Over the past few years, there has been remarkable progress in research on 3D point clouds and their use in autonomous driving scenarios has become widespread. However, deep learning methods heavily rely on annotated data and often face domain generalization issues. Unlike 2D images whose domains usually pertain to the texture information present in them, the features derived from a 3D point cloud are affected by the distribution of the points. The lack of a 3D domain adaptation benchmark leads to the common practice of training a model on one benchmark (e.g. Waymo) and then assessing it on another dataset (e.g. KITTI). This setting results in two distinct domain gaps: scenarios and sensors, making it difficult to analyze and evaluate the method accurately. To tackle this problem, this paper presents LiDAR Dataset with Cross Sensors (LiDAR-CS Dataset), which contains large-scale annotated LiDAR point cloud under six groups of different sensors but with the same corresponding scenarios, captured from hybrid realistic LiDAR simulator. To our knowledge, LiDAR-CS Dataset is the first dataset that addresses the sensor-related gaps in the domain of 3D object detection in real traffic. Furthermore, we evaluate and analyze the performance using various baseline detectors and demonstrated its potential applications. Project page: https://opendriving.github.io/lidar-cs.
In the field of visual representation learning, performance of contrastive learning has been catching up with the supervised method which is commonly a classification convolutional neural network. However, most of the research work focuses on improving the accuracy of downstream tasks such as image classification and object detection. For visual contrastive learning, the influences of individual image features (e.g., color and shape) to model performance remain ambiguous. This paper investigates such influences by designing various ablation experiments, the results of which are evaluated by specifically designed metrics. While these metrics are not invented by us, we first use them in the field of representation evaluation. Specifically, we assess the contribution of two primary image features (i.e., color and shape) in a quantitative way. Experimental results show that compared with supervised representations, contrastive representations tend to cluster with objects of similar color in the representation space, and contain less shape information than supervised representations. Finally, we discuss that the current data augmentation is responsible for these results. We believe that exploring an unsupervised augmentation method that
The past few years have seen an increased interest in aerial image object detection due to its critical value to large-scale geo-scientific research like environmental studies, urban planning, and intelligence monitoring. However, the task is very challenging due to the birds-eye view perspective, complex backgrounds, large and various image sizes, different appearances of objects, and the scarcity of well-annotated datasets. Recent advances in computer vision have shown promise tackling the challenge. Specifically, Vision Transformer Detector (ViTDet) was proposed to extract multi-scale features for object detection. The empirical study shows that ViTDet's simple design achieves good performance on natural scene images and can be easily embedded into any detector architecture. To date, ViTDet's potential benefit to challenging aerial image object detection has not been explored. Therefore, in our study, 25 experiments were carried out to evaluate the effectiveness of ViTDet for aerial image object detection on three well-known datasets: Airbus Aircraft, RarePlanes, and Dataset of Object DeTection in Aerial images (DOTA). Our results show that ViTDet can consistently outperform its convolutional neural network counterparts on horizontal bounding box (HBB) object detection by a large margin (up to 17% on average precision) and that it achieves the competitive performance for oriented bounding box (OBB) object detection. Our results also establish a baseline for future research.
Since the introduction of Vision Transformers, the landscape of many computer vision tasks (e.g., semantic segmentation), which has been overwhelmingly dominated by CNNs, recently has significantly revolutionized. However, the computational cost and memory requirement renders these methods unsuitable on the mobile device. In this paper, we introduce a new method squeeze-enhanced Axial Transformer (SeaFormer) for mobile visual recognition. Specifically, we design a generic attention block characterized by the formulation of squeeze Axial and detail enhancement. It can be further used to create a family of backbone architectures with superior cost-effectiveness. Coupled with a light segmentation head, we achieve the best trade-off between segmentation accuracy and latency on the ARM-based mobile devices on the ADE20K, Cityscapes, Pascal Context and COCO-Stuff datasets. Critically, we beat both the mobilefriendly rivals and Transformer-based counterparts with better performance and lower latency without bells and whistles. Furthermore, we incorporate a feature upsampling-based multi-resolution distillation technique, further reducing the inference latency of the proposed framework. Beyond semantic segmentation, we further apply the proposed SeaFormer architecture to image classification and object detection problems, demonstrating the potential of serving as a versatile mobile-friendly backbone. Our code and models are made publicly available at https://github.com/fudan-zvg/SeaFormer.
Infrared small object detection (ISOS) aims to segment small objects only covered with several pixels from clutter background in infrared images. It's of great challenge due to: 1) small objects lack of sufficient intensity, shape and texture information; 2) small objects are easily lost in the process where detection models, say deep neural networks, obtain high-level semantic features and image-level receptive fields through successive downsampling. This paper proposes a reliable detection model for ISOS, dubbed UCFNet, which can handle well the two issues. It builds upon central difference convolution (CDC) and fast Fourier convolution (FFC). On one hand, CDC can effectively guide the network to learn the contrast information between small objects and the background, as the contrast information is very essential in human visual system dealing with the ISOS task. On the other hand, FFC can gain image-level receptive fields and extract global information while preventing small objects from being overwhelmed.Experiments on several public datasets demonstrate that our method significantly outperforms the state-of-the-art ISOS models, and can provide useful guidelines for designing better ISOS deep models. Code are available at https://github.com/wcyjerry/BasicISOS.
