We present V2M4, a novel 4D reconstruction method that directly generates a usable 4D mesh animation asset from a single monocular video. Unlike existing approaches that rely on priors from multi-view image and video generation models, our method is based on native 3D mesh generation models. Naively applying 3D mesh generation models to generate a mesh for each frame in a 4D task can lead to issues such as incorrect mesh poses, misalignment of mesh appearance, and inconsistencies in mesh geometry and texture maps. To address these problems, we propose a structured workflow that includes camera search and mesh reposing, condition embedding optimization for mesh appearance refinement, pairwise mesh registration for topology consistency, and global texture map optimization for texture consistency. Our method outputs high-quality 4D animated assets that are compatible with mainstream graphics and game software. Experimental results across a variety of animation types and motion amplitudes demonstrate the generalization and effectiveness of our method. Project page: https://windvchen.github.io/V2M4/.

Recent advancements in human motion synthesis have focused on specific types of motions, such as human-scene interaction, locomotion or human-human interaction, however, there is a lack of a unified system capable of generating a diverse combination of motion types. In response, we introduce *Sitcom-Crafter*, a comprehensive and extendable system for human motion generation in 3D space, which can be guided by extensive plot contexts to enhance workflow efficiency for anime and game designers. The system is comprised of eight modules, three of which are dedicated to motion generation, while the remaining five are augmentation modules that ensure consistent fusion of motion sequences and system functionality. Central to the generation modules is our novel 3D scene-aware human-human interaction module, which addresses collision issues by synthesizing implicit 3D Signed Distance Function (SDF) points around motion spaces, thereby minimizing human-scene collisions without additional data collection costs. Complementing this, our locomotion and human-scene interaction modules leverage existing methods to enrich the system's motion generation capabilities. Augmentation modules encompass plot comprehension for command generation, motion synchronization for seamless integration of different motion types, hand pose retrieval to enhance motion realism, motion collision revision to prevent human collisions, and 3D retargeting to ensure visual fidelity. Experimental evaluations validate the system's ability to generate high-quality, diverse, and physically realistic motions, underscoring its potential for advancing creative workflows. Code and demonstration videos can be found in the supplementary files.

Most anomaly detection (AD) methods adopt an unsupervised approach, relying exclusively on normal samples during training, which limits the model’s discriminative ability. In real world scenarios, only small amounts of anomaly data are typically available, which can still provide valuable insights for model learning. However, supervised anomaly detection methods may be impacted by the scarcity of anomaly samples, leading to significant overlap in the feature distributions of normal and anomaly samples, thereby degrading overall performance. To address this, we propose a distribution-transformed supervised anomaly detection method (DTAD). This method employs a two-stage distribution transformation to progressively reduce the overlap between normal and anomaly distributions, thereby enhancing the model’s discriminative performance. In the first stage, residual calculation is used to initially separate normal and abnormal distributions, with an attention network highlighting critical feature contributions. In the second stage, a contrastive loss function (semi-push-pull loss) is employed to expand the decision boundary between normal and abnormal samples, further improving distribution separation. On the benchmark datasets MVTecAD, AITEX, ELPV, and BrainMRI, our method outperforms recent state-of-the-art approaches, demonstrating its effectiveness.

Many existing adversarial attacks generate -norm perturbations on image RGB space. Despite some achievements in transferability and attack success rate, the crafted adversarial examples are easily perceived by human eyes. Towards visual imperceptibility, some recent works explore unrestricted attacks without -norm constraints, yet lacking transferability of attacking black-box models. In this work, we propose a novel imperceptible and transferable attack by leveraging both the generative and discriminative power of diffusion models. Specifically, instead of direct manipulation in pixel space, we craft perturbations in the latent space of diffusion models. Combined with well-designed content-preserving structures, we can generate human-insensitive perturbations embedded with semantic clues. For better transferability, we further "deceive" the diffusion model which can be viewed as an implicit recognition surrogate, by distracting its attention away from the target regions. To our knowledge, our proposed method, DiffAttack, is the first that introduces diffusion models into the adversarial attack field. Extensive experiments conducted across diverse model architectures (CNNs, Transformers, and MLPs), datasets (ImageNet, CUB-200, and Standford Cars), and defense mechanisms underscore the superiority of our attack over existing methods such as iterative attacks, GAN-based attacks, and ensemble attacks. Furthermore, we provide a comprehensive discussion on future research avenues in diffusion-based adversarial attacks, aiming to chart a course for this burgeoning field.

