The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep learning networks are ill-equipped for incremental learning. When a well-trained network is adapted to new categories, its performance on the old categories will dramatically degrade. To address this problem, incremental learning methods have been explored which preserve the old knowledge of deep learning models. However, the state-of-the-art incremental object detector employs an external fixed region proposal method that increases overall computation time and reduces accuracy comparing to Region Proposal Network (RPN) based object detectors such as Faster RCNN. The purpose of this paper is to design an efficient end-to-end incremental object detector using knowledge distillation. We first evaluate and analyze the performance of the RPN-based detector with classic distillation on incremental detection tasks. Then, we introduce multi-network adaptive distillation that properly retains knowledge from the old categories when fine-tuning the model for new task. Experiments on the benchmark datasets, PASCAL VOC and COCO, demonstrate that the proposed incremental detector based on Faster RCNN is more accurate as well as being 13 times faster than the baseline detector.
Anomaly detection in manufacturing pipelines remains a critical challenge, intensified by the complexity and variability of industrial environments. This paper introduces AssemAI, an interpretable image-based anomaly detection system tailored for smart manufacturing pipelines. Utilizing a curated image dataset from an industry-focused rocket assembly pipeline, we address the challenge of imbalanced image data and demonstrate the importance of image-based methods in anomaly detection. Our primary contributions include deriving an image dataset, fine-tuning an object detection model YOLO-FF, and implementing a custom anomaly detection model for assembly pipelines. The proposed approach leverages domain knowledge in data preparation, model development and reasoning. We implement several anomaly detection models on the derived image dataset, including a Convolutional Neural Network, Vision Transformer (ViT), and pre-trained versions of these models. Additionally, we incorporate explainability techniques at both user and model levels, utilizing ontology for user-level explanations and SCORE-CAM for in-depth feature and model analysis. Finally, the best-performing anomaly detection model and YOLO-FF are deployed in a real-time setting. Our results include ablation studies on the baselines and a comprehensive evaluation of the proposed system. This work highlights the broader impact of advanced image-based anomaly detection in enhancing the reliability and efficiency of smart manufacturing processes. The image dataset, codes to reproduce the results and additional experiments are available at https://github.com/renjithk4/AssemAI.
We present Context Forest (ConF), a technique for predicting properties of the objects in an image based on its global appearance. Compared to standard nearest-neighbour techniques, ConF is more accurate, fast and memory efficient. We train ConF to predict which aspects of an object class are likely to appear in a given image (e.g. which viewpoint). This enables to speed-up multi-component object detectors, by automatically selecting the most relevant components to run on that image. This is particularly useful for detectors trained from large datasets, which typically need many components to fully absorb the data and reach their peak performance. ConF provides a speed-up of 2x for the DPM detector [1] and of 10x for the EE-SVM detector [2]. To show ConF's generality, we also train it to predict at which locations objects are likely to appear in an image. Incorporating this information in the detector score improves mAP performance by about 2% by removing false positive detections in unlikely locations.
We present PartGLEE, a part-level foundation model for locating and identifying both objects and parts in images. Through a unified framework, PartGLEE accomplishes detection, segmentation, and grounding of instances at any granularity in the open world scenario. Specifically, we propose a Q-Former to construct the hierarchical relationship between objects and parts, parsing every object into corresponding semantic parts. By incorporating a large amount of object-level data, the hierarchical relationships can be extended, enabling PartGLEE to recognize a rich variety of parts. We conduct comprehensive studies to validate the effectiveness of our method, PartGLEE achieves the state-of-the-art performance across various part-level tasks and obtain competitive results on object-level tasks. The proposed PartGLEE significantly enhances hierarchical modeling capabilities and part-level perception over our previous GLEE model. Further analysis indicates that the hierarchical cognitive ability of PartGLEE is able to facilitate a detailed comprehension in images for mLLMs. The model and code will be released at https://provencestar.github.io/PartGLEE-Vision/ .
Moving object detection and segmentation from a single moving camera is a challenging task, requiring an understanding of recognition, motion and 3D geometry. Combining both recognition and reconstruction boils down to a fusion problem, where appearance and motion features need to be combined for classification and segmentation. In this paper, we present a novel fusion architecture for monocular motion segmentation - M3Former, which leverages the strong performance of transformers for segmentation and multi-modal fusion. As reconstructing motion from monocular video is ill-posed, we systematically analyze different 2D and 3D motion representations for this problem and their importance for segmentation performance. Finally, we analyze the effect of training data and show that diverse datasets are required to achieve SotA performance on Kitti and Davis.
