowledge to enhance its vulnerability detection capabilities. The approach markedly enhances the model's capacity for feature extraction and cross-class adaptation, while concurrently reducing computational overhead.In order to further enhance the extraction of vulnerability features, an adaptive fusion module is proposed in this paper, which aims to strengthen the interaction and fusion of feature information.The experimental results demonstrate that the STip model attains an average F1 value detection score of 91.16% for the four vulnerabilities without disclosing the original smart contract data. To validate the viability of the proposed lightweight migration approach, the student model is deployed in a migration learning task targeting a novel vulnerability type, resulting in an accuracy of 91.02% and an F1 score of 90.46%. To the best of our knowledge, AF-STip is the inaugural model to apply data-free knowledge migration to smart contract vulnerability detection. While markedly reducing the computational overhead, the method still demonstrates exceptional performance in detecting novel vulnerabilities.
Data-free knowledge distillation transfers knowledge by recovering training data from a pre-trained model. Despite the recent success of seeking global data diversity, the diversity within each class and the similarity among different classes are largely overlooked, resulting in data homogeneity and limited performance. In this paper, we introduce a novel Relation-Guided Adversarial Learning method with triplet losses, which solves the homogeneity problem from two aspects. To be specific, our method aims to promote both intra-class diversity and inter-class confusion of the generated samples. To this end, we design two phases, an image synthesis phase and a student training phase. In the image synthesis phase, we construct an optimization process to push away samples with the same labels and pull close samples with different labels, leading to intra-class diversity and inter-class confusion, respectively. Then, in the student training phase, we perform an opposite optimization, which adversarially attempts to reduce the distance of samples of the same classes and enlarge the distance of samples of different classes. To mitigate the conflict of seeking high global diversity and keeping inter-class confusing, we propose a focal weighted sampling strategy by selecting the negative in the triplets unevenly within a finite range of distance. RGAL shows significant improvement over previous state-of-the-art methods in accuracy and data efficiency. Besides, RGAL can be inserted into state-of-the-art methods on various data-free knowledge transfer applications. Experiments on various benchmarks demonstrate the effectiveness and generalizability of our proposed method on various tasks, specially data-free knowledge distillation, data-free quantization, and non-exemplar incremental learning. Our code is available at https://github.com/Sharpiless/RGAL.
Existing Video Frame interpolation (VFI) models tend to suffer from time-to-location ambiguity when trained with video of non-uniform motions, such as accelerating, decelerating, and changing directions, which often yield blurred interpolated frames. In this paper, we propose (i) a novel motion description map, Bidirectional Motion field (BiM), to effectively describe non-uniform motions; (ii) a BiM-guided Flow Net (BiMFN) with Content-Aware Upsampling Network (CAUN) for precise optical flow estimation; and (iii) Knowledge Distillation for VFI-centric Flow supervision (KDVCF) to supervise the motion estimation of VFI model with VFI-centric teacher flows. The proposed VFI is called a Bidirectional Motion field-guided VFI (BiM-VFI) model. Extensive experiments show that our BiM-VFI model significantly surpasses the recent state-of-the-art VFI methods by 26% and 45% improvements in LPIPS and STLPIPS respectively, yielding interpolated frames with much fewer blurs at arbitrary time instances.
