In this paper, we present a toolchain for a comprehensive audio/video analysis by leveraging deep learning based multimodal approach. To this end, different specific tasks of Speech to Text (S2T), Acoustic Scene Classification (ASC), Acoustic Event Detection (AED), Visual Object Detection (VOD), Image Captioning (IC), and Video Captioning (VC) are conducted and integrated into the toolchain. By combining individual tasks and analyzing both audio \& visual data extracted from input video, the toolchain offers various audio/video-based applications: Two general applications of audio/video clustering, comprehensive audio/video summary and a specific application of riot or violent context detection. Furthermore, the toolchain presents a flexible and adaptable architecture that is effective to integrate new models for further audio/video-based applications.
Computer vision applications are increasingly popular for wildlife monitoring tasks. While some studies focus on the monitoring of a single species, such as a particular endangered species, others monitor larger functional groups, such as predators. In our study, we used camera trap images collected in north-western New South Wales, Australia, to investigate how model results were affected by combining multiple species in single classes, and whether the addition of negative samples can improve model performance. We found that species that benefited the most from merging into a single class were mainly species that look alike morphologically, i.e. macropods. Whereas species that looked distinctively different gave mixed results when merged, e.g. merging pigs and goats together as non-native large mammals. We also found that adding negative samples improved model performance marginally in most instances, and recommend conducting a more comprehensive study to explore whether the marginal gains were random or consistent. We suggest that practitioners could classify morphologically similar species together as a functional group or higher taxonomic group to draw ecological inferences. Nevertheless, whether to merge classes or not will depend on the ecological question to be explored.
Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt transformer-based models to fuse features from both modalities, further introducing various modules that modulate visual features to align with the language expressions and eliminate the irrelevant redundant information. However, their loss function, still adopting common Object Detection losses, solely governs the bounding box regression output, failing to fully optimize for the above objectives. To tackle this problem, in this paper, we first analyze the attention mechanisms of transformer-based models. Building upon this, we further propose a novel framework named Attention-Driven Constraint Balancing (AttBalance) to optimize the behavior of visual features within language-relevant regions. Extensive experimental results show that our method brings impressive improvements. Specifically, we achieve constant improvements over five different models evaluated on four different benchmarks. Moreover, we attain a new state-of-the-art performance by integrating our method into QRNet.
Different from Object Detection, Visual Grounding deals with detecting a bounding box for each text-image pair. This one box for each text-image data provides sparse supervision signals. Although previous works achieve impressive results, their passive utilization of annotation, i.e. the sole use of the box annotation as regression ground truth, results in a suboptimal performance. In this paper, we present SegVG, a novel method transfers the box-level annotation as Segmentation signals to provide an additional pixel-level supervision for Visual Grounding. Specifically, we propose the Multi-layer Multi-task Encoder-Decoder as the target grounding stage, where we learn a regression query and multiple segmentation queries to ground the target by regression and segmentation of the box in each decoding layer, respectively. This approach allows us to iteratively exploit the annotation as signals for both box-level regression and pixel-level segmentation. Moreover, as the backbones are typically initialized by pretrained parameters learned from unimodal tasks and the queries for both regression and segmentation are static learnable embeddings, a domain discrepancy remains among these three types of features, which impairs subsequent target grounding. To mitigate this discrepancy, we introduce the Triple Alignment module, where the query, text, and vision tokens are triangularly updated to share the same space by triple attention mechanism. Extensive experiments on five widely used datasets validate our state-of-the-art (SOTA) performance.
Children often suffer wrist injuries in daily life, while fracture injuring radiologists usually need to analyze and interpret X-ray images before surgical treatment by surgeons. The development of deep learning has enabled neural network models to work as computer-assisted diagnosis (CAD) tools to help doctors and experts in diagnosis. Since the YOLOv8 models have obtained the satisfactory success in object detection tasks, it has been applied to fracture detection. The Global Context (GC) block effectively models the global context in a lightweight way, and incorporating it into YOLOv8 can greatly improve the model performance. This paper proposes the YOLOv8+GC model for fracture detection, which is an improved version of the YOLOv8 model with the GC block. Experimental results demonstrate that compared to the original YOLOv8 model, the proposed YOLOv8-GC model increases the mean average precision calculated at intersection over union threshold of 0.5 (mAP 50) from 63.58% to 66.32% on the GRAZPEDWRI-DX dataset, achieving the state-of-the-art (SOTA) level. The implementation code for this work is available on GitHub at https://github.com/RuiyangJu/YOLOv8_Global_Context_Fracture_Detection.