Data-driven saliency detection has attracted strong interest as a result of applying convolutional neural networks to the detection of eye fixations. Although a number of imagebased salient object and fixation detection models have been proposed, video fixation detection still requires more exploration. Different from image analysis, motion and temporal information is a crucial factor affecting human attention when viewing video sequences. Although existing models based on local contrast and low-level features have been extensively researched, they failed to simultaneously consider interframe motion and temporal information across neighboring video frames, leading to unsatisfactory performance when handling complex scenes. To this end, we propose a novel and efficient video eye fixation detection model to improve the saliency detection performance. By simulating the memory mechanism and visual attention mechanism of human beings when watching a video, we propose a step-gained fully convolutional network by combining the memory information on the time axis with the motion information on the space axis while storing the saliency information of the current frame. The model is obtained through hierarchical training, which ensures the accuracy of the detection. Extensive experiments in comparison with 11 state-of-the-art methods are carried out, and the results show that our proposed model outperforms all 11 methods across a number of publicly available datasets.
Most of existing salient object detection models have achieved great progress by aggregating multi-level features extracted from convolutional neural networks. However, because of the different receptive fields of different convolutional layers, there exists big differences between features generated by these layers. Common feature fusion strategies (addition or concatenation) ignore these differences and may cause suboptimal solutions. In this paper, we propose the F3Net to solve above problem, which mainly consists of cross feature module (CFM) and cascaded feedback decoder (CFD) trained by minimizing a new pixel position aware loss (PPA). Specifically, CFM aims to selectively aggregate multi-level features. Different from addition and concatenation, CFM adaptively selects complementary components from input features before fusion, which can effectively avoid introducing too much redundant information that may destroy the original features. Besides, CFD adopts a multi-stage feedback mechanism, where features closed to supervision will be introduced to the output of previous layers to supplement them and eliminate the differences between features. These refined features will go through multiple similar iterations before generating the final saliency maps. Furthermore, different from binary cross entropy, the proposed PPA loss doesn't treat pixels equally, which can synthesize the local structure information of a pixel to guide the network to focus more on local details. Hard pixels from boundaries or error-prone parts will be given more attention to emphasize their importance. F3Net is able to segment salient object regions accurately and provide clear local details. Comprehensive experiments on five benchmark datasets demonstrate that F3Net outperforms state-of-the-art approaches on six evaluation metrics.
Slip detection is essential for robots to make robust grasping and fine manipulation. In this paper, a novel dynamic vision-based finger system for slip detection and suppression is proposed. We also present a baseline and feature based approach to detect object slips under illumination and vibration uncertainty. A threshold method is devised to autonomously sample noise in real-time to improve slip detection. Moreover, a fuzzy based suppression strategy using incipient slip feedback is proposed for regulating the grip force. A comprehensive experimental study of our proposed approaches under uncertainty and system for high-performance precision manipulation are presented. We also propose a slip metric to evaluate such performance quantitatively. Results indicate that the system can effectively detect incipient slip events at a sampling rate of 2kHz ($\Delta t = 500\mu s$) and suppress them before a gross slip occurs. The event-based approach holds promises to high precision manipulation task requirement in industrial manufacturing and household services.
Remote examination and job interviews have gained popularity and become indispensable because of both pandemics and the advantage of remote working circumstances. Most companies and academic institutions utilize these systems for their recruitment processes and also for online exams. However, one of the critical problems of the remote examination systems is conducting the exams in a reliable environment. In this work, we present a cheating analysis pipeline for online interviews and exams. The system only requires a video of the candidate, which is recorded during the exam. Then cheating detection pipeline is employed to detect another person, electronic device usage, and candidate absence status. The pipeline consists of face detection, face recognition, object detection, and face tracking algorithms. To evaluate the performance of the pipeline we collected a private video dataset. The video dataset includes both cheating activities and clean videos. Ultimately, our pipeline presents an efficient and fast guideline to detect and analyze cheating activities in an online interview and exam video.
Out-of-distribution (OOD) detection has recently received special attention due to its critical role in safely deploying modern deep learning (DL) architectures. This work proposes a reconstruction-based multi-class OOD detector that operates on radar range doppler images (RDIs). The detector aims to classify any moving object other than a person sitting, standing, or walking as OOD. We also provide a simple yet effective pre-processing technique to detect minor human body movements like breathing. The simple idea is called respiration detector (RESPD) and eases the OOD detection, especially for human sitting and standing classes. On our dataset collected by 60GHz short-range FMCW Radar, we achieve AUROCs of 97.45%, 92.13%, and 96.58% for sitting, standing, and walking classes, respectively. We perform extensive experiments and show that our method outperforms state-of-the-art (SOTA) OOD detection methods. Also, our pipeline performs 24 times faster than the second-best method and is very suitable for real-time processing.
