Video object detection is a tough task due to the deteriorated quality of video sequences captured under complex environments. Currently, this area is dominated by a series of feature enhancement based methods, which distill beneficial semantic information from multiple frames and generate enhanced features through fusing the distilled information. However, the distillation and fusion operations are usually performed at either frame level or instance level with external guidance using additional information, such as optical flow and feature memory. In this work, we propose a dual semantic fusion network (abbreviated as DSFNet) to fully exploit both frame-level and instance-level semantics in a unified fusion framework without external guidance. Moreover, we introduce a geometric similarity measure into the fusion process to alleviate the influence of information distortion caused by noise. As a result, the proposed DSFNet can generate more robust features through the multi-granularity fusion and avoid being affected by the instability of external guidance. To evaluate the proposed DSFNet, we conduct extensive experiments on the ImageNet VID dataset. Notably, the proposed dual semantic fusion network achieves, to the best of our knowledge, the best performance of 84.1\% mAP among the current state-of-the-art video object detectors with ResNet-101 and 85.4\% mAP with ResNeXt-101 without using any post-processing steps.
Visual perception plays an important role in autonomous driving. One of the primary tasks is object detection and identification. Since the vision sensor is rich in color and texture information, it can quickly and accurately identify various road information. The commonly used technique is based on extracting and calculating various features of the image. The recent development of deep learning-based method has better reliability and processing speed and has a greater advantage in recognizing complex elements. For depth estimation, vision sensor is also used for ranging due to their small size and low cost. Monocular camera uses image data from a single viewpoint as input to estimate object depth. In contrast, stereo vision is based on parallax and matching feature points of different views, and the application of deep learning also further improves the accuracy. In addition, Simultaneous Location and Mapping (SLAM) can establish a model of the road environment, thus helping the vehicle perceive the surrounding environment and complete the tasks. In this paper, we introduce and compare various methods of object detection and identification, then explain the development of depth estimation and compare various methods based on monocular, stereo, and RDBG sensors, next review and compare various methods of SLAM, and finally summarize the current problems and present the future development trends of vision technologies.
Recognition and reasoning are two pillars of visual understanding. However, these tasks have an imbalance in focus; whereas recent advances in neural networks have shown strong empirical performance in visual recognition, there has been comparably much less success in solving visual reasoning. Intuitively, unifying these two tasks under a singular framework is desirable, as they are mutually dependent and beneficial. Motivated by the recent success of multi-task transformers for visual recognition and language understanding, we propose a unified neural architecture for visual recognition and reasoning with a generic interface (e.g., tokens) for both. Our framework enables the principled investigation of how different visual recognition tasks, datasets, and inductive biases can help enable spatiotemporal reasoning capabilities. Noticeably, we find that object detection, which requires spatial localization of individual objects, is the most beneficial recognition task for reasoning. We further demonstrate via probing that implicit object-centric representations emerge automatically inside our framework. Intriguingly, we discover that certain architectural choices such as the backbone model of the visual encoder have a significant impact on visual reasoning, but little on object detection. Given the results of our experiments, we believe that visual reasoning should be considered as a first-class citizen alongside visual recognition, as they are strongly correlated but benefit from potentially different design choices.
Scene understanding and object recognition is a difficult to achieve yet crucial skill for robots. Recently, Convolutional Neural Networks (CNN), have shown success in this task. However, there is still a gap between their performance on image datasets and real-world robotics scenarios. We present a novel paradigm for incrementally improving a robot's visual perception through active human interaction. In this paradigm, the user introduces novel objects to the robot by means of pointing and voice commands. Given this information, the robot visually explores the object and adds images from it to re-train the perception module. Our base perception module is based on recent development in object detection and recognition using deep learning. Our method leverages state of the art CNNs from off-line batch learning, human guidance, robot exploration and incremental on-line learning.
Behavioral and semantic relationships play a vital role on intelligent self-driving vehicles and ADAS systems. Different from other research focused on trajectory, position, and bounding boxes, relationship data provides a human understandable description of the object's behavior, and it could describe an object's past and future status in an amazingly brief way. Therefore it is a fundamental method for tasks such as risk detection, environment understanding, and decision making. In this paper, we propose RSG-Net (Road Scene Graph Net): a graph convolutional network designed to predict potential semantic relationships from object proposals, and produces a graph-structured result, called "Road Scene Graph". The experimental results indicate that this network, trained on Road Scene Graph dataset, could efficiently predict potential semantic relationships among objects around the ego-vehicle.
