To segment a signal into blocks to be analyzed, few-shot keyword spotting (KWS) systems often utilize a sliding window of fixed size. Because of the varying lengths of different keywords or their spoken instances, choosing the right window size is a problem: A window should be long enough to contain all necessary information needed to recognize a keyword but a longer window may contain irrelevant information such as multiple words or noise and thus makes it difficult to reliably detect on- and offsets of keywords. We propose TACos, a novel angular margin loss for deriving two-dimensional embeddings that retain temporal properties of the underlying speech signal. In experiments conducted on KWS-DailyTalk, a few-shot KWS dataset presented in this work, using these embeddings as templates for dynamic time warping is shown to outperform using other representations or a sliding window and that using time-reversed segments of the keywords during training improves the performance.
相關內容
Several photonic microring resonators (MRRs) based analog accelerators have been proposed to accelerate the inference of integer-quantized CNNs with remarkably higher throughput and energy efficiency compared to their electronic counterparts. However, the existing analog photonic accelerators suffer from three shortcomings: (i) severe hampering of wavelength parallelism due to various crosstalk effects, (ii) inflexibility of supporting various dataflows other than the weight-stationary dataflow, and (iii) failure in fully leveraging the ability of photodetectors to perform in-situ accumulations. These shortcomings collectively hamper the performance and energy efficiency of prior accelerators. To tackle these shortcomings, we present a novel Hybrid timE Amplitude aNalog optical Accelerator, called HEANA. HEANA employs hybrid time-amplitude analog optical multipliers (TAOMs) that increase the flexibility of HEANA to support multiple dataflows. A spectrally hitless arrangement of TAOMs significantly reduces the crosstalk effects, thereby increasing the wavelength parallelism in HEANA. Moreover, HEANA employs our invented balanced photo-charge accumulators (BPCAs) that enable buffer-less, in-situ, temporal accumulations to eliminate the need to use reduction networks in HEANA, relieving it from related latency and energy overheads. Our evaluation for the inference of four modern CNNs indicates that HEANA provides improvements of atleast 66x and 84x in frames-per-second (FPS) and FPS/W (energy-efficiency), respectively, for equal-area comparisons, on gmean over two MRR-based analog CNN accelerators from prior work.
The process of estimating and counting tree density using only a single aerial or satellite image is a difficult task in the fields of photogrammetry and remote sensing. However, it plays a crucial role in the management of forests. The huge variety of trees in varied topography severely hinders tree counting models to perform well. The purpose of this paper is to propose a framework that is learnt from the source domain with sufficient labeled trees and is adapted to the target domain with only a limited number of labeled trees. Our method, termed as AdaTreeFormer, contains one shared encoder with a hierarchical feature extraction scheme to extract robust features from the source and target domains. It also consists of three subnets: two for extracting self-domain attention maps from source and target domains respectively and one for extracting cross-domain attention maps. For the latter, an attention-to-adapt mechanism is introduced to distill relevant information from different domains while generating tree density maps; a hierarchical cross-domain feature alignment scheme is proposed that progressively aligns the features from the source and target domains. We also adopt adversarial learning into the framework to further reduce the gap between source and target domains. Our AdaTreeFormer is evaluated on six designed domain adaptation tasks using three tree counting datasets, ie Jiangsu, Yosemite, and London; and outperforms the state of the art methods significantly.
Deep neural networks (DNNs) have demonstrated remarkable performance across various tasks, including image and speech recognition. However, maximizing the effectiveness of DNNs requires meticulous optimization of numerous hyperparameters and network parameters through training. Moreover, high-performance DNNs entail many parameters, which consume significant energy during training. In order to overcome these challenges, researchers have turned to spiking neural networks (SNNs), which offer enhanced energy efficiency and biologically plausible data processing capabilities, rendering them highly suitable for sensory data tasks, particularly in neuromorphic data. Despite their advantages, SNNs, like DNNs, are susceptible to various threats, including adversarial examples and backdoor attacks. Yet, the field of SNNs still needs to be explored in terms of understanding and countering these attacks. This paper delves into backdoor attacks in SNNs using neuromorphic datasets and diverse triggers. Specifically, we explore backdoor triggers within neuromorphic data that can manipulate their position and color, providing a broader scope of possibilities than conventional triggers in domains like images. We present various attack strategies, achieving an attack success rate of up to 100% while maintaining a negligible impact on clean accuracy. Furthermore, we assess these attacks' stealthiness, revealing that our most potent attacks possess significant stealth capabilities. Lastly, we adapt several state-of-the-art defenses from the image domain, evaluating their efficacy on neuromorphic data and uncovering instances where they fall short, leading to compromised performance.
High-definition (HD) cameras for surveillance and road traffic have experienced tremendous growth, demanding intensive computation resources for real-time analytics. Recently, offloading frames from the front-end device to the back-end edge server has shown great promise. In multi-stream competitive environments, efficient bandwidth management and proper scheduling are crucial to ensure both high inference accuracy and high throughput. To achieve this goal, we propose BiSwift, a bi-level framework that scales the concurrent real-time video analytics by a novel adaptive hybrid codec integrated with multi-level pipelines, and a global bandwidth controller for multiple video streams. The lower-level front-back-end collaborative mechanism (called adaptive hybrid codec) locally optimizes the accuracy and accelerates end-to-end video analytics for a single stream. The upper-level scheduler aims to accuracy fairness among multiple streams via the global bandwidth controller. The evaluation of BiSwift shows that BiSwift is able to real-time object detection on 9 streams with an edge device only equipped with an NVIDIA RTX3070 (8G) GPU. BiSwift improves 10%$\sim$21% accuracy and presents 1.2$\sim$9$\times$ throughput compared with the state-of-the-art video analytics pipelines.
