We tackle the problem of learning object detectors without supervision. Differently from weakly-supervised object detection, we do not assume image-level class labels. Instead, we extract a supervisory signal from audio-visual data, using the audio component to "teach" the object detector. While this problem is related to sound source localisation, it is considerably harder because the detector must classify the objects by type, enumerate each instance of the object, and do so even when the object is silent. We tackle this problem by first designing a self-supervised framework with a contrastive objective that jointly learns to classify and localise objects. Then, without using any supervision, we simply use these self-supervised labels and boxes to train an image-based object detector. With this, we outperform previous unsupervised and weakly-supervised detectors for the task of object detection and sound source localization. We also show that we can align this detector to ground-truth classes with as little as one label per pseudo-class, and show how our method can learn to detect generic objects that go beyond instruments, such as airplanes and cats.
Latest CNN-based object detection models are quite accurate but require a high-performance GPU to run in real-time. They still are heavy in terms of memory size and speed for an embedded system with limited memory space. Since the object detection for autonomous system is run on an embedded processor, it is preferable to compress the detection network as light as possible while preserving the detection accuracy. There are several popular lightweight detection models but their accuracy is too low for safe driving applications. Therefore, this paper proposes a new object detection model, referred as YOffleNet, which is compressed at a high ratio while minimizing the accuracy loss for real-time and safe driving application on an autonomous system. The backbone network architecture is based on YOLOv4, but we could compress the network greatly by replacing the high-calculation-load CSP DenseNet with the lighter modules of ShuffleNet. Experiments with KITTI dataset showed that the proposed YOffleNet is compressed by 4.7 times than the YOLOv4-s that could achieve as fast as 46 FPS on an embedded GPU system(NVIDIA Jetson AGX Xavier). Compared to the high compression ratio, the accuracy is reduced slightly to 85.8% mAP, that is only 2.6% lower than YOLOv4-s. Thus, the proposed network showed a high potential to be deployed on the embedded system of the autonomous system for the real-time and accurate object detection applications.
Accurately localising object proposals is an important precondition for high detection rate for the state-of-the-art object detection frameworks. The accuracy of an object detection method has been shown highly related to the average recall (AR) of the proposals. In this work, we propose an advanced object proposal network in favour of translation-invariance for objectness classification, translation-variance for bounding box regression, large effective receptive fields for capturing global context and scale-invariance for dealing with a range of object sizes from extremely small to large. The design of the network architecture aims to be simple while being effective and with real time performance. Without bells and whistles the proposed object proposal network significantly improves the AR at 1,000 proposals by $35\%$ and $45\%$ on PASCAL VOC and COCO dataset respectively and has a fast inference time of 44.8 ms for input image size of $640^{2}$. Empirical studies have also shown that the proposed method is class-agnostic to be generalised for general object proposal.
In object detection, the detection backbone consumes more than half of the overall inference cost. Recent researches attempt to reduce this cost by optimizing the backbone architecture with the help of Neural Architecture Search (NAS). However, existing NAS methods for object detection require hundreds to thousands of GPU hours of searching, making them impractical in fast-paced research and development. In this work, we propose a novel zero-shot NAS method to address this issue. The proposed method, named MAE-DET, automatically designs efficient detection backbones via the Maximum Entropy Principle without training network parameters, reducing the architecture design cost to nearly zero yet delivering the state-of-the-art (SOTA) performance. Under the hood, MAE-DET maximizes the differential entropy of detection backbones, leading to a better feature extractor for object detection under the same computational budgets. After merely one GPU day of fully automatic design, MAE-DET innovates SOTA detection backbones on multiple detection benchmark datasets with little human intervention. Comparing to ResNet-50 backbone, MAE-DET is $+2.0\%$ better in mAP when using the same amount of FLOPs/parameters, and is $1.54$ times faster on NVIDIA V100 at the same mAP. Code and pre-trained models are available at https://github.com/alibaba/lightweight-neuralarchitecture-search.
This paper proposes a novel method to estimate the global scale of a 3D reconstructed model within a Kalman filtering-based monocular SLAM algorithm. Our Bayesian framework integrates height priors over the detected objects belonging to a set of broad predefined classes, based on recent advances in fast generic object detection. Each observation is produced on single frames, so that we do not need a data association process along video frames. This is because we associate the height priors with the image region sizes at image places where map features projections fall within the object detection regions. We present very promising results of this approach obtained on several experiments with different object classes.
