The spectacular success of training large models on extensive datasets highlights the potential of scaling up for exceptional performance. To deploy these models on edge devices, knowledge distillation (KD) is commonly used to create a compact model from a larger, pretrained teacher model. However, as models and datasets rapidly scale up in practical applications, it is crucial to consider the applicability of existing KD approaches originally designed for limited-capacity architectures and small-scale datasets. In this paper, we revisit current KD methods and identify the presence of a small-data pitfall, where most modifications to vanilla KD prove ineffective on large-scale datasets. To guide the design of consistently effective KD methods across different data scales, we conduct a meticulous evaluation of the knowledge transfer process. Our findings reveal that incorporating more useful information is crucial for achieving consistently effective KD methods, while modifications in loss functions show relatively less significance. In light of this, we present a paradigmatic example that combines vanilla KD with deep supervision, incorporating additional information into the student during distillation. This approach surpasses almost all recent KD methods. We believe our study will offer valuable insights to guide the community in navigating beyond the small-data pitfall and toward consistently effective KD.

Recent advances in multimodal semantic segmentation show that incorporating auxiliary inputs—such as depth or thermal images—can significantly improve performance over single-modality (RGB-only) approaches. However, most existing solutions rely on parallel backbone networks and complex fusion modules, greatly increasing model size and computational demands. Inspired by prompt tuning in large language models, we introduce \textbf{MixPrompt}: a prompting-based framework that integrates auxiliary modalities into a pretrained RGB segmentation model without modifying its architecture. MixPrompt uses a lightweight prompting module to extract and fuse information from auxiliary inputs into the main RGB backbone. This module is initialized using the early layers of a pretrained RGB feature extractor, ensuring a strong starting point. At each backbone layer, MixPrompt aligns RGB and auxiliary features in multiple low-rank subspaces, maximizing information use with minimal parameter overhead. An information mixing scheme enables cross-subspace interaction for further performance gains. During training, only the prompting module and segmentation head are updated, keeping the RGB backbone frozen for parameter efficiency. Experiments across NYU Depth V2, SUN-RGBD, MFNet, and DELIVER datasets show that MixPrompt achieves improvements of 4.3, 1.1, 0.4, and 1.1 mIoU, respectively, over two-branch baselines, while using nearly half the parameters. MixPrompt also outperforms recent prompting-based methods under similar compute budgets.

The impressive performance of transformer models has sparked the deployment of intelligent applications on resource-constrained edge devices. However, ensuring high-quality service for real-time edge systems is a significant challenge due to the considerable computational demands and resource requirements of these models. Existing strategies typically either offload transformer computations to other devices or directly deploy compressed models on individual edge devices. These strategies, however, result in either considerable communication overhead or suboptimal trade-offs between accuracy and efficiency. To tackle these challenges, we propose a collaborative inference system for general transformer models, termed CoFormer. The central idea behind CoFormer is to exploit the divisibility and integrability of transformer. An off-the-shelf large transformer can be decomposed into multiple smaller models for distributed inference, and their intermediate results are aggregated to generate the final output. We formulate an optimization problem to minimize both inference latency and accuracy degradation under heterogeneous hardware constraints. DeBo algorithm is proposed to first solve the optimization problem to derive the decomposition policy, and then progressively calibrate decomposed models to restore performance. We demonstrate the capability to support a wide range of transformer models on heterogeneous edge devices, achieving up to 3.1× inference speedup with large transformer models. Notably, CoFormer enables the efficient inference of GPT2-XL with 1.6 billion parameters on edge devices, reducing memory requirements by 76.3%. CoFormer can also reduce energy consumption by approximately 40% while maintaining satisfactory inference performance.