Transparent object perception is a crucial skill for applications such as robot manipulation in household and laboratory settings. Existing methods utilize RGB-D or stereo inputs to handle a subset of perception tasks including depth and pose estimation. However, transparent object perception remains to be an open problem. In this paper, we forgo the unreliable depth map from RGB-D sensors and extend the stereo based method. Our proposed method, MVTrans, is an end-to-end multi-view architecture with multiple perception capabilities, including depth estimation, segmentation, and pose estimation. Additionally, we establish a novel procedural photo-realistic dataset generation pipeline and create a large-scale transparent object detection dataset, Syn-TODD, which is suitable for training networks with all three modalities, RGB-D, stereo and multi-view RGB. Project Site: https://ac-rad.github.io/MVTrans/
Endometrial cancer is one of the most common tumors in the female reproductive system and is the third most common gynecological malignancy that causes death after ovarian and cervical cancer. Early diagnosis can significantly improve the 5-year survival rate of patients. With the development of artificial intelligence, computer-assisted diagnosis plays an increasingly important role in improving the accuracy and objectivity of diagnosis, as well as reducing the workload of doctors. However, the absence of publicly available endometrial cancer image datasets restricts the application of computer-assisted diagnostic techniques.In this paper, a publicly available Endometrial Cancer PET/CT Image Dataset for Evaluation of Semantic Segmentation and Detection of Hypermetabolic Regions (ECPC-IDS) are published. Specifically, the segmentation section includes PET and CT images, with a total of 7159 images in multiple formats. In order to prove the effectiveness of segmentation methods on ECPC-IDS, five classical deep learning semantic segmentation methods are selected to test the image segmentation task. The object detection section also includes PET and CT images, with a total of 3579 images and XML files with annotation information. Six deep learning methods are selected for experiments on the detection task.This study conduct extensive experiments using deep learning-based semantic segmentation and object detection methods to demonstrate the differences between various methods on ECPC-IDS. As far as we know, this is the first publicly available dataset of endometrial cancer with a large number of multiple images, including a large amount of information required for image and target detection. ECPC-IDS can aid researchers in exploring new algorithms to enhance computer-assisted technology, benefiting both clinical doctors and patients greatly.
In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks. However, when extended to point cloud data, existing works mainly focus on building task-specific models, and fail to extract universal 3D vision-language embedding that generalize well. We carefully investigate three common tasks in semantic 3D scene understanding, and derive key insights into the development of a pre-training model. Motivated by these observations, we propose a vision-language pre-training framework 3DVLP (3D vision-language pre-training with object contrastive learning), which transfers flexibly on 3D vision-language downstream tasks. 3DVLP takes visual grounding as the proxy task and introduces Object-level IoU-guided Detection (OID) loss to obtain high-quality proposals in the scene. Moreover, we design Object-level Cross-Contrastive alignment (OCC) task and Object-level Self-Contrastive learning (OSC) task to align the objects with descriptions and distinguish different objects in the scene, respectively. Extensive experiments verify the excellent performance of 3DVLP on three 3D vision-language tasks, reflecting its superiority in semantic 3D scene understanding.
In the last decade, Convolutional Neural Network (CNN) and transformer based object detectors have achieved high performance on a large variety of datasets. Though the majority of detection literature has developed this capability on datasets such as MS COCO, these detectors have still proven effective for remote sensing applications. Challenges in this particular domain, such as small numbers of annotated objects and low object density, hinder overall performance. In this work, we present a novel augmentation method, called collage pasting, for increasing the object density without a need for segmentation masks, thereby improving the detector performance. We demonstrate that collage pasting improves precision and recall beyond related methods, such as mosaic augmentation, and enables greater control of object density. However, we find that collage pasting is vulnerable to certain out-of-distribution shifts, such as image corruptions. To address this, we introduce two simple approaches for combining collage pasting with PixMix augmentation method, and refer to our combined techniques as ColMix. Through extensive experiments, we show that employing ColMix results in detectors with superior performance on aerial imagery datasets and robust to various corruptions.
Rotation detection is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. Though considerable progress has been made, for practical settings, there still exist challenges for rotating objects with large aspect ratio, dense distribution and category extremely imbalance. In this paper, we propose an end-to-end refined single-stage rotation detector for fast and accurate object detection by using a progressive regression approach from coarse to fine granularity. Considering the shortcoming of feature misalignment in existing refined single-stage detector, we design a feature refinement module to improve detection performance by getting more accurate features. The key idea of feature refinement module is to re-encode the position information of the current refined bounding box to the corresponding feature points through pixel-wise feature interpolation to realize feature reconstruction and alignment. For more accurate rotation estimation, an approximate SkewIoU loss is proposed to solve the problem that the calculation of SkewIoU is not derivable. Experiments on three popular remote sensing public datasets DOTA, HRSC2016, UCAS-AOD as well as one scene text dataset ICDAR2015 show the effectiveness of our approach. Tensorflow and Pytorch version codes are available at https://github.com/Thinklab-SJTU/R3Det_Tensorflow and https://github.com/SJTU-Thinklab-Det/r3det-on-mmdetection, and R3Det is also integrated in our open source rotation detection benchmark: https://github.com/yangxue0827/RotationDetection.