Physical adversarial examples in optical remote sensing have garnered significant attention in recent years due to their practicality and high adversarial threat potential. However, existing methods focus on position-fixed adversarial patches, neglecting tailored considerations for the domain-specific texture patterns and mobility required by aerial platforms. To address the issues above, we proposed a novel method of physical adversarial camouflage generation for the first time in optical remote sensing, which paints adversarial camouflage with specialized textures onto the targets to escape detection from DNN-based models. In pursuit of achieving a synthesis of visual harmony and adversarial attack potency, we propose a "latent variable-based" adversarial camouflage generation approach, in which we introduce a texture generator controlled by a group of latent variables to generate camouflage patterns with adversarial properties. By employing this idea, we can constrain the searching domain for adversarial examples to the domain characterized by camouflage exhibiting textures with high visual harmony, and easily focus on finding the most threatening ones during the optimization. We chose airplanes as the object of interest and object detection as the typical reconnaissance method in experiments. Our method achieved high attack success rates (ASRs) against a majority of existing detection models. Comparison with existing pixel-level optimization methods confirmed that the integration of a dedicated generator helps solve the trade-off dilemma between visual harmony and adversarial potency. Real-world experiments involving targets painted by our developed adversarial camouflage confirmed the adversarial attack potency and practicality, with a more than 50% increase on average in the ASRs compared to the conventional camouflage.

We propose a zero-shot approach to image harmonization, aiming to overcome the reliance on large amounts of synthetic composite images in existing methods. These methods, while showing promising results, involve significant training expenses and often struggle with generalization to unseen images. To this end, we introduce a fully modularized framework inspired by human behavior. Leveraging the reasoning capabilities of recent foundation models in language and vision, our approach comprises three main stages. Initially, we employ a pretrained vision-language model (VLM) to generate descriptions for the composite image. Subsequently, these descriptions guide the foreground harmonization direction of a text-to-image generative model (T2I). We refine text embeddings for enhanced representation of imaging conditions and employ self-attention and edge maps for structure preservation. Following each harmonization iteration, an evaluator determines whether to conclude or modify the harmonization direction. The resulting framework, mirroring human behavior, achieves harmonious results without the need for extensive training. We present compelling visual results across diverse scenes and objects, along with quantitative comparisons validating the effectiveness of our approach.

This paper explores the stability problems of discrete-time linear time-invariant (LTI) systems subject to random time delays. We first develop a general mean-square small-gain stability condition for feedback systems containing structured stochastic multiplicative uncertainties. Subsequently, we apply this mean-square small-gain condition to certain LTI random delay systems, where delays exhibit random delay lengths. Necessary and sufficient mean-square stability criteria are derived. These criteria, applicable to systems with either single or multiple sources of random delays, typically involve computing the spectral radius of a constant matrix. This computation allows us to determine whether a system's state variance matrix converges asymptotically despite the presence of random delays.