Recent advancements in vision transformers (ViTs) have demonstrated that larger models often achieve superior performance. However, training these models remains computationally intensive and costly. To address this challenge, we introduce ScaleNet, an efficient approach for scaling ViT models. Unlike conventional training from scratch, ScaleNet facilitates rapid model expansion with negligible increases in parameters, building on existing pretrained models. This offers a cost-effective solution for scaling up ViTs. Specifically, ScaleNet achieves model expansion by inserting additional layers into pretrained ViTs, utilizing layer-wise weight sharing to maintain parameters efficiency. Each added layer shares its parameter tensor with a corresponding layer from the pretrained model. To mitigate potential performance degradation due to shared weights, ScaleNet introduces a small set of adjustment parameters for each layer. These adjustment parameters are implemented through parallel adapter modules, ensuring that each instance of the shared parameter tensor remains distinct and optimized for its specific function. Experiments on the ImageNet-1K dataset demonstrate that ScaleNet enables efficient expansion of ViT models. With a $2\times $ depth-scaled DeiT-Base model, ScaleNet achieves a 7.42% accuracy improvement over training from scratch while requiring only one-third of the training epochs, highlighting its efficiency in scaling ViTs. Beyond image classification, our method shows significant potential for application in downstream vision areas, as evidenced by the validation in object detection task.

Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended to not only comprehend but also seamlessly transit to out-of-domain tasks. However, current endeavors are hamstrung by an over-reliance on colossal models, exemplified by models with upwards of 3B parameters, and the necessity for an extensive corpus of visual data, often comprising a staggering 400B tokens. In this paper, we delve into the development of an efficient, autoregression-based vision model, innovatively architected to operate on a limited dataset. We meticulously demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding during the testing phase. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint, and a marked decrease in training data requirements, thereby paving the way for more sustainable and accessible advancements in the field of generalist vision models. The code is available at https://github.com/ggjy/DeLVM.

The recent advancements in cross-modal transformers have demonstrated their superior performance in RGB-D segmentation tasks by effectively integrating information from both RGB and depth modalities. However, existing methods often overlook the varying levels of informative content present in each modality, treating them equally and using models of the same architecture. This oversight can potentially hinder segmentation performance, especially considering that RGB images typically contain significantly more information than depth images. To address this issue, we propose PrimKD, a knowledge distillation based approach that focuses on guided multimodal fusion, with an emphasis on leveraging the primary RGB modality. In our approach, we utilize a model trained exclusively on the RGB modality as the teacher, guiding the learning process of a student model that fuses both RGB and depth modalities. To prioritize information from the primary RGB modality while leveraging the depth modality, we incorporate primary focused feature reconstruction and a selective alignment scheme. This integration enhances the overall freature fusion, resulting in improved segmentation results. We evaluate our proposed method on the NYU Depth V2 and SUN-RGBD datasets, and the experimental results demonstrate the effectiveness of PrimKD. Specifically, our approach achieves mIoU scores of 57.8 and 52.5 on these two datasets, respectively, surpassing existing counterparts by 1.5 and 0.4 mIoU. The code is available at https://github.com/xiaoshideta/PrimKD.

Recent years have witnessed the great success of vision transformer (ViT), which has achieved state-of-the-art performance on multiple computer vision benchmarks. However, ViT models suffer from vast amounts of parameters and high computation cost, leading to difficult deployment on resource-constrained edge devices. Existing solutions mostly compress ViT models to a compact model but still cannot achieve real-time inference. To tackle this issue, we propose to explore the divisibility of transformer structure, and decompose the large ViT into multiple small models for collaborative inference at edge devices. Our objective is to achieve fast and energy-efficient collaborative inference while maintaining comparable accuracy compared with large ViTs. To this end, we first propose a collaborative inference framework termedDeViTto facilitate edge deployment by decomposing large ViTs. Subsequently, we design a decomposition-and-ensemble algorithm based on knowledge distillation, termed DEKD, to fuse multiple small decomposed models while dramatically reducing communication overheads, and handle heterogeneous models by developing a feature matching module to promote the imitations of decomposed models from the large ViT. Extensive experiments for three representative ViT backbones on four widely-used datasets demonstrate our method achieves efficient collaborative inference for ViTs and outperforms existing lightweight ViTs, striking a good trade-off between efficiency and accuracy. For example, our DeViTs improves end-to-end latency by 2.89× with only 1.65% accuracy sacrifice using CIFAR-100 compared to the large ViT, ViT-L/16, on the GPU server. DeDeiTs surpasses the recent efficient ViT, MobileViT-S, by 3.54% in accuracy on ImageNet-1 K, while running 1.72× faster and requiring 55.28% lower energy consumption on the edge device.