양식 필드 검출(Form Field Detection, FFD)은 문서 이해 시스템의 핵심 구성 요소로, 대규모 산업용 디지털화부터 자동화된 분석을 위한 접근성 높은 양식 상호작용에 이르기까지 다양한 응용을 가능하게 한다. 기존의 객체 검출(object detection) 작업과 달리, FFD는 필드가 눈에 보이는 전경 콘텐츠가 아니라 레이아웃 구조와 공백(whitespace)에 의해 정의되는 경우가 많기 때문에 본질적으로 어려운 과제이다. 기존의 대규모 데이터셋(dataset)은 휴리스틱 기반 주석 파이프라인에 의존하는 경우가 많아, 노이즈가 많고 일관성이 떨어지는 레이블이 생성되어 신뢰할 수 있는 평가를 저해한다. 본 연구에서는 일관되고 고품질의 주석을 갖춘, 신중하게 큐레이션된 FFD 벤치마크인 mini-CommonForms를 소개하고, 최신 검출 접근법에 대한 상세한 평가를 제시한다. 이 벤치마크는 문서 자동화 및 접근성 지향 응용 분야에서 재현 가능한 연구를 지원하도록 설계되었다. 데이터셋과 코드는 https://github.com/moured/mini-commonforms 에서 확인할 수 있다.
Large-scale object detection datasets (e.g., MS-COCO) try to define the ground truth bounding boxes as clear as possible. However, we observe that ambiguities are still introduced when labeling the bounding boxes. In this paper, we propose a novel bounding box regression loss for learning bounding box transformation and localization variance together. Our loss greatly improves the localization accuracies of various architectures with nearly no additional computation. The learned localization variance allows us to merge neighboring bounding boxes during non-maximum suppression (NMS), which further improves the localization performance. On MS-COCO, we boost the Average Precision (AP) of VGG-16 Faster R-CNN from 23.6% to 29.1%. More importantly, for ResNet-50-FPN Mask R-CNN, our method improves the AP and AP90 by 1.8% and 6.2% respectively, which significantly outperforms previous state-of-the-art bounding box refinement methods. Our code and models are available at: github.com/yihui-he/KL-Loss
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs). Many popular methods impose deep supervision to perform side-output predictions that are linearly aggregated for final saliency prediction. In this paper, we theoretically and experimentally demonstrate that linear aggregation of side-output predictions is suboptimal, and it only makes limited use of the side-output information obtained by deep supervision. To solve this problem, we propose Deeply-supervised Nonlinear Aggregation (DNA) for better leveraging the complementary information of various side-outputs. Compared with existing methods, it i) aggregates side-output features rather than predictions, and ii) adopts nonlinear instead of linear transformations. Experiments demonstrate that DNA can successfully break through the bottleneck of current linear approaches. Specifically, the proposed saliency detector, a modified U-Net architecture with DNA, performs favorably against state-of-the-art methods on various datasets and evaluation metrics without bells and whistles.
Deep neural network (DNN) based salient object detection in images based on high-quality labels is expensive. Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth labels. In this work, we propose a two-stage mechanism for robust unsupervised object saliency prediction, where the first stage involves refinement of the noisy pseudo labels generated from different handcrafted methods. Each handcrafted method is substituted by a deep network that learns to generate the pseudo labels. These labels are refined incrementally in multiple iterations via our proposed self-supervision technique. In the second stage, the refined labels produced from multiple networks representing multiple saliency methods are used to train the actual saliency detection network. We show that this self-learning procedure outperforms all the existing unsupervised methods over different datasets. Results are even comparable to those of fully-supervised state-of-the-art approaches. The code is available at https://tinyurl.com/wtlhgo3 .
Single-stage detectors suffer from extreme foreground-background class imbalance, while two-stage detectors do not. Therefore, in semi-supervised object detection, two-stage detectors can deliver remarkable performance by only selecting high-quality pseudo labels based on classification scores. However, directly applying this strategy to single-stage detectors would aggravate the class imbalance with fewer positive samples. Thus, single-stage detectors have to consider both quality and quantity of pseudo labels simultaneously. In this paper, we design a dynamic self-adaptive threshold (DSAT) strategy in classification branch, which can automatically select pseudo labels to achieve an optimal trade-off between quality and quantity. Besides, to assess the regression quality of pseudo labels in single-stage detectors, we propose a module to compute the regression uncertainty of boxes based on Non-Maximum Suppression. By leveraging only 10% labeled data from COCO, our method achieves 35.0% AP on anchor-free detector (FCOS) and 32.9% on anchor-based detector (RetinaNet).