Multimodal learning significantly benefits cancer survival prediction, especially the integration of pathological images and genomic data. Despite advantages of multimodal learning for cancer survival prediction, massive redundancy in multimodal data prevents it from extracting discriminative and compact information: (1) An extensive amount of intra-modal task-unrelated information blurs discriminability, especially for gigapixel whole slide images (WSIs) with many patches in pathology and thousands of pathways in genomic data, leading to an "intra-modal redundancy" issue. (2) Duplicated information among modalities dominates the representation of multimodal data, which makes modality-specific information prone to being ignored, resulting in an "inter-modal redundancy" issue. To address these, we propose a new framework, Prototypical Information Bottlenecking and Disentangling (PIBD), consisting of Prototypical Information Bottleneck (PIB) module for intra-modal redundancy and Prototypical Information Disentanglement (PID) module for inter-modal redundancy. Specifically, a variant of information bottleneck, PIB, is proposed to model prototypes approximating a bunch of instances for different risk levels, which can be used for selection of discriminative instances within modality. PID module decouples entangled multimodal data into compact distinct components: modality-common and modality-specific knowledge, under the guidance of the joint prototypical distribution. Extensive experiments on five cancer benchmark datasets demonstrated our superiority over other methods. The code is released.

High-resolution (HR) image harmonization is of great significance in real-world applications such as image synthesis and image editing. However, due to the high memory costs, existing dense pixel-to-pixel harmonization methods are mainly focusing on processing low-resolution (LR) images. Some recent works resort to combining with color-to-color transformations but are either limited to certain resolutions or heavily depend on hand-crafted image filters. In this work, we explore leveraging the implicit neural representation (INR) and propose a novel image Harmonization method based on Implicit neural Networks (HINet), which to the best of our knowledge, is the first dense pixel-to-pixel method applicable to HR images without any hand-crafted filter design. Inspired by the Retinex theory, we decouple the MLPs into two parts to respectively capture the content and environment of composite images. A Low-Resolution Image Prior (LRIP) network is designed to alleviate the Boundary Inconsistency problem, and we also propose new designs for the training and inference process. Extensive experiments have demonstrated the effectiveness of our method compared with state-of-the-art methods. Furthermore, some interesting and practical applications of the proposed method are explored. Our code is available at https://github.com/WindVChen/INR-Harmonization.

In contrast to digital image adversarial attacks, adversarial patch attacks involve physical operations that project crafted perturbations into real-world scenarios. During the digital-to-physical transition, adversarial patches inevitably undergo information distortion. Existing approaches focus on data augmentation and printer color gamut regularization to improve the generalization of adversarial patches to the physical world. However, these efforts overlook a critical issue within the adversarial patch crafting pipeline—namely, the significant disparity between the appearance of adversarial patches during the digital optimization phase and their manifestation in the physical world. This unexplored concern, termed “Digital-to-Physical Visual Inconsistency", introduces inconsistent objectives between the digital and physical realms, potentially skewing optimization directions for adversarial patches. To tackle this challenge, we propose a novel harmonization-based adversarial patch attack. Our approach involves the design of a self-supervised harmonization method, seamlessly integrated into the adversarial patch generation pipeline. This integration aligns the appearance of adversarial patches overlaid on digital images with the imaging environment of the background, ensuring a consistent optimization direction with the primary physical attack goal. We validate our method through extensive testing on the aerial object detection task. To enhance the controllability of environmental factors for method evaluation, we construct a dataset of 3D simulated scenarios using a graphics rendering engine. Extensive experiments on these scenarios demonstrate the efficacy of our approach. Our code and dataset are publicly accessible at https://github.com/WindVChen/VCO-AP.

Deep neural networks (DNNs) have been widely applied in remote sensing, and the research on its adversarial attack algorithm is the key to evaluating its robustness. Current adversarial attack methods primarily prioritize maximizing the attack success rate, disregarding the imperceptibility of the generated adversarial noise to human visual perception. Moreover, research on adversarial sample transferability has mostly focused on cross-model and cross-dataset scenarios, overlooking the investigation of adversarial attacks across different resolutions, while the rarely studied cross-resolution adversarial attacks are critical for remote sensing with different resolutions. In this article, we propose a novel method for generating imperceptible adversarial samples for cross-resolution remote sensing images based on implicit neural representations (INRs). By mapping the discrete images to a continuous neural functional space, we explicitly guarantee the visual quality of adversarial samples and decouple the model input from the image resolution. To enhance the visual fidelity of the generated adversarial samples, a multiscale discriminative learning scheme is proposed for the optimization process. For cross-resolution adversarial attacks, we align with images of different resolutions and generate cross-resolution adversarial perturbation by benefiting from the natural properties of the continuous resolution of INRs. To validate the effectiveness of our method, we compare it with the existing adversarial attacking methods using four evaluation metrics. Experiments show that our method achieves the best results in terms of attack success rate, imperceptibility, and cross-resolution attack transferability. Our code will be made publicly available.