In the realm of novelty detection, accurately identifying outliers in data without specific class information poses a significant challenge. While current methods excel in single-object scenarios, they struggle with multi-object situations due to their focus on individual objects. Our paper suggests a novel approach: redefining `normal' at the object level in training datasets. Rather than the usual image-level view, we consider the most dominant object in a dataset as the norm, offering a perspective that is more effective for real-world scenarios. Adapting to our object-level definition of `normal', we modify knowledge distillation frameworks, where a student network learns from a pre-trained teacher network. Our first contribution, DeFeND(Dense Feature Fine-tuning on Normal Data), integrates dense feature fine-tuning into the distillation process, allowing the teacher network to focus on object-level features with a self-supervised loss. The second is masked knowledge distillation, where the student network works with partially hidden inputs, honing its ability to deduce and generalize from incomplete data. This approach not only fares well in single-object novelty detection but also considerably surpasses existing methods in multi-object contexts. The implementation is available at: https://github.com/SMSD75/Redefining_Normal_ACCV24/tree/main
Few-shot Class-Incremental Learning (FSCIL) addresses the challenges of evolving data distributions and the difficulty of data acquisition in real-world scenarios. To counteract the catastrophic forgetting typically encountered in FSCIL, knowledge distillation is employed as a way to maintain the knowledge from learned data distribution. Recognizing the limitations of generating discriminative feature representations in a few-shot context, our approach incorporates structural information between samples into knowledge distillation. This structural information serves as a remedy for the low quality of features. Diverging from traditional structured distillation methods that compute sample similarity, we introduce the Displacement Knowledge Distillation (DKD) method. DKD utilizes displacement rather than similarity between samples, incorporating both distance and angular information to significantly enhance the information density retained through knowledge distillation. Observing performance disparities in feature distribution between base and novel classes, we propose the Dual Distillation Network (DDNet). This network applies traditional knowledge distillation to base classes and DKD to novel classes, challenging the conventional integration of novel classes with base classes. Additionally, we implement an instance-aware sample selector during inference to dynamically adjust dual branch weights, thereby leveraging the complementary strengths of each approach. Extensive testing on three benchmarks demonstrates that DDNet achieves state-of-the-art results. Moreover, through rigorous experimentation and comparison, we establish the robustness and general applicability of our proposed DKD method.
Existing knowledge distillation (KD) methods have demonstrated their ability in achieving student network performance on par with their teachers. However, the knowledge gap between the teacher and student remains significant and may hinder the effectiveness of the distillation process. In this work, we introduce the structure of Neural Collapse (NC) into the KD framework. NC typically occurs in the final phase of training, resulting in a graceful geometric structure where the last-layer features form a simplex equiangular tight frame. Such phenomenon has improved the generalization of deep network training. We hypothesize that NC can also alleviate the knowledge gap in distillation, thereby enhancing student performance. This paper begins with an empirical analysis to bridge the connection between knowledge distillation and neural collapse. Through this analysis, we establish that transferring the teacher's NC structure to the student benefits the distillation process. Therefore, instead of merely transferring instance-level logits or features, as done by existing distillation methods, we encourage students to learn the teacher's NC structure. Thereby, we propose a new distillation paradigm termed Neural Collapse-inspired Knowledge Distillation (NCKD). Comprehensive experiments demonstrate that NCKD is simple yet effective, improving the generalization of all distilled student models and achieving state-of-the-art accuracy performance.
Offsite-tuning is a privacy-preserving method for tuning large language models (LLMs) by sharing a lossy compressed emulator from the LLM owners with data owners for downstream task tuning. This approach protects the privacy of both the model and data owners. However, current offsite tuning methods often suffer from adaptation degradation, high computational costs, and limited protection strength due to uniformly dropping LLM layers or relying on expensive knowledge distillation. To address these issues, we propose ScaleOT, a novel privacy-utility-scalable offsite-tuning framework that effectively balances privacy and utility. ScaleOT introduces a novel layerwise lossy compression algorithm that uses reinforcement learning to obtain the importance of each layer. It employs lightweight networks, termed harmonizers, to replace the raw LLM layers. By combining important original LLM layers and harmonizers in different ratios, ScaleOT generates emulators tailored for optimal performance with various model scales for enhanced privacy protection. Additionally, we present a rank reduction method to further compress the original LLM layers, significantly enhancing privacy with negligible impact on utility. Comprehensive experiments show that ScaleOT can achieve nearly lossless offsite tuning performance compared with full fine-tuning while obtaining better model privacy.