While multi-class 3D detectors are needed in many robotics applications, training them with fully labeled datasets can be expensive in labeling cost. An alternative approach is to have targeted single-class labels on disjoint data samples. In this paper, we are interested in training a multi-class 3D object detection model, while using these single-class labeled data. We begin by detailing the unique stance of our "Single-Class Supervision" (SCS) setting with respect to related concepts such as partial supervision and semi supervision. Then, based on the case study of training the multi-class version of Range Sparse Net (RSN), we adapt a spectrum of algorithms -- from supervised learning to pseudo-labeling -- to fully exploit the properties of our SCS setting, and perform extensive ablation studies to identify the most effective algorithm and practice. Empirical experiments on the Waymo Open Dataset show that proper training under SCS can approach or match full supervision training while saving labeling costs.
Due to the more dramatic multi-scale variations and more complicated foregrounds and backgrounds in optical remote sensing images (RSIs), the salient object detection (SOD) for optical RSIs becomes a huge challenge. However, different from natural scene images (NSIs), the discussion on the optical RSI SOD task still remains scarce. In this paper, we propose a multi-scale context network, namely MSCNet, for SOD in optical RSIs. Specifically, a multi-scale context extraction module is adopted to address the scale variation of salient objects by effectively learning multi-scale contextual information. Meanwhile, in order to accurately detect complete salient objects in complex backgrounds, we design an attention-based pyramid feature aggregation mechanism for gradually aggregating and refining the salient regions from the multi-scale context extraction module. Extensive experiments on two benchmarks demonstrate that MSCNet achieves competitive performance with only 3.26M parameters. The code will be available at https://github.com/NuaaYH/MSCNet.
Camera and LiDAR serve as informative sensors for accurate and robust autonomous driving systems. However, these sensors often exhibit heterogeneous natures, resulting in distributional modality gaps that present significant challenges for fusion. To address this, a robust fusion technique is crucial, particularly for enhancing 3D object detection. In this paper, we introduce a dynamic adjustment technology aimed at aligning modal distributions and learning effective modality representations to enhance the fusion process. Specifically, we propose a triphase domain aligning module. This module adjusts the feature distributions from both the camera and LiDAR, bringing them closer to the ground truth domain and minimizing differences. Additionally, we explore improved representation acquisition methods for dynamic fusion, which includes modal interaction and specialty enhancement. Finally, an adaptive learning technique that merges the semantics and geometry information for dynamical instance optimization. Extensive experiments in the nuScenes dataset present competitive performance with state-of-the-art approaches. Our code will be released in the future.
Multimodal 3D object detection has garnered considerable interest in autonomous driving. However, multimodal detectors suffer from dimension mismatches that derive from fusing 3D points with 2D pixels coarsely, which leads to sub-optimal fusion performance. In this paper, we propose a multimodal framework FGU3R to tackle the issue mentioned above via unified 3D representation and fine-grained fusion, which consists of two important components. First, we propose an efficient feature extractor for raw and pseudo points, termed Pseudo-Raw Convolution (PRConv), which modulates multimodal features synchronously and aggregates the features from different types of points on key points based on multimodal interaction. Second, a Cross-Attention Adaptive Fusion (CAAF) is designed to fuse homogeneous 3D RoI (Region of Interest) features adaptively via a cross-attention variant in a fine-grained manner. Together they make fine-grained fusion on unified 3D representation. The experiments conducted on the KITTI and nuScenes show the effectiveness of our proposed method.
Personalized object detection aims to adapt a general-purpose detector to recognize user-specific instances from only a few examples. Lightweight models often struggle in this setting due to their weak semantic priors, while large vision-language models (VLMs) offer strong object-level understanding but are too computationally demanding for real-time or on-device applications. We introduce MOCHA (Multi-modal Objects-aware Cross-arcHitecture Alignment), a distillation framework that transfers multimodal region-level knowledge from a frozen VLM teacher into a lightweight vision-only detector. MOCHA extracts fused visual and textual teacher's embeddings and uses them to guide student training through a dual-objective loss that enforces accurate local alignment and global relational consistency across regions. This process enables efficient transfer of semantics without the need for teacher modifications or textual input at inference. MOCHA consistently outperforms prior baselines across four personalized detection benchmarks under strict few-shot regimes, yielding a +10.1 average improvement, with minimal inference cost.