Physical adversarial attacks in aerial object detection have gained significant attention. Existing adversarial patches exhibit subpar visual effects and encounter limitations when transitioning from digital to physical spaces, restricting applicability in real-world scenarios. To address these challenges, we propose an adversarial texture generation method based on background texture design. This method selectively covers the background environment without interfering with the target surface. We also explore the translational invariance of fully convolutional networks to decouple adversarial textures from shapes, allowing adversarial textures to be arbitrarily expanded during use. The areas where adversarial textures are placed are designated as the “detection failure zone,” rendering the detector ineffective regardless of the aircraft’s position within this zone. This significantly enhances the practicality of the adversarial texture. To improve its concealment, we align the features of the adversarial textures with those of the original image using a pretrained VGG network, ensuring a consistent style and color tone with the background environment. Additionally, we employ a discriminator to further control the visual effects of the adversarial samples, ensuring effective concealment. Furthermore, we simulate the real environment in digital space using operations like affine transformations and Gaussian blur to transfer adversarial textures seamlessly from digital to physical space. This allows for the integration of adversarial textures into real environments without compromising their effectiveness. Experimental results demonstrate the effectiveness and consistent styling of the proposed adversarial texture in real-world environments, showing robustness against environmental changes, weather conditions, and viewing angles.

In this paper, we consider the problem of simultaneously detecting objects and inferring their visual attributes in an image, even for those with no manual annotations provided at the training stage, resembling an open-vocabulary scenario. To achieve this goal, we make the following contributions: (i) we start with a naive two-stage approach for open-vocabulary object detection and attribute classification, termed CLIP-Attr. The candidate objects are first proposed with an offline RPN and later classified for semantic category and attributes; (ii) we combine all available datasets and train with a federated strategy to finetune the CLIP model, aligning the visual representation with attributes, additionally, we investigate the efficacy of leveraging freely available online image-caption pairs under weakly supervised learning; (iii) in pursuit of efficiency, we train a Faster-RCNN type model end-to-end with knowledge distillation, that performs class-agnostic object proposals and classification on semantic categories and attributes with classifiers generated from a text encoder; Finally, (iv) we conduct extensive experiments on VAW, MS-COCO, LSA, and OVAD datasets, and show that recognition of semantic category and attributes is complementary for visual scene understanding, i.e., jointly training object detection and attributes prediction largely outperform existing approaches that treat the two tasks independently, demonstrating strong generalization ability to novel attributes and categories.

Remote sensing scene classification is an important yet challenging task. In recent years, the excellent feature representation ability of convolutional neural networks (CNNs) has led to substantial improvements in scene classification accuracy. However, handling resolution variations of remote sensing images is still challenging because CNNs are not inherently capable of modeling multiresolution input images. In this letter, we propose a novel scene classification method with scale and resolution adaptation ability by leveraging the recent advances in implicit neural representations (INRs). Unlike previous CNN-based methods that make predictions based on rasterized image inputs, the proposed method converts the images as continuous functions with INRs optimization and then performs classification within the function space. When the image is represented as a function, the image resolution can be decoupled from the pixel values so that the resolution does not have much impact on the classification performance. Our method also shows great potential for multiresolution remote sensing scene classification. Using only a simple multilayer perceptron (MLP) classifier in the proposed function space, our method achieves classification accuracy comparable to deep CNNs but exhibits better adaptability to image scale and resolution changes.