A General Underwater Object Detector (GUOD) should perform well on most of underwater circumstances. However, with limited underwater dataset, conventional object detection methods suffer from domain shift severely. This paper aims to build a GUOD with small underwater dataset with limited types of water quality. First, we propose a data augmentation method Water Quality Transfer (WQT) to increase domain diversity of the original small dataset. Second, for mining the semantic information from data generated by WQT, DG-YOLO is proposed, which consists of three parts: YOLOv3, DIM and IRM penalty. Finally, experiments on original and synthetic URPC2019 dataset prove that WQT+DG-YOLO achieves promising performance of domain generalization in underwater object detection.
To address the challenges of providing quick and plausible explanations in Explainable AI (XAI) for object detection models, we introduce the Gaussian Class Activation Mapping Explainer (G-CAME). Our method efficiently generates concise saliency maps by utilizing activation maps from selected layers and applying a Gaussian kernel to emphasize critical image regions for the predicted object. Compared with other Region-based approaches, G-CAME significantly reduces explanation time to 0.5 seconds without compromising the quality. Our evaluation of G-CAME, using Faster-RCNN and YOLOX on the MS-COCO 2017 dataset, demonstrates its ability to offer highly plausible and faithful explanations, especially in reducing the bias on tiny object detection.
This paper addresses the problem of how to exploit spatio-temporal information available in videos to improve the object detection precision. We propose a two stage object detector called FANet based on short-term spatio-temporal feature aggregation to give a first detection set, and long-term object linking to refine these detections. Firstly, we generate a set of short tubelet proposals containing the object in $N$ consecutive frames. Then, we aggregate RoI pooled deep features through the tubelet using a temporal pooling operator that summarizes the information with a fixed size output independent of the number of input frames. On top of that, we define a double head implementation that we feed with spatio-temporal aggregated information for spatio-temporal object classification, and with spatial information extracted from the current frame for object localization and spatial classification. Furthermore, we also specialize each head branch architecture to better perform in each task taking into account the input data. Finally, a long-term linking method builds long tubes using the previously calculated short tubelets to overcome detection errors. We have evaluated our model in the widely used ImageNet VID dataset achieving a 80.9% mAP, which is the new state-of-the-art result for single models. Also, in the challenging small object detection dataset USC-GRAD-STDdb, our proposal outperforms the single frame baseline by 5.4% mAP.
In this paper, we propose a method for ensembling the outputs of multiple object detectors for improving detection performance and precision of bounding boxes on image data. We further extend it to video data by proposing a two-stage tracking-based scheme for detection refinement. The proposed method can be used as a standalone approach for improving object detection performance, or as a part of a framework for faster bounding box annotation in unseen datasets, assuming that the objects of interest are those present in some common public datasets.
This paper proposes MCSSL, a self-supervised learning approach for building custom object detection models in multi-camera networks. MCSSL associates bounding boxes between cameras with overlapping fields of view by leveraging epipolar geometry and state-of-the-art tracking and reID algorithms, and prudently generates two sets of pseudo-labels to fine-tune backbone and detection networks respectively in an object detection model. To train effectively on pseudo-labels,a powerful reID-like pretext task with consistency loss is constructed for model customization. Our evaluation shows that compared with legacy selftraining methods, MCSSL improves average mAP by 5.44% and 6.76% on WildTrack and CityFlow dataset, respectively.
Object detection is the task of detecting objects in an image. In this task, the detection of small objects is particularly difficult. Other than the small size, it is also accompanied by difficulties due to blur, occlusion, and so on. Current small object detection methods are tailored to small and dense situations, such as pedestrians in a crowd or far objects in remote sensing scenarios. However, when the target object is small and sparse, there is a lack of objects available for training, making it more difficult to learn effective features. In this paper, we propose a specialized method for detecting a specific category of small objects; birds. Particularly, we improve the features learned by the neck; the sub-network between the backbone and the prediction head, to learn more effective features with a hierarchical design. We employ Swin Transformer to upsample the image features. Moreover, we change the shifted window size for adapting to small objects. Experiments show that the proposed Swin Transformer-based neck combined with CenterNet can lead to good performance by changing the window sizes. We further find that smaller window sizes (default 2) benefit mAPs for small object detection.