This paper presents a comprehensive review of the evolution of the YOLO (You Only Look Once) object detection algorithm, focusing on YOLOv5, YOLOv8, and YOLOv10. We analyze the architectural advancements, performance improvements, and suitability for edge deployment across these versions. YOLOv5 introduced significant innovations such as the CSPDarknet backbone and Mosaic Augmentation, balancing speed and accuracy. YOLOv8 built upon this foundation with enhanced feature extraction and anchor-free detection, improving versatility and performance. YOLOv10 represents a leap forward with NMS-free training, spatial-channel decoupled downsampling, and large-kernel convolutions, achieving state-of-the-art performance with reduced computational overhead. Our findings highlight the progressive enhancements in accuracy, efficiency, and real-time performance, particularly emphasizing their applicability in resource-constrained environments. This review provides insights into the trade-offs between model complexity and detection accuracy, offering guidance for selecting the most appropriate YOLO version for specific edge computing applications.
Unsupervised Domain Adaptive Object Detection (DAOD) could adapt a model trained on a source domain to an unlabeled target domain for object detection. Existing unsupervised DAOD methods usually perform feature alignments from the target to the source. Unidirectional domain transfer would omit information about the target samples and result in suboptimal adaptation when there are large domain shifts. Therefore, we propose a pairwise attentive adversarial network with a Domain Mixup (DomMix) module to mitigate the aforementioned challenges. Specifically, a deep-level mixup is employed to construct an intermediate domain that allows features from both domains to share their differences. Then a pairwise attentive adversarial network is applied with attentive encoding on both image-level and instance-level features at different scales and optimizes domain alignment by adversarial learning. This allows the network to focus on regions with disparate contextual information and learn their similarities between different domains. Extensive experiments are conducted on several benchmark datasets, demonstrating the superiority of our proposed method.
Vision Transformers (ViTs) have exhibited exceptional performance across diverse computer vision tasks, while their substantial parameter size incurs significantly increased memory and computational demands, impeding effective inference on resource-constrained devices. Quantization has emerged as a promising solution to mitigate these challenges, yet existing methods still suffer from significant accuracy loss at low-bit. We attribute this issue to the distinctive distributions of post-LayerNorm and post-GELU activations within ViTs, rendering conventional hardware-friendly quantizers ineffective, particularly in low-bit scenarios. To address this issue, we propose a novel framework called Activation-Distribution-Friendly post-training Quantization for Vision Transformers, ADFQ-ViT. Concretely, we introduce the Per-Patch Outlier-aware Quantizer to tackle irregular outliers in post-LayerNorm activations. This quantizer refines the granularity of the uniform quantizer to a per-patch level while retaining a minimal subset of values exceeding a threshold at full-precision. To handle the non-uniform distributions of post-GELU activations between positive and negative regions, we design the Shift-Log2 Quantizer, which shifts all elements to the positive region and then applies log2 quantization. Moreover, we present the Attention-score enhanced Module-wise Optimization which adjusts the parameters of each quantizer by reconstructing errors to further mitigate quantization error. Extensive experiments demonstrate ADFQ-ViT provides significant improvements over various baselines in image classification, object detection, and instance segmentation tasks at 4-bit. Specifically, when quantizing the ViT-B model to 4-bit, we achieve a 10.23% improvement in Top-1 accuracy on the ImageNet dataset.
Confusion and forgetting of object classes have been challenges of prime interest in Few-Shot Object Detection (FSOD). To overcome these pitfalls in metric learning based FSOD techniques, we introduce a novel Submodular Mutual Information Learning (SMILe) framework which adopts combinatorial mutual information functions to enforce the creation of tighter and discriminative feature clusters in FSOD. Our proposed approach generalizes to several existing approaches in FSOD, agnostic of the backbone architecture demonstrating elevated performance gains. A paradigm shift from instance based objective functions to combinatorial objectives in SMILe naturally preserves the diversity within an object class resulting in reduced forgetting when subjected to few training examples. Furthermore, the application of mutual information between the already learnt (base) and newly added (novel) objects ensures sufficient separation between base and novel classes, minimizing the effect of class confusion. Experiments on popular FSOD benchmarks, PASCAL-VOC and MS-COCO show that our approach generalizes to State-of-the-Art (SoTA) approaches improving their novel class performance by up to 5.7% (3.3 mAP points) and 5.4% (2.6 mAP points) on the 10-shot setting of VOC (split 3) and 30-shot setting of COCO datasets respectively. Our experiments also demonstrate better retention of base class performance and up to 2x faster convergence over existing approaches agnostic of the underlying architecture.