Despite its fruitful applications in remote sensing, image super-resolution is troublesome to train and deploy as it handles different resolution magnifications with separate models. Accordingly, we propose a highly-applicable super-resolution framework called FunSR, which settles different magnifications with a unified model by exploiting context interaction within implicit function space. FunSR composes a functional representor, a functional interactor, and a functional parser. Specifically, the representor transforms the low-resolution image from Euclidean space to multi-scale pixel-wise function maps; the interactor enables pixel-wise function expression with global dependencies; and the parser, which is parameterized by the interactor’s output, converts the discrete coordinates with additional attributes to RGB values. Extensive experimental results demonstrate that FunSR reports state-of-the-art performance on both fixed-magnification and continuous-magnification settings, meanwhile, it provides many friendly applications thanks to its unified nature. Our code is available at https://github.com/KyanChen/FunSR.

Remote sensing image change captioning (RSICC) is a novel task that aims to describe the differences between bi-temporal images by natural language. Previous methods ignore a significant specificity of the task: the difficulty of RSICC is different for unchanged and changed image pairs. They process the unchanged and changed image pairs in a coupled way, which usually causes confusion for change captioning. In this paper, we decouple the task into two issues to ease it: whether and what changes have occurred. An image-level classifier performs binary classification to address the first issue. A feature-level encoder contributes to extracting discriminative features to help the caption generation module address the second issue. Besides, for caption generation, we utilize prompt learning to introduce pre-trained large language models (LLMs) into the RSICC task. A multi-prompt learning strategy is proposed to generate a set of unified prompts and a class-specific prompt conditioned on the image-level classifier’s results. The strategy can prompt a pre-trained LLM to know whether changes exist and generate captions. Finally, the multiple prompts and the visual features of the feature-level encoder are fed into a frozen LLM for language generation. Compared with previous methods, our method can leverage the powerful abilities of the pre-trained LLM in language to generate plausible captions, which is free of training. Extensive experiments show that our method is effective and achieves state-of-the-art performance. Besides, an additional experiment demonstrates that our decoupling paradigm is more promising than the previous coupled paradigm for the RSICC task. We will make our codebase publicly available to facilitate future research at https://github.com/Chen-Yang-Liu/PromptCC.

Fine-grained image classification can be considered as a discriminative learning process where images of different subclasses are separated from each other while the same subclass images are clustered. Most existing methods perform synchronous discriminative learning in their approaches. Although achieving promising results in fine-grained visual classification (FGVC) in natural images, these methods may fail in fine-grained ship classification (FGSC) problem in remote sensing (RS) images due to the highly “imbalanced fineness" and “imbalanced appearances" of ships among subclasses. To tackle the issue, we propose an asynchronous contrastive learning-based method for effective FGSC. The proposed method, which we refer to as “Push-and-Pull Network (P2Net)", includes a “push-out stage” and a “pull-in stage”, where the first stage forces all the instances to be de-correlated and then the second one groups them into each subclass. A dual-branch network is designed to separate/de-correlate the images with each other, while an Integration Module is designed to aggregate the de-correlated images into their corresponding subclass together with a Proxy-based Module designed for acceleration. In this way, the correlation between subclasses can be decoupled, which in turn makes the final classification much easier. Our method can be trained end-to-end and requires no additional annotations other than category information. Extensive experiments are conducted on two large-scale FGSC datasets (FGSC-23 and FGSCR-42). Our method outperforms other state-of-the-art approaches. Ablation experiments also suggest the effectiveness of our design. Our code is available at https://github.com/WindVChen/Push-and-Pull-Network.