In this paper we extensively explore the suitability of YOLO architectures to monitor the process flow across a Fischertechnik industry 4.0 application. Specifically, different YOLO architectures in terms of size and complexity design along with different prior-shapes assignment strategies are adopted. To simulate the real world factory environment, we prepared a rich dataset augmented with different distortions that highly enhance and in some cases degrade our image qualities. The degradation is performed to account for environmental variations and enhancements opt to compensate the color correlations that we face while preparing our dataset. The analysis of our conducted experiments shows the effectiveness of the presented approach evaluated using different measures along with the training and validation strategies that we tailored to tackle the unavoidable color correlations that the problem at hand inherits by nature.
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change the prediction result. Existing adversarial attacks on object detection focus on attacking anchor-based detectors, which may not work well for anchor-free detectors. In this paper, we propose the first adversarial attack dedicated to anchor-free detectors. It is a category-wise attack that attacks important pixels of all instances of a category simultaneously. Our attack manifests in two forms, sparse category-wise attack (SCA) and dense category-wise attack (DCA), that minimize the $L_0$ and $L_\infty$ norm-based perturbations, respectively. For DCA, we present three variants, DCA-G, DCA-L, and DCA-S, that select a global region, a local region, and a semantic region, respectively, to attack. Our experiments on large-scale benchmark datasets including PascalVOC, MS-COCO, and MS-COCO Keypoints indicate that our proposed methods achieve state-of-the-art attack performance and transferability on both object detection and human pose estimation tasks.
In this thesis, we study multiple tasks related to document layout analysis such as the detection of text lines, the splitting into acts or the detection of the writing support. Thus, we propose two deep neural models following two different approaches. We aim at proposing a model for object detection that considers the difficulties associated with document processing, including the limited amount of training data available. In this respect, we propose a pixel-level detection model and a second object-level detection model. We first propose a detection model with few parameters, fast in prediction, and which can obtain accurate prediction masks from a reduced number of training data. We implemented a strategy of collection and uniformization of many datasets, which are used to train a single line detection model that demonstrates high generalization capabilities to out-of-sample documents. We also propose a Transformer-based detection model. The design of such a model required redefining the task of object detection in document images and to study different approaches. Following this study, we propose an object detection strategy consisting in sequentially predicting the coordinates of the objects enclosing rectangles through a pixel classification. This strategy allows obtaining a fast model with only few parameters. Finally, in an industrial setting, new non-annotated data are often available. Thus, in the case of a model adaptation to this new data, it is expected to provide the system as few new annotated samples as possible. The selection of relevant samples for manual annotation is therefore crucial to enable successful adaptation. For this purpose, we propose confidence estimators from different approaches for object detection. We show that these estimators greatly reduce the amount of annotated data while optimizing the performances.
We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models. We leverage the property of self-supervised models to 'discover' objects without supervision and amplify it to train a state-of-the-art localization model without any human labels. CutLER first uses our proposed MaskCut approach to generate coarse masks for multiple objects in an image and then learns a detector on these masks using our robust loss function. We further improve the performance by self-training the model on its predictions. Compared to prior work, CutLER is simpler, compatible with different detection architectures, and detects multiple objects. CutLER is also a zero-shot unsupervised detector and improves detection performance AP50 by over 2.7 times on 11 benchmarks across domains like video frames, paintings, sketches, etc. With finetuning, CutLER serves as a low-shot detector surpassing MoCo-v2 by 7.3% APbox and 6.6% APmask on COCO when training with 5% labels.
We explore the extent to which zero-shot vision-language models exhibit gender bias for different vision tasks. Vision models traditionally required task-specific labels for representing concepts, as well as finetuning; zero-shot models like CLIP instead perform tasks with an open-vocabulary, meaning they do not need a fixed set of labels, by using text embeddings to represent concepts. With these capabilities in mind, we ask: Do vision-language models exhibit gender bias when performing zero-shot image classification, object detection and semantic segmentation? We evaluate different vision-language models with multiple datasets across a set of concepts and find (i) all models evaluated show distinct performance differences based on the perceived gender of the person co-occurring with a given concept in the image and that aggregating analyses over all concepts can mask these concerns; (ii) model calibration (i.e. the relationship between accuracy and confidence) also differs distinctly by perceived gender, even when evaluating on similar representations of concepts; and (iii) these observed disparities align with existing gender biases in word embeddings from language models. These findings suggest that, while language greatly expands the capability of vision tasks, it can also contribute to social biases in zero-shot vision settings. Furthermore, biases can further propagate when foundational models like CLIP are used by other models to enable zero-shot capabilities.