In the realm of deploying Machine Learning-based Advanced Driver Assistance Systems (ML-ADAS) into real-world scenarios, adverse weather conditions pose a significant challenge. Conventional ML models trained on clear weather data falter when faced with scenarios like extreme fog or heavy rain, potentially leading to accidents and safety hazards. This paper addresses this issue by proposing a novel approach: employing a Denoising Deep Neural Network as a preprocessing step to transform adverse weather images into clear weather images, thereby enhancing the robustness of ML-ADAS systems. The proposed method eliminates the need for retraining all subsequent Depp Neural Networks (DNN) in the ML-ADAS pipeline, thus saving computational resources and time. Moreover, it improves driver visualization, which is critical for safe navigation in adverse weather conditions. By leveraging the UNet architecture trained on an augmented KITTI dataset with synthetic adverse weather images, we develop the Weather UNet (WUNet) DNN to remove weather artifacts. Our study demonstrates substantial performance improvements in object detection with WUNet preprocessing under adverse weather conditions. Notably, in scenarios involving extreme fog, our proposed solution improves the mean Average Precision (mAP) score of the YOLOv8n from 4% to 70%.
Objects in aerial images are typically embedded in complex backgrounds and exhibit arbitrary orientations. When employing oriented bounding boxes (OBB) to represent arbitrary oriented objects, the periodicity of angles could lead to discontinuities in label regression values at the boundaries, inducing abrupt fluctuations in the loss function. To address this problem, an OBB representation based on the complex plane is introduced in the oriented detection framework, and a trigonometric loss function is proposed. Moreover, leveraging prior knowledge of complex background environments and significant differences in large objects in aerial images, a conformer RPN head is constructed to predict angle information. The proposed loss function and conformer RPN head jointly generate high-quality oriented proposals. A category-aware dynamic label assignment based on predicted category feedback is proposed to address the limitations of solely relying on IoU for proposal label assignment. This method makes negative sample selection more representative, ensuring consistency between classification and regression features. Experiments were conducted on four realistic oriented detection datasets, and the results demonstrate superior performance in oriented object detection with minimal parameter tuning and time costs. Specifically, mean average precision (mAP) scores of 82.02%, 71.99%, 69.87%, and 98.77% were achieved on the DOTA-v1.0, DOTA-v1.5, DIOR-R, and HRSC2016 datasets, respectively.
Drone detection is a challenging object detection task where visibility conditions and quality of the images may be unfavorable, and detections might become difficult due to complex backgrounds, small visible objects, and hard to distinguish objects. Both provide high confidence for drone detections, and eliminating false detections requires efficient algorithms and approaches. Our previous work, which uses YOLOv5, uses both real and synthetic data and a Kalman-based tracker to track the detections and increase their confidence using temporal information. Our current work improves on the previous approach by combining several improvements. We used a more diverse dataset combining multiple sources and combined with synthetic samples chosen from a large synthetic dataset based on the error analysis of the base model. Also, to obtain more resilient confidence scores for objects, we introduced a classification component that discriminates whether the object is a drone or not. Finally, we developed a more advanced scoring algorithm for object tracking that we use to adjust localization confidence. Furthermore, the proposed technique won 1st Place in the Drone vs. Bird Challenge (Workshop on Small-Drone Surveillance, Detection and Counteraction Techniques at ICIAP 2021).