The ability to detect slip, particularly incipient slip, enables robotic systems to take corrective measures to prevent a grasped object from being dropped. Therefore, slip detection can enhance the overall security of robotic gripping. However, accurately detecting incipient slip remains a significant challenge. In this paper, we propose a novel learning-based approach to detect incipient slip using the PapillArray (Contactile, Australia) tactile sensor. The resulting model is highly effective in identifying patterns associated with incipient slip, achieving a detection success rate of 95.6% when tested with an offline dataset. Furthermore, we introduce several data augmentation methods to enhance the robustness of our model. When transferring the trained model to a robotic gripping environment distinct from where the training data was collected, our model maintained robust performance, with a success rate of 96.8%, providing timely feedback for stabilizing several practical gripping tasks. Our project website: https://sites.google.com/view/incipient-slip-detection.
In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for many-task vehicle analysis from a given image. A robust convolutional network is introduced for simultaneous vehicle detection, part localization, visibility characterization and 3D dimension estimation. Its architecture is based on a new coarse-to-fine object proposal that boosts the vehicle detection. Moreover, the Deep MANTA network is able to localize vehicle parts even if these parts are not visible. In the inference, the network's outputs are used by a real time robust pose estimation algorithm for fine orientation estimation and 3D vehicle localization. We show in experiments that our method outperforms monocular state-of-the-art approaches on vehicle detection, orientation and 3D location tasks on the very challenging KITTI benchmark.
Convolutional neural networks have recently shown excellent results in general object detection and many other tasks. Albeit very effective, they involve many user-defined design choices. In this paper we want to better understand these choices by inspecting two key aspects "what did the network learn?", and "what can the network learn?". We exploit new annotations (Pascal3D+), to enable a new empirical analysis of the R-CNN detector. Despite common belief, our results indicate that existing state-of-the-art convnet architectures are not invariant to various appearance factors. In fact, all considered networks have similar weak points which cannot be mitigated by simply increasing the training data (architectural changes are needed). We show that overall performance can improve when using image renderings for data augmentation. We report the best known results on the Pascal3D+ detection and view-point estimation tasks.
We present Morpheus, a new model for generating pixel-level morphological classifications of astronomical sources. Morpheus leverages advances in deep learning to perform source detection, source segmentation, and morphological classification pixel-by-pixel via a semantic segmentation algorithm adopted from the field of computer vision. By utilizing morphological information about the flux of real astronomical sources during object detection, Morpheus shows resiliency to false-positive identifications of sources. We evaluate Morpheus by performing source detection, source segmentation, morphological classification on the Hubble Space Telescope data in the five CANDELS fields with a focus on the GOODS South field, and demonstrate a high completeness in recovering known GOODS South 3D-HST sources with H < 26 AB. We release the code publicly, provide online demonstrations, and present an interactive visualization of the Morpheus results in GOODS South.
Nowadays, autonomous cars are gaining traction due to their numerous potential applications on battlefields and in resolving a variety of other real-world challenges. The main goal of our project is to build an autonomous system using DeepRacer which will follow a specific person (for our project, a soldier) when they will be moving in any direction. Two main components to accomplish this project is an optimized Single-Shot Multibox Detection (SSD) object detection model and a Reinforcement Learning (RL) model. We accomplished the task using SSD Lite instead of SSD and at the end, compared the results among SSD, SSD with Neural Computing Stick (NCS), and SSD Lite. Experimental results show that SSD Lite gives better performance among these three techniques and exhibits a considerable boost in inference speed (~2-3 times) without compromising accuracy.
Holistic 3D indoor scene understanding refers to jointly recovering the i) object bounding boxes, ii) room layout, and iii) camera pose, all in 3D. The existing methods either are ineffective or only tackle the problem partially. In this paper, we propose an end-to-end model that simultaneously solves all three tasks in real-time given only a single RGB image. The essence of the proposed method is to improve the prediction by i) parametrizing the targets (e.g., 3D boxes) instead of directly estimating the targets, and ii) cooperative training across different modules in contrast to training these modules individually. Specifically, we parametrize the 3D object bounding boxes by the predictions from several modules, i.e., 3D camera pose and object attributes. The proposed method provides two major advantages: i) The parametrization helps maintain the consistency between the 2D image and the 3D world, thus largely reducing the prediction variances in 3D coordinates. ii) Constraints can be imposed on the parametrization to train different modules simultaneously. We call these constraints "cooperative losses" as they enable the joint training and inference. We employ three cooperative losses for 3D bounding boxes, 2D projections, and physical constraints to estimate a geometrically consistent and physically plausible 3D scene. Experiments on the SUN RGB-D dataset shows that the proposed method significantly outperforms prior approaches on 3D object detection, 3D layout estimation, 3D camera pose estimation, and holistic scene understanding.