Multiple Choice Question Answering (MCQA) is an important problem with numerous real-world applications, such as medicine, law, and education. The high cost of building MCQA datasets makes few-shot learning pivotal in this domain. While Large Language Models (LLMs) can enable few-shot learning, their direct application in real-world scenarios is often hindered by their high computational cost. To address this challenge, we propose a simple yet effective approach that uses LLMs for data generation and scoring. Our approach utilizes LLMs to create MCQA data which contains questions and choices, and to assign probability scores to the generated choices. We then use the generated data and LLM-assigned scores to finetune a smaller and more efficient encoder-only model, DeBERTa-v3-base by leveraging distillation loss. Extensive experiments on the Massive Multitask Language Understanding (MMLU) benchmark demonstrate that our method improves accuracy from 28.9% to 39.3%, representing a gain of over 10% compared to a baseline finetuned directly on 5-shot examples. This shows the effectiveness of LLM-driven data generation and knowledge distillation for few-shot MCQA.
Knowledge distillation (KD) is a model compression technique that transfers knowledge from a large teacher model to a smaller student model to enhance its performance. Existing methods often assume that the student model is inherently inferior to the teacher model. However, we identify that the fundamental issue affecting student performance is the bias transferred by the teacher. Current KD frameworks transmit both right and wrong knowledge, introducing bias that misleads the student model. To address this issue, we propose a novel strategy to rectify bias and greatly improve the student model's performance. Our strategy involves three steps: First, we differentiate knowledge and design a bias elimination method to filter out biases, retaining only the right knowledge for the student model to learn. Next, we propose a bias rectification method to rectify the teacher model's wrong predictions, fundamentally addressing bias interference. The student model learns from both the right knowledge and the rectified biases, greatly improving its prediction accuracy. Additionally, we introduce a dynamic learning approach with a loss function that updates weights dynamically, allowing the student model to quickly learn right knowledge-based easy tasks initially and tackle hard tasks corresponding to biases later, greatly enhancing the student model's learning efficiency. To the best of our knowledge, this is the first strategy enabling the student model to surpass the teacher model. Experiments demonstrate that our strategy, as a plug-and-play module, is versatile across various mainstream KD frameworks. We will release our code after the paper is accepted.
With the rapid development of gravitational wave astronomy, the increasing number of detected events necessitates efficient methods for parameter estimation and model updates. This study presents a novel approach using knowledge distillation techniques to enhance computational efficiency in gravitational wave analysis. We develop a framework combining ResNet1D and Inverse Autoregressive Flow (IAF) architectures, where knowledge from a complex teacher model is transferred to a lighter student model. Our experimental results show that the student model achieves a validation loss of 3.70 with optimal configuration (40,100,0.75), compared to the teacher model's 4.09, while reducing the number of parameters by 43\%. The Jensen-Shannon divergence between teacher and student models remains below 0.0001 across network layers, indicating successful knowledge transfer. By optimizing ResNet layers (7-16) and hidden features (70-120), we achieve a 35\% reduction in inference time while maintaining parameter estimation accuracy. This work demonstrates significant improvements in computational efficiency for gravitational wave data analysis, providing valuable insights for real-time event processing.
This paper proposes small and efficient machine learning models (TinyML) for resource-constrained edge devices, specifically for on-device indoor localisation. Typical approaches for indoor localisation rely on centralised remote processing of data transmitted from lower powered devices such as wearables. However, there are several benefits for moving this to the edge device itself, including increased battery life, enhanced privacy, reduced latency and lowered operational costs, all of which are key for common applications such as health monitoring. The work focuses on model compression techniques, including quantization and knowledge distillation, to significantly reduce the model size while maintaining high predictive performance. We base our work on a large state-of-the-art transformer-based model and seek to deploy it within low-power MCUs. We also propose a state-space-based architecture using Mamba as a more compact alternative to the transformer. Our results show that the quantized transformer model performs well within a 64 KB RAM constraint, achieving an effective balance between model size and localisation precision. Additionally, the compact Mamba model has strong performance under even tighter constraints, such as a 32 KB of RAM, without the need for model compression, making it a viable option for more resource-limited environments. We demonstrate that, through our framework, it is feasible to deploy advanced indoor localisation models onto low-power MCUs with restricted memory limitations. The application of these TinyML models in healthcare has the potential to revolutionize patient monitoring by providing accurate, real-time location data while minimizing power consumption, increasing data privacy, improving latency and reducing infrastructure costs.