Insulator defect detection is of great significance to ensure the normal operation of power transmission and distribution networks. In response to the problems of low speed, low accuracy, and difficulty in deploying to embedded terminals in existing insulator defect detection, this paper proposes a lightweight insulator defect detection model based on an improved YOLOv5s, named LiteYOLO-ID. Firstly, to significantly reduce the model parameters while maintaining detection accuracy, we design a new lightweight convolution module called EGC (ECA-GhostNet-C2f). Secondly, based on the EGC module, we construct the EGC-CSPGhostNet backbone network, which optimizes the feature extraction process and achieves model compression. Additionally, we design a lightweight neck network, EGC-PANet, to further reduce the parameter count and achieve efficient feature fusion. Experimental results show that on the IDID-Plus dataset, compared to the original YOLOv5s model, not only does LiteYOLO-ID reduce the model parameters by 47.13\%, but it also improves the mAP(0.5) by 1\%. Furthermore, the generalization of the model is validated on the Pascal VOC dataset and the SFID dataset. Importantly, after TensorRT optimization, the inference speed of the LiteYOLO-ID algorithm on the Jetson TX2 NX reaches 20.2 FPS, meeting the real-time detection requirements of insulator defects. Our code, weight models, and datasets can be obtained at the following URL: https://github.com/LuYang-2023/Insulator-defect-detection.
Safety issues at construction sites have long plagued the industry, posing risks to worker safety and causing economic damage due to potential hazards. With the advancement of artificial intelligence, particularly in the field of computer vision, the automation of safety monitoring on construction sites has emerged as a solution to this longstanding issue. Despite achieving impressive performance, advanced object detection methods like YOLOv8 still face challenges in handling the complex conditions found at construction sites. To solve these problems, this study presents the Global Stability Optimization YOLO (GSO-YOLO) model to address challenges in complex construction sites. The model integrates the Global Optimization Module (GOM) and Steady Capture Module (SCM) to enhance global contextual information capture and detection stability. The innovative AIoU loss function, which combines CIoU and EIoU, improves detection accuracy and efficiency. Experiments on datasets like SODA, MOCS, and CIS show that GSO-YOLO outperforms existing methods, achieving SOTA performance.
Position bias has proven to be a prevalent issue of modern language models (LMs), where the models prioritize content based on its position within the given context. This bias often leads to unexpected model failures and hurts performance, robustness, and reliability across various applications. Our mechanistic analysis attributes the position bias to two components employed in nearly all state-of-the-art LMs: causal attention and relative positional encodings. Based on the analyses, we propose to eliminate position bias (e.g., different retrieved documents' orders in QA affect performance) with a training-free zero-shot approach. Our method changes the causal attention to bidirectional attention between documents and utilizes model attention values to decide the relative orders of documents instead of using the order provided in input prompts, therefore enabling Position-INvariant inferencE (PINE) at the document level. By eliminating position bias, models achieve better performance and reliability in downstream tasks, including LM-as-a-judge, retrieval-augmented QA, molecule generation, and math reasoning. Notably, PINE is especially useful when adapting LMs for evaluating reasoning pairs: it consistently provides 8 to 10 percentage points performance gains, making Llama-3-70B-Instruct perform even better than GPT-4-0125-preview and GPT-4o-2024-08-06 on the RewardBench reasoning set.
Agriculture faces a growing challenge with wildlife wreaking havoc on crops, threatening sustainability. The project employs advanced object detection, the system utilizes the Mobile Net SSD model for real-time animal classification. The methodology initiates with the creation of a dataset, where each animal is represented by annotated images. The SSD Mobile Net architecture facilitates the use of a model for image classification and object detection. The model undergoes fine-tuning and optimization during training, enhancing accuracy for precise animal classification. Real-time detection is achieved through a webcam and the OpenCV library, enabling prompt identification and categorization of approaching animals. By seamlessly integrating intelligent scarecrow technology with object detection, this system offers a robust solution to field protection, minimizing crop damage and promoting precision farming. It represents a valuable contribution to agricultural sustainability, addressing the challenge of wildlife interference with crops. The implementation of the Intelligent Scarecrow Monitoring System stands as a progressive tool for proactive field management and protection, empowering farmers with an advanced solution for precision agriculture. Keywords: Machine learning, Deep Learning, Computer Vision, MobileNet SSD
Deep neural networks (DNNs) are widely used in real-world applications, yet they remain vulnerable to errors and adversarial attacks. Formal verification offers a systematic approach to identify and mitigate these vulnerabilities, enhancing model robustness and reliability. While most existing verification methods focus on image classification models, this work extends formal verification to the more complex domain of emph{object detection} models. We propose a formulation for verifying the robustness of such models and demonstrate how state-of-the-art verification tools, originally developed for classification, can be adapted for this purpose. Our experiments, conducted on various datasets and networks, highlight the ability of formal verification to uncover vulnerabilities in object detection models, underscoring the need to extend verification efforts to this domain. This work lays the foundation for further research into formal verification across a broader range of computer vision applications.