The rapid detection of ships within the wide sea area is essential for intelligence acquisition. Most modern deep learning-based ship detection methods focus on locating ships in high-resolution (HR) remote sensing (RS) images. Seldom efforts have been made on ship detection in medium-resolution (MR) RS images. An MR image covers a much wider area than an HR one of the same size, thus facilitating quick ship detection. To this end, we propose a tiny ship detection method namely, Degraded Reconstruction Enhancement Network (DRENet), for MR RS images. Different from previous methods that mainly focus on feature fusion strategies to improve the expression ability of the detector, we design an additional network branch, i.e., degraded reconstruction enhancer, to learn to regress an object-aware blurred version of the input image in the training phase. Our intuition is that the proposed reconstruction branch may guide the backbone to focus more on tiny ship targets instead of the vast background. Moreover, we incorporate a CRoss-stage Multi-head Attention module in the detector to further improve the feature discrimination by leveraging the self-attention mechanism. To fill the gap of lacking a large-scale MR ship detection dataset, we introduce Levir-Ship, which contains 3876 GF-1/GF-6 multi-spectral images and over 3K tiny ship instances. Experiments on Levir-Ship validate the effectiveness and efficiency of the proposed method. Our method achieves 82.4 AP with 85 FPS, which outperforms many state-of-the-art ship detection methods. Our code and dataset will be made public.

The protection of Intellectual Property (IP) has emerged as one of the most important issues in the hardware design industry. Most VLSI design companies are now fabless and need to protect their IP from being illegally distributed. One of the main approach to address this has been through logic locking. Logic locking prevents IPs from being reversed engineered as well as overbuilding the hardware circuit by untrusted foundries. One of the main problem with existing logic locking techniques is that the foundry has full access to the entire design including the logic locking mechanism. Because of the importance of this topic, continuous more robust locking mechanisms are proposed and equally fast new methods to break them appear. One alternative approach is to lock a circuit through omission. The main idea is to selectively map a portion of the IP onto an embedded FPGA (eFPGA). Because the foundry does not have access to the bitstream, the circuit cannot be used until programmed by the legitimate user. One of the main problems with this approach is the large overhead in terms of area and power, as well as timing degradation. Area is especially a concern for price sensitive applications. To address this, in this work we presents a method to map portions of a design onto a Coarse Grained Runtime Reconfigurable Architecture (CGRRA) such that multiple parts of a design can be hidden onto the CGRRA, substantially amortizing the area overhead introduced by the CGRRA.

This paper proposes a practical method to watermark behavioral IP (BIPs) for High-Level Synthesis (HLS), such that the watermark can be unequivocally retrieved at the generated RTL code, while being unremovable. The main approaches to watermark BIPs so far have focus on modifying the HLS process by e.g. introducing watermarking-aware scheduling or register binding algorithms. The main problem with these approaches is that they involve having full control over the HLS tool's internal behavior, which is not practically possible. Specifically, state-of-the-art HLS tools do not allow this type of controllability. Hence, these approaches are currently impossible to be implemented. On the other hand, commercial HLS tools make extensive use of synthesis directives in the form of pragmas. In this work we make use of these synthesis directives to assign operations in the source code to specific functional units given in the technology library in order to create the watermark. Experimental results show that our proposed method is effective in creating strong watermarks, while practical at the same time.

Among various competing designs targeting similar functionality, the key differentiator typically consists of a small amount of custom Intellectual Property (IP). To protect this IP from reverse engineering, designers need effective solutions for hiding the unique aspects of their implementations. In this work, we introduce a general framework for partitioning the computation performed by a design into a part whose implementation is commonly known (and encountered across many designs), and a part which is unique to this design. The former can then be built using conventional techniques (including untrusted manufacturing facilities) while the latter needs to be protected using additional obfuscation techniques. The existence of several other known implementations of the (same or similar) target function serves as a decoy which deflects efforts seeking to reverse-engineer the unique implementation. We demonstrate our framework using a hardware accelerator case study where (a) partitioning is performed through High Level Synthesis (HLS), (b) the commonly known portion of the accelerator is implemented as an Application Specific Integrated Circuit (ASIC), and (c) the unique portion of the accelerator is implemented on an embedded Field-Programmable Gate Array (eFPGA).