Knowledge distillation (KD) has been widely studied in unsupervised Industrial Image Anomaly Detection (AD), but its application to unsupervised multimodal AD remains underexplored. Existing KD-based methods for multimodal AD that use fused multimodal features to obtain teacher representations face challenges. Anomalies in one modality may not be effectively captured in the fused teacher features, leading to detection failures. Besides, these methods do not fully leverage the rich intra- and inter-modality information. In this paper, we propose Crossmodal Reverse Distillation (CRD) based on Multi-branch design to realize Multimodal Industrial AD. By assigning independent branches to each modality, our method enables finer detection of anomalies within each modality. Furthermore, we enhance the interaction between modalities during the distillation process by designing Crossmodal Filter and Amplifier. With the idea of crossmodal mapping, the student network is allowed to better learn normal features while anomalies in all modalities are ensured to be effectively detected. Experimental verifications on the MVTec 3D-AD dataset demonstrate that our method achieves state-of-the-art performance in multimodal anomaly detection and localization.
Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the state of the student during the distillation, adopting a fixed solution space that limits the capability of KD. Additionally, relying solely on L1-type loss struggles to leverage the distribution information of images. In this work, we propose a novel dynamic contrastive knowledge distillation (DCKD) framework for image restoration. Specifically, we introduce dynamic contrastive regularization to perceive the student's learning state and dynamically adjust the distilled solution space using contrastive learning. Additionally, we also propose a distribution mapping module to extract and align the pixel-level category distribution of the teacher and student models. Note that the proposed DCKD is a structure-agnostic distillation framework, which can adapt to different backbones and can be combined with methods that optimize upper-bound constraints to further enhance model performance. Extensive experiments demonstrate that DCKD significantly outperforms the state-of-the-art KD methods across various image restoration tasks and backbones.
Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to address all of these challenges by developing an extremely small and fast T2I model that generates high-resolution and high-quality images on mobile platforms. We propose several techniques to achieve this goal. First, we systematically examine the design choices of the network architecture to reduce model parameters and latency, while ensuring high-quality generation. Second, to further improve generation quality, we employ cross-architecture knowledge distillation from a much larger model, using a multi-level approach to guide the training of our model from scratch. Third, we enable a few-step generation by integrating adversarial guidance with knowledge distillation. For the first time, our model SnapGen, demonstrates the generation of 1024x1024 px images on a mobile device around 1.4 seconds. On ImageNet-1K, our model, with only 372M parameters, achieves an FID of 2.06 for 256x256 px generation. On T2I benchmarks (i.e., GenEval and DPG-Bench), our model with merely 379M parameters, surpasses large-scale models with billions of parameters at a significantly smaller size (e.g., 7x smaller than SDXL, 14x smaller than IF-XL).