The tremendous success of large models trained on extensive datasets demonstrates that scale is a key ingredient in achieving superior results. Therefore, the reflection on the rationality of designing knowledge distillation (KD) approaches for limited-capacity architectures solely based on small-scale datasets is now deemed imperative. In this paper, we identify the small data pitfall that presents in previous KD methods, which results in the underestimation of the power of vanilla KD framework on large-scale datasets such as ImageNet-1K. Specifically, we show that employing stronger data augmentation techniques and using larger datasets can directly decrease the gap between vanilla KD and other meticulously designed KD variants. This highlights the necessity of designing and evaluating KD approaches in the context of practical scenarios, casting off the limitations of small-scale datasets. Our investigation of the vanilla KD and its variants in more complex schemes, including stronger training strategies and different model capacities, demonstrates that vanilla KD is elegantly simple but astonishingly effective in large-scale scenarios. Without bells and whistles, we obtain state-of-the-art ResNet-50, ViT-S, and ConvNeXtV2-T models for ImageNet, which achieve 83.1%, 84.3%, and 85.0% top-1 accuracy, respectively. PyTorch code and checkpoints can be found at https://github.com/Hao840/vanillaKD.

Knowledge distillation (KD) has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. However, most existing distillation methods are designed under the assumption that the teacher and student models belong to the same model family, particularly the hint-based approaches. By using centered kernel alignment (CKA) to compare the learned features between heterogeneous teacher and student models, we observe significant feature divergence. This divergence illustrates the ineffectiveness of previous hint-based methods in cross-architecture distillation. To tackle the challenge in distilling heterogeneous models, we propose a simple yet effective one-for-all KD framework called OFA-KD, which significantly improves the distillation performance between heterogeneous architectures. Specifically, we project intermediate features into an aligned latent space such as the logits space, where architecture-specific information is discarded. Additionally, we introduce an adaptive target enhancement scheme to prevent the student from being disturbed by irrelevant information. Extensive experiments with various architectures, including CNN, Transformer, and MLP, demonstrate the superiority of our OFA-KD framework in enabling distillation between heterogeneous architectures. Specifically, when equipped with our OFA-KD, the student models achieve notable performance improvements, with a maximum gain of 8.0% on the CIFAR-100 dataset and 0.7% on the ImageNet-1K dataset. PyTorch code and checkpoints can be found at https://github.com/Hao840/OFAKD.

Recently, deploying deep neural network (DNN) models via collaborative inference, which splits a pre-trained model into two parts and executes them on user equipment (UE) and edge server respectively, becomes attractive. However, the large intermediate feature of DNN impedes flexible decoupling, and existing approaches either focus on the single UE scenario or simply define tasks considering the required CPU cycles, but ignore the indivisibility of a single DNN layer. In this article, we study the multi-agent collaborative inference scenario, where a single edge server coordinates the inference of multiple UEs. Our goal is to achieve fast and energy-efficient inference for all UEs. To achieve this goal, we design a lightweight autoencoder-based method to compress the large intermediate feature at first. Then we define tasks according to the inference overhead of DNNs and formulate the problem as a Markov decision process (MDP). Finally, we propose a multi-agent hybrid proximal policy optimization (MAHPPO) algorithm to solve the optimization problem with a hybrid action space. We conduct extensive experiments with different types of networks, and the results show that our method can reduce up to 56% of inference latency and save up to 72% of energy consumption.