다양한 주행 환경에서의 자동 차량 검출(Automatic Vehicle Detection, AVD)은 조명 조건, 도로 유형, 차량 유형이 다양하기 때문에 독특한 과제를 제기한다. YOLO, Faster R-CNN과 같은 전통적인 방법들은 이러한 복잡성을 다루는 데 종종 어려움을 겪는다. 컴퓨터 비전(CV)이 발전함에 따라, 합성곱 신경망(CNN)과 트랜스포머 기반 접근법을 결합하는 것은 검출 정확도와 효율성 향상을 위한 유망한 기회를 제공한다. 본 연구는 복잡하고 다양한 환경에서 자동 차량 검출을 위해 Detection Transformer(DETR)를 실험한 최초의 연구이다. 우리는 DETR의 특징 학습과 어텐션 메커니즘을 향상시키기 위해 Collaborative Hybrid Assignments Training 방식인 Co-DETR을 사용한다. 다양한 레이블 할당 전략을 활용하고 다중 병렬 보조 헤드를 도입함으로써, 학습 동안 더 효과적인 감독을 제공하고 긍정 좌표를 추출하여 학습 효율을 높인다. BadODD 데이터셋을 사용하여 DETR 변형 및 YOLO 모델에 대해 광범위한 실험을 수행함으로써, 우리 접근법의 장점을 입증한다. 우리의 방법은 우수한 결과와 다양한 조건에서의 향상된 정확도를 달성하여, 실세계 배포에 실용적이다. 이 연구는 자율 내비게이션 기술을 크게 발전시키고 자율주행차를 위한 객체 검출 분야에서 새로운 연구 방향을 연다. CNN과 트랜스포머의 강점을 통합함으로써, 우리는 어려운 주행 환경에서 강건하고 효율적인 차량 검출을 위한 DETR의 잠재력을 강조한다.
Timber represents an increasingly valuable and versatile resource. However, forestry operations such as harvesting, handling and measuring logs still require substantial human labor in remote environments posing significant safety risks. Progressively automating these tasks has the potential of increasing their efficiency as well as safety, but requires an accurate detection of individual logs as well as live trees and their context. Although initial approaches have been proposed for this challenging application domain, specialized data and algorithms are still too scarce to develop robust solutions. To mitigate this gap, we introduce the TimberVision dataset, consisting of more than 2k annotated RGB images containing a total of 51k trunk components including cut and lateral surfaces, thereby surpassing any existing dataset in this domain in terms of both quantity and detail by a large margin. Based on this data, we conduct a series of ablation experiments for oriented object detection and instance segmentation and evaluate the influence of multiple scene parameters on model performance. We introduce a generic framework to fuse the components detected by our models for both tasks into unified trunk representations. Furthermore, we automatically derive geometric properties and apply multi-object tracking to further enhance robustness. Our detection and tracking approach provides highly descriptive and accurate trunk representations solely from RGB image data, even under challenging environmental conditions. Our solution is suitable for a wide range of application scenarios and can be readily combined with other sensor modalities.
This paper proposes a novel joint learning and densely-cooperative fusion (JL-DCF) architecture for RGB-D salient object detection. Existing models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately-designed training process. In contrast, our JL-DCF learns from both RGB and depth inputs through a Siamese network. To this end, we propose two effective components: joint learning (JL), and densely-cooperative fusion (DCF). The JL module provides robust saliency feature learning, while the latter is introduced for complementary feature discovery. Comprehensive experiments on four popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the top-1 D3Net model by an average of ~1.9% (S-measure) across six challenging datasets, showing that the proposed framework offers a potential solution for real-world applications and could provide more insight into the cross-modality complementarity task. The code will be available at https://github.com/kerenfu/JLDCF/.
Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature representations. We propose Tied Block Convolution (TBC) that shares the same thinner filters over equal blocks of channels and produces multiple responses with a single filter. The concept of TBC can also be extended to group convolution and fully connected layers, and can be applied to various backbone networks and attention modules. Our extensive experimentation on classification, detection, instance segmentation, and attention demonstrates TBC's significant across-the-board gain over standard convolution and group convolution. The proposed TiedSE attention module can even use 64 times fewer parameters than the SE module to achieve comparable performance. In particular, standard CNNs often fail to accurately aggregate information in the presence of occlusion and result in multiple redundant partial object proposals. By sharing filters across channels, TBC reduces correlation and can effectively handle highly overlapping instances. TBC increases the average precision for object detection on MS-COCO by 6% when the occlusion ratio is 80%. Our code will be released.