Lifelong person re-identification (LReID) is an important but challenging task that suffers from catastrophic forgetting due to significant domain gaps between training steps. Existing LReID approaches typically rely on data replay and knowledge distillation to mitigate this issue. However, data replay methods compromise data privacy by storing historical exemplars, while knowledge distillation methods suffer from limited performance due to the cumulative forgetting of undistilled knowledge. To overcome these challenges, we propose a novel paradigm that models and rehearses the distribution of the old domains to enhance knowledge consolidation during the new data learning, possessing a strong anti-forgetting capacity without storing any exemplars. Specifically, we introduce an exemplar-free LReID method called Distribution Rehearsing via Adaptive Style Kernel Learning (DASK). DASK includes a Distribution Rehearser Learning (DRL) mechanism that learns to transform arbitrary distribution data into the current data style at each learning step. To enhance the style transfer capacity of DRL, an Adaptive Kernel Prediction Network (AKPNet) is explored to achieve an instance-specific distribution adjustment. Additionally, we design a Distribution Rehearsing-driven LReID Training (DRRT) module, which rehearses old distribution based on the new data via the old AKPNet model, achieving effective new-old knowledge accumulation under a joint knowledge consolidation scheme. Experimental results show our DASK outperforms the existing methods by 3.6%-6.8% and 4.5%-6.5% on anti-forgetting and generalization capacity, respectively. Our code is available at https://github.com/zhoujiahuan1991/AAAI2025-LReID-DASK
Knowledge distillation, where a small student model learns from a pre-trained large teacher model, has achieved substantial empirical success since the seminal work of \citep{hinton2015distilling}. Despite prior theoretical studies exploring the benefits of knowledge distillation, an important question remains unanswered: why does soft-label training from the teacher require significantly fewer neurons than directly training a small neural network with hard labels? To address this, we first present motivating experimental results using simple neural network models on a binary classification problem. These results demonstrate that soft-label training consistently outperforms hard-label training in accuracy, with the performance gap becoming more pronounced as the dataset becomes increasingly difficult to classify. We then substantiate these observations with a theoretical contribution based on two-layer neural network models. Specifically, we show that soft-label training using gradient descent requires only $O\left(\frac{1}{\gamma^2 \epsilon}\right)$ neurons to achieve a classification loss averaged over epochs smaller than some $\epsilon > 0$, where $\gamma$ is the separation margin of the limiting kernel. In contrast, hard-label training requires $O\left(\frac{1}{\gamma^4} \cdot \ln\left(\frac{1}{\epsilon}\right)\right)$ neurons, as derived from an adapted version of the gradient descent analysis in \citep{ji2020polylogarithmic}. This implies that when $\gamma \leq \epsilon$, i.e., when the dataset is challenging to classify, the neuron requirement for soft-label training can be significantly lower than that for hard-label training. Finally, we present experimental results on deep neural networks, further validating these theoretical findings.
Knowledge Distillation (KD) is essential in transferring dark knowledge from a large teacher to a small student network, such that the student can be much more efficient than the teacher but with comparable accuracy. Existing KD methods, however, rely on a large teacher trained specifically for the target task, which is both very inflexible and inefficient. In this paper, we argue that a SSL-pretrained model can effectively act as the teacher and its dark knowledge can be captured by the coordinate system or linear subspace where the features lie in. We then need only one forward pass of the teacher, and then tailor the coordinate system (TCS) for the student network. Our TCS method is teacher-free and applies to diverse architectures, works well for KD and practical few-shot learning, and allows cross-architecture distillation with large capacity gap. Experiments show that TCS achieves significantly higher accuracy than state-of-the-art KD methods, while only requiring roughly half of their training time and GPU memory costs.
Oil spills in the ocean pose severe environmental risks, making early detection essential. Synthetic aperture radar (SAR) based oil spill segmentation offers robust monitoring under various conditions but faces challenges due to the limited labeled data and inherent speckle noise in SAR imagery. To address these issues, we propose (i) a diffusion-based Data Augmentation and Knowledge Distillation (DAKD) pipeline and (ii) a novel SAR oil spill segmentation network, called SAROSS-Net. In our DAKD pipeline, we present a diffusion-based SAR-JointNet that learns to generate realistic SAR images and their labels for segmentation, by effectively modeling joint distribution with balancing two modalities. The DAKD pipeline augments the training dataset and distills knowledge from SAR-JointNet by utilizing generated soft labels (pixel-wise probability maps) to supervise our SAROSS-Net. The SAROSS-Net is designed to selectively transfer high-frequency features from noisy SAR images, by employing novel Context-Aware Feature Transfer blocks along skip connections. We demonstrate our SAR-JointNet can generate realistic SAR images and well-aligned segmentation labels, providing the augmented data to train SAROSS-Net with enhanced generalizability. Our SAROSS-Net trained with the DAKD pipeline significantly outperforms existing SAR oil spill segmentation methods with large margins.