In the past few years, transformers have achieved promising performance on various computer vision tasks. Unfortunately, the immense inference overhead of most existing vision transformers withholds them from being deployed on edge devices such as cell phones and smart watches. Knowledge distillation is a widely used paradigm for compressing cumbersome architectures into compact students via transferring information. However, most of them are designed for convolutional neural networks (CNNs), which do not fully investigate the character of vision transformers. In this paper, we fully utilize the patch-level information and propose a fine-grained manifold distillation method for transformer-based networks. Specifically, we train a tiny student model to match a pre-trained teacher model in the patch-level manifold space. Then, we decouple the manifold matching loss into three terms with careful design to further reduce the computational costs for the patch relationship. Equipped with the proposed method, a DeiT-Tiny model containing 5M parameters achieves 76.5\% top-1 accuracy on ImageNet-1k, which is +2.0\% higher than previous distillation approaches. Transfer learning results on other classification benchmarks and downstream vision tasks also demonstrate the superiority of our method over the state-of-the-art algorithms.

Recently, the compression and deployment of powerful deep neural networks (DNNs) on resource-limited edge devices to provide intelligent services have become attractive tasks. Although knowledge distillation (KD) is a feasible solution for compression, its requirement on the original dataset raises privacy concerns. In addition, it is common to integrate multiple pretrained models to achieve satisfactory performance. How to compress multiple models into a tiny model is challenging, especially when the original data are unavailable. To tackle this challenge, we propose a framework termed collaborative data-free knowledge distillation via multi-level feature sharing (CDFKD-MFS), which consists of a multi-header student module, an asymmetric adversarial data-free KD module, and an attention-based aggregation module. In this framework, the student model equipped with a multi-level feature-sharing structure learns from multiple teacher models and is trained together with a generator in an asymmetric adversarial manner. When some real samples are available, the attention module adaptively aggregates predictions of the student headers, which can further improve performance. We conduct extensive experiments on three popular computer visual datasets. In particular, compared with the most competitive alternative, the accuracy of the proposed framework is 1.18% higher on the CIFAR-100 dataset, 1.67% higher on the Caltech-101 dataset, and 2.99% higher on the mini-ImageNet dataset.

Model compression without the original data for fine-tuning is challenging for deploying large-size models on resource constrained edge devices. To this end, we propose a novel data-free model compression framework based on knowledge distillation (KD), where multiple teachers are utilized in a collaborative manner to enable reliable distillation. It mainly consists of three components: adversarial data generation, multi-teacher KD, and adaptive outputs aggregation. In particular, some synthesized data are generated in an adversarial manner to mimic the original data for model compression. Then a multi-header module is developed to simultaneously leverage diverse knowledge from multiple teachers. The distillation outputs are adaptively aggregated for final prediction. The experimental results demonstrate that our framework outperforms the data-free counterpart significantly (4.48% on MNIST and 2.96% on CIFAR-10). Effectiveness of different components of our method is also verified via carefully designed ablation study.

Recent advances in deep learning bring impressive performance for multimedia applications. Hence, compressing and deploying these applications on resource-limited edge devices via model compression becomes attractive. Knowledge distillation (KD) is one of the most popular model compression techniques. However, most well-behaved KD approaches require the original dataset, which is usually unavailable due to privacy issues, while existing data-free KD methods perform much worse than data-required counterparts. In this paper, we analyze previous data-free KD methods from the data perspective and point out that using a single pre-trained model limits the performance of these approaches. We then propose a Data-Free Ensemble knowledge Distillation (DFED) framework, which contains a student network, a generator network, and multiple pre-trained teacher networks. During training, the student mimics behaviors of the ensemble of teachers using samples synthesized by a generator, which aims to enlarge the prediction discrepancy between the student and teachers. A moment matching loss term assists the generator training by minimizing the distance between activations of synthesized samples and real samples. We evaluate DFED on three popular image classification datasets. Results demonstrate that our method achieves significant performance improvements compared with previous works. We also design an ablation study to verify the effectiveness of each component of the proposed framework.