Effective Receptive field (ERF) plays an important role in transform coding, which determines how much redundancy can be removed at most during transform and how many spatial priors can be utilized to synthesize textures during inverse transform. Existing methods rely on stacks of small kernels, whose ERF remains not large enough instead, or heavy non-local attention mechanisms, which limit the potential of high resolution image coding. To tackle this issue, we propose Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression (LLIC). Specifically, for the first time in learned image compression community, we introduce a few large kernel-based depth-wise convolutions to reduce more redundancy while maintaining modest complexity. Due to wide range of image diversity, we propose to enhance the adaptability of convolutions via generating weights in a self-conditioned manner. The large kernels cooperate with non-linear embedding and gate mechanisms for better expressiveness and lighter point-wise interactions. We also investigate improved training techniques to fully exploit the potential of large kernels. In addition, to enhance the interactions among channels, we propose the adaptive channel-wise bit allocation via generating channel importance factor in a self-conditioned manner. To demonstrate the effectiveness of proposed transform coding, we align the entropy model to compare with existing transform methods and obtain models LLIC-STF, LLIC-ELIC, LLIC-TCM. Extensive experiments demonstrate our proposed LLIC models have significant improvements over corresponding baselines and achieve state-of-the-art performances and better trade-off between performance and complexity.
Recently, GPT-4 with Vision (GPT-4V) has demonstrated remarkable visual capabilities across various tasks, but its performance in emotion recognition has not been fully evaluated. To bridge this gap, we present the quantitative evaluation results of GPT-4V on 19 benchmark datasets covering 5 tasks: visual sentiment analysis, micro-expression recognition, facial emotion recognition, dynamic facial emotion recognition, and multimodal emotion recognition. This paper collectively refers to these tasks as ``Generalized Emotion Recognition (GER)''. Through experimental analysis, we observe that GPT-4V generally outperforms supervised systems in visual sentiment analysis, highlighting its powerful visual understanding capabilities. Meanwhile, GPT-4V shows the ability to integrate multimodal clues and exploit temporal information, which is also critical for emotion recognition. Despite these achievements, GPT-4V is primarily tailored for general-purpose domains, which cannot recognize micro-expressions that require specialized knowledge. To the best of our knowledge, this paper provides the first quantitative assessment of GPT-4V for the GER tasks, offering valuable insights to researchers in this field. It can also serve as a zero-shot benchmark for subsequent research. Our code and evaluation results are available at: //github.com/zeroQiaoba/gpt4v-emotion.
The notable success of large language models (LLMs) has sparked an upsurge in building language agents to complete various complex tasks. We present AMOR, an agent framework based on open-source LLMs, which reasons with external knowledge bases and adapts to specific domains through human supervision to the reasoning process. AMOR builds reasoning logic over a finite state machine (FSM) that solves problems through autonomous executions and transitions over disentangled modules. This allows humans to provide direct feedback to the individual modules, and thus naturally forms process supervision. Based on this reasoning and feedback framework, we develop AMOR through two-stage fine-tuning: warm-up and adaptation. The former fine-tunes the LLM with examples automatically constructed from various public datasets and enables AMOR to generalize across different knowledge environments, while the latter tailors AMOR to specific domains using process feedback. Extensive experiments across multiple domains demonstrate the advantage of AMOR to strong baselines, thanks to its FSM-based reasoning and process feedback mechanism.
The introduction of ChatGPT has led to a significant increase in the utilization of Large Language Models (LLMs) for addressing downstream tasks. There's an increasing focus on cost-efficient training and deployment within this context. Low-cost training and deployment of LLMs represent the future development trend. This paper reviews the evolution of large language model training techniques and inference deployment technologies aligned with this emerging trend. The discussion on training includes various aspects, including data preprocessing, training architecture, pre-training tasks, parallel training, and relevant content related to model fine-tuning. On the inference side, the paper covers topics such as model compression, parallel computation, memory scheduling, and structural optimization. It also explores LLMs' utilization and provides insights into their future development.
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this paper, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.
Visual dialogue is a challenging task that needs to extract implicit information from both visual (image) and textual (dialogue history) contexts. Classical approaches pay more attention to the integration of the current question, vision knowledge and text knowledge, despising the heterogeneous semantic gaps between the cross-modal information. In the meantime, the concatenation operation has become de-facto standard to the cross-modal information fusion, which has a limited ability in information retrieval. In this paper, we propose a novel Knowledge-Bridge Graph Network (KBGN) model by using graph to bridge the cross-modal semantic relations between vision and text knowledge in fine granularity, as well as retrieving required knowledge via an adaptive information selection mode. Moreover, the reasoning clues for visual dialogue can be clearly drawn from intra-modal entities and inter-modal bridges. Experimental results on VisDial v1.0 and VisDial-Q datasets demonstrate that our model outperforms exiting models with state-of-the-art results.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191