Recent years have seen object detection robotic systems deployed in several personal devices (e.g., home robots and appliances). This has highlighted a challenge in their design, i.e., they cannot efficiently update their knowledge to distinguish between general classes and user-specific instances (e.g., a dog vs. user's dog). We refer to this challenging task as Instance-level Personalized Object Detection (IPOD). The personalization task requires many samples for model tuning and optimization in a centralized server, raising privacy concerns. An alternative is provided by approaches based on recent large-scale Foundation Models, but their compute costs preclude on-device applications. In our work we tackle both problems at the same time, designing a Few-Shot IPOD strategy called AuXFT. We introduce a conditional coarse-to-fine few-shot learner to refine the coarse predictions made by an efficient object detector, showing that using an off-the-shelf model leads to poor personalization due to neural collapse. Therefore, we introduce a Translator block that generates an auxiliary feature space where features generated by a self-supervised model (e.g., DINOv2) are distilled without impacting the performance of the detector. We validate AuXFT on three publicly available datasets and one in-house benchmark designed for the IPOD task, achieving remarkable gains in all considered scenarios with excellent time-complexity trade-off: AuXFT reaches a performance of 80% its upper bound at just 32% of the inference time, 13% of VRAM and 19% of the model size.
Semi-supervised object detection (SSOD), leveraging unlabeled data to boost object detectors, has become a hot topic recently. However, existing SSOD approaches mainly focus on horizontal objects, leaving multi-oriented objects common in aerial images unexplored. At the same time, the annotation cost of multi-oriented objects is significantly higher than that of their horizontal counterparts. Therefore, in this paper, we propose a simple yet effective Semi-supervised Oriented Object Detection method termed SOOD++. Specifically, we observe that objects from aerial images are usually arbitrary orientations, small scales, and aggregation, which inspires the following core designs: a Simple Instance-aware Dense Sampling (SIDS) strategy is used to generate comprehensive dense pseudo-labels; the Geometry-aware Adaptive Weighting (GAW) loss dynamically modulates the importance of each pair between pseudo-label and corresponding prediction by leveraging the intricate geometric information of aerial objects; we treat aerial images as global layouts and explicitly build the many-to-many relationship between the sets of pseudo-labels and predictions via the proposed Noise-driven Global Consistency (NGC). Extensive experiments conducted on various multi-oriented object datasets under various labeled settings demonstrate the effectiveness of our method. For example, on the DOTA-V1.5 benchmark, the proposed method outperforms previous state-of-the-art (SOTA) by a large margin (+2.92, +2.39, and +2.57 mAP under 10%, 20%, and 30% labeled data settings, respectively) with single-scale training and testing. More importantly, it still improves upon a strong supervised baseline with 70.66 mAP, trained using the full DOTA-V1.5 train-val set, by +1.82 mAP, resulting in a 72.48 mAP, pushing the new state-of-the-art. The code will be made available.
While supervised learning has achieved significant success in computer vision tasks, acquiring high-quality annotated data remains a bottleneck. This paper explores both scholarly and non-scholarly works in AI-assistive deep learning image annotation systems that provide textual suggestions, captions, or descriptions of the input image to the annotator. This potentially results in higher annotation efficiency and quality. Our exploration covers annotation for a range of computer vision tasks including image classification, object detection, regression, instance, semantic segmentation, and pose estimation. We review various datasets and how they contribute to the training and evaluation of AI-assistive annotation systems. We also examine methods leveraging neuro-symbolic learning, deep active learning, and self-supervised learning algorithms that enable semantic image understanding and generate free-text output. These include image captioning, visual question answering, and multi-modal reasoning. Despite the promising potential, there is limited publicly available work on AI-assistive image annotation with textual output capabilities. We conclude by suggesting future research directions to advance this field, emphasizing the need for more publicly accessible datasets and collaborative efforts between academia and industry.