Although LiDAR sensors are crucial for autonomous systems due to providing precise depth information, they struggle with capturing fine object details, especially at a distance, due to sparse and non-uniform data. Recent advances introduced pseudo-LiDAR, i.e., synthetic dense point clouds, using additional modalities such as cameras to enhance 3D object detection. We present a novel LiDAR-only framework that augments raw scans with denser pseudo point clouds by solely relying on LiDAR sensors and scene semantics, omitting the need for cameras. Our framework first utilizes a segmentation model to extract scene semantics from raw point clouds, and then employs a multi-modal domain translator to generate synthetic image segments and depth cues without real cameras. This yields a dense pseudo point cloud enriched with semantic information. We also introduce a new semantically guided projection method, which enhances detection performance by retaining only relevant pseudo points. We applied our framework to different advanced 3D object detection methods and reported up to 2.9% performance upgrade. We also obtained comparable results on the KITTI 3D object detection dataset, in contrast to other state-of-the-art LiDAR-only detectors.
In autonomous driving, the temporal stability of 3D object detection greatly impacts the driving safety. However, the detection stability cannot be accessed by existing metrics such as mAP and MOTA, and consequently is less explored by the community. To bridge this gap, this work proposes Stability Index (SI), a new metric that can comprehensively evaluate the stability of 3D detectors in terms of confidence, box localization, extent, and heading. By benchmarking state-of-the-art object detectors on the Waymo Open Dataset, SI reveals interesting properties of object stability that have not been previously discovered by other metrics. To help models improve their stability, we further introduce a general and effective training strategy, called Prediction Consistency Learning (PCL). PCL essentially encourages the prediction consistency of the same objects under different timestamps and augmentations, leading to enhanced detection stability. Furthermore, we examine the effectiveness of PCL with the widely-used CenterPoint, and achieve a remarkable SI of 86.00 for vehicle class, surpassing the baseline by 5.48. We hope our work could serve as a reliable baseline and draw the community's attention to this crucial issue in 3D object detection. Codes will be made publicly available.
Object detection shows promise for medical and surgical applications such as cell counting and tool tracking. However, its faces multiple real-world edge deployment challenges including limited high-quality annotated data, data sharing restrictions, and computational constraints. In this work, we introduce UltraFlwr, a framework for federated medical and surgical object detection. By leveraging Federated Learning (FL), UltraFlwr enables decentralized model training across multiple sites without sharing raw data. To further enhance UltraFlwr's efficiency, we propose YOLO-PA, a set of novel Partial Aggregation (PA) strategies specifically designed for YOLO models in FL. YOLO-PA significantly reduces communication overhead by up to 83% per round while maintaining performance comparable to Full Aggregation (FA) strategies. Our extensive experiments on BCCD and m2cai16-tool-locations datasets demonstrate that YOLO-PA not only provides better client models compared to client-wise centralized training and FA strategies, but also facilitates efficient training and deployment across resource-constrained edge devices. Further, we also establish one of the first benchmarks in federated medical and surgical object detection. This paper advances the feasibility of training and deploying detection models on the edge, making federated object detection more practical for time-critical and resource-constrained medical and surgical applications. UltraFlwr is publicly available at https://github.com/KCL-BMEIS/UltraFlwr.
We study the problem of detecting human-object interactions (HOI) in static images, defined as predicting a human and an object bounding box with an interaction class label that connects them. HOI detection is a fundamental problem in computer vision as it provides semantic information about the interactions among the detected objects. We introduce HICO-DET, a new large benchmark for HOI detection, by augmenting the current HICO classification benchmark with instance annotations. To solve the task, we propose Human-Object Region-based Convolutional Neural Networks (HO-RCNN). At the core of our HO-RCNN is the Interaction Pattern, a novel DNN input that characterizes the spatial relations between two bounding boxes. Experiments on HICO-DET demonstrate that our HO-RCNN, by exploiting human-object spatial relations through Interaction Patterns, significantly improves the performance of HOI detection over baseline approaches.
Automatic detection of traffic accidents is an important emerging topic in traffic monitoring systems. Nowadays many urban intersections are equipped with surveillance cameras connected to traffic management systems. Therefore, computer vision techniques can be viable tools for automatic accident detection. This paper presents a new efficient framework for accident detection at intersections for traffic surveillance applications. The proposed framework consists of three hierarchical steps, including efficient and accurate object detection based on the state-of-the-art YOLOv4 method, object tracking based on Kalman filter coupled with the Hungarian algorithm for association, and accident detection by trajectory conflict analysis. A new cost function is applied for object association to accommodate for occlusion, overlapping objects, and shape changes in the object tracking step. The object trajectories are analyzed in terms of velocity, angle, and distance in order to detect different types of trajectory conflicts including vehicle-to-vehicle, vehicle-to-pedestrian, and vehicle-to-bicycle. Experimental results using real traffic video data show the feasibility of the proposed method in real-time applications of traffic surveillance. In particular, trajectory conflicts, including near-accidents and accidents occurring at urban intersections are detected with a low false alarm rate and a high detection rate. The robustness of the proposed framework is evaluated using video sequences collected from YouTube with diverse illumination conditions. The dataset is publicly available at: http://github.com/hadi-ghnd/AccidentDetection.