This work proposes a method to accelerate the process of High-Level Synthesis (HLS) Design Space Exploration (DSE) by pre-characterizing micro-kernels offline and creating predictive models of these. HLS allows to generate different types of micro-architectures from the same untimed behavioral description. This is typically done by setting different combinations of synthesis options in the form or synthesis directives specified as pragmas in the code. This allows, e.g. to control how loops should be synthesized, arrays and functions. Unique combinations of these pragmas leads to micro-architectures with a unique area vs. performance/power trade-offs. The main problem is that the search space grows exponentially with the number of explorable operations. Thus, the main goal of efficient HLS DSE is to find the synthesis directives' combinations that lead to the Pareto-optimal designs quickly. Our proposed method is based on the pre-characterization of micro-kernels offline, creating predictive models for each of the kernels, and using the results to explore a new unseen behavioral description using compositional methods. In addition, we make use of perceptual hashing to match new unseen micro-kernels with the pre-characterized micro-kernels in order to further speed up the search process. Experimental results show that our proposed method is orders of magnitude faster than traditional methods.

This work investigates if temperature can be used to fingerprint FPGA designs and presents a method to generate a large number of functionally equivalent FPGA designs such that each design has a unique distinguishable thermal signature. The main methodology behind this work is based on the design space exploration of each hardware accelerator in the design specified as a behavioral description (e.g. ANSI-C, C++ or SystemC) to obtain a trade-off curve of designs with unique area vs. performance trade-offs as well as a third dimension that consists of the difference in their thermal profle. Experimental results, prototyping different hardware accelerators on a FPGA, and using a high resolution infrared camera, show the usability of our proposed method, which is able to distinguish between the different design versions and hence can serve to detect if an FPGA design is unlawfully being used.

This paper presents a method to generate a variety of micro-architectures for a given hardware accelerator mapped onto reconfigurable fabric optimized for different operating frequencies. The most optimal micro-architecture is then loaded onto the fabric for a given operating frequency in order to minimize the power consumption. State-of-the-art FPGAs are runtime reconfigurable and provide multiple clock domains. This enables these devices to reconfigure any accelerator mapped on them and their frequencies at runtime. At the same time, FPGA vendors have embraced High-Level Synthesis (HLS) to increase the design productivity and help designers with limited hardware development skills to program these devices. One of the advantages of HLS over traditional RT-level hardware design is that HLS allows to automatically generate micro-architectures with unique area, performance and power trade-offs by setting different synthesis options, which is impractical or very time consuming at the RT-level. This work leverages these two features and investigates the benefit of adapting the micro-architecture of hardware accelerators mapped onto a reconfigurable fabric at runtime when the operating frequency changes to reduce the power consumption, while maximizing the throughput. To enable the frequency-aware micro-architectural adaptation we also propose a simple micro-architectural resource manager and show that the overhead in terms of area and delay is negligible. We conduct two sets of experiments. The first shows that our proposed approach leads to faster circuits which consume less power than just statically scaling the frequency of the fastest micro-architecture for a variety of different test cases. The second case, presents case study of a face detection application mapped onto a battery-operated wireless camera sensor node powered by solar cells.

In this work, we propose a method that automatically generates a set of functional equivalent systems with unique performance vs. peak temperature, where the starting point is a set of behavioral descriptions for High-Level Synthesis (HLS), and the output the Pareto-optimal systems. This is accomplished by leveraging one of the main benefits of C-based VLSI design: The ability to automatically create functional equivalent circuits with unique area vs. performance trade-offs from a single behavioral description. The proposed method is built around three main phases. The first phase performs a design space exploration on each module given as a behavioral description for HLS to obtain a trade-off curve of dominating micro-architectures. The second phase builds different systems by combining different mixes of micro-architectures. Finally, phase 3 continues by selectively floorplanning these micro-architectures in the system to obtain a trade-off curve of Pareto-optimal systems. Experimental results targeting a FPGA show that our proposed method works well.