Object detection in Remote Sensing Images (RSI) is a critical task for numerous applications in Earth Observation (EO). Differing from object detection in natural images, object detection in remote sensing images faces challenges of scarcity of annotated data and the presence of small objects represented by only a few pixels. Multi-modal fusion has been determined to enhance the accuracy by fusing data from multiple modalities such as RGB, infrared (IR), lidar, and synthetic aperture radar (SAR). To this end, the fusion of representations at the mid or late stage, produced by parallel subnetworks, is dominant, with the disadvantages of increasing computational complexity in the order of the number of modalities and the creation of additional engineering obstacles. Using the cross-attention mechanism, we propose a novel multi-modal fusion strategy for mapping relationships between different channels at the early stage, enabling the construction of a coherent input by aligning the different modalities. By addressing fusion in the early stage, as opposed to mid or late-stage methods, our method achieves competitive and even superior performance compared to existing techniques. Additionally, we enhance the SWIN transformer by integrating convolution layers into the feed-forward of non-shifting blocks. This augmentation strengthens the model's capacity to merge separated windows through local attention, thereby improving small object detection. Extensive experiments prove the effectiveness of the proposed multimodal fusion module and the architecture, demonstrating their applicability to object detection in multimodal aerial imagery.
Visual relationship detection is fundamental for holistic image understanding. However, localizing and classifying (subject, predicate, object) triplets constitutes a hard learning objective due to the combinatorial explosion of possible relationships, their long-tail distribution in natural images, and an expensive annotation process. This paper introduces a novel weakly-supervised method for visual relationship detection that relies only on image-level predicate annotations. A graph neural network is trained to classify the predicates in an image from the graph representation of all objects, implicitly encoding an inductive bias for pairwise relationships. We then frame relationship detection as the explanation of such a predicate classifier, i.e. we reconstruct a complete relationship by recovering the subject and the object of a predicted predicate. Using this novel technique and minimal labels, we present comparable results to recent fully-supervised and weakly-supervised methods on three diverse and challenging datasets: HICO-DET for human-object interaction, Visual Relationship Detection for generic object-to-object relationships, and UnRel for unusual relationships.
Building reliable object detectors that can detect out-of-distribution (OOD) objects is critical yet underexplored. One of the key challenges is that models lack supervision signals from unknown data, producing overconfident predictions on OOD objects. We propose a new unknown-aware object detection framework through Spatial-Temporal Unknown Distillation (STUD), which distills unknown objects from videos in the wild and meaningfully regularizes the model's decision boundary. STUD first identifies the unknown candidate object proposals in the spatial dimension, and then aggregates the candidates across multiple video frames to form a diverse set of unknown objects near the decision boundary. Alongside, we employ an energy-based uncertainty regularization loss, which contrastively shapes the uncertainty space between the in-distribution and distilled unknown objects. STUD establishes the state-of-the-art performance on OOD detection tasks for object detection, reducing the FPR95 score by over 10% compared to the previous best method. Code is available at https://github.com/deeplearning-wisc/stud.
In this work, we pioneer the study of open-vocabulary monocular 3D object detection, a novel task that aims to detect and localize objects in 3D space from a single RGB image without limiting detection to a predefined set of categories. We formalize this problem, establish baseline methods, and introduce a class-agnostic approach that leverages open-vocabulary 2D detectors and lifts 2D bounding boxes into 3D space. Our approach decouples the recognition and localization of objects in 2D from the task of estimating 3D bounding boxes, enabling generalization across unseen categories. Additionally, we propose a target-aware evaluation protocol to address inconsistencies in existing datasets, improving the reliability of model performance assessment. Extensive experiments on the Omni3D dataset demonstrate the effectiveness of the proposed method in zero-shot 3D detection for novel object categories, validating its robust generalization capabilities. Our method and evaluation protocols contribute towards the development of open-vocabulary object detection models that can effectively operate in real-world, category-diverse environments.