The generalization power of the pre-trained model is the key for few-shot deep learning. Dropout is a regularization technique used in traditional deep learning methods. In this paper, we explore the power of dropout on few-shot learning and provide some insights about how to use it. Extensive experiments on the few-shot object detection and few-shot image classification datasets, i.e., Pascal VOC, MS COCO, CUB, and mini-ImageNet, validate the effectiveness of our method.
In recent years, camera-based 3D object detection has gained widespread attention for its ability to achieve high performance with low computational cost. However, the robustness of these methods to adversarial attacks has not been thoroughly examined, especially when considering their deployment in safety-critical domains like autonomous driving. In this study, we conduct the first comprehensive investigation of the robustness of leading camera-based 3D object detection approaches under various adversarial conditions. We systematically analyze the resilience of these models under two attack settings: white-box and black-box; focusing on two primary objectives: classification and localization. Additionally, we delve into two types of adversarial attack techniques: pixel-based and patch-based. Our experiments yield four interesting findings: (a) bird's-eye-view-based representations exhibit stronger robustness against localization attacks; (b) depth-estimation-free approaches have the potential to show stronger robustness; (c) accurate depth estimation effectively improves robustness for depth-estimation-based methods; (d) incorporating multi-frame benign inputs can effectively mitigate adversarial attacks. We hope our findings can steer the development of future camera-based object detection models with enhanced adversarial robustness.
Most existing perception systems rely on sensory data acquired from cameras, which perform poorly in low light and adverse weather conditions. To resolve this limitation, we have witnessed advanced LiDAR sensors become popular in perception tasks in autonomous driving applications. Nevertheless, their usage in traffic monitoring systems is less ubiquitous. We identify two significant obstacles in cost-effectively and efficiently developing such a LiDAR-based traffic monitoring system: (i) public LiDAR datasets are insufficient for supporting perception tasks in infrastructure systems, and (ii) 3D annotations on LiDAR point clouds are time-consuming and expensive. To fill this gap, we present an efficient semi-automated annotation tool that automatically annotates LiDAR sequences with tracking algorithms while offering a fully annotated infrastructure LiDAR dataset -- FLORIDA (Florida LiDAR-based Object Recognition and Intelligent Data Annotation) -- which will be made publicly available. Our advanced annotation tool seamlessly integrates multi-object tracking (MOT), single-object tracking (SOT), and suitable trajectory post-processing techniques. Specifically, we introduce a human-in-the-loop schema in which annotators recursively fix and refine annotations imperfectly predicted by our tool and incrementally add them to the training dataset to obtain better SOT and MOT models. By repeating the process, we significantly increase the overall annotation speed by three to four times and obtain better qualitative annotations than a state-of-the-art annotation tool. The human annotation experiments verify the effectiveness of our annotation tool. In addition, we provide detailed statistics and object detection evaluation results for our dataset in serving as a benchmark for perception tasks at traffic intersections.
Neural Architecture Search (NAS) is quickly becoming the go-to approach to optimize the structure of Deep Learning (DL) models for complex tasks such as Image Classification or Object Detection. However, many other relevant applications of DL, especially at the edge, are based on time-series processing and require models with unique features, for which NAS is less explored. This work focuses in particular on Temporal Convolutional Networks (TCNs), a convolutional model for time-series processing that has recently emerged as a promising alternative to more complex recurrent architectures. We propose the first NAS tool that explicitly targets the optimization of the most peculiar architectural parameters of TCNs, namely dilation, receptive-field and number of features in each layer. The proposed approach searches for networks that offer good trade-offs between accuracy and number of parameters/operations, enabling an efficient deployment on embedded platforms. We test the proposed NAS on four real-world, edge-relevant tasks, involving audio and bio-signals. Results show that, starting from a single seed network, our method is capable of obtaining a rich collection of Pareto optimal architectures, among which we obtain models with the same accuracy as the seed, and 15.9-152x fewer parameters. Compared to three state-of-the-art NAS tools, ProxylessNAS, MorphNet and FBNetV2, our method explores a larger search space for TCNs (up to 10^12x) and obtains superior solutions, while requiring low GPU memory and search time. We deploy our NAS outputs on two distinct edge devices, the multicore GreenWaves Technology GAP8 IoT processor and the single-core STMicroelectronics STM32H7 microcontroller. With respect to the state-of-the-art hand-tuned models, we reduce latency and energy of up to 5.5x and 3.8x on the two targets respectively, without any accuracy loss.
Detecting objects in a video, known as Video Object Detection (VOD), is challenging since appearance changes of objects over time may bring detection errors. Recent research has focused on aggregating features from adjacent frames to compensate for the deteriorated appearances of a frame. Moreover, using distant frames is also proposed to deal with deteriorated appearances over several frames. Since an object’s position may change significantly at a distant frame, they only use features of object candidate regions, which do not depend on their position. However, such methods rely on object candidate regions’ detection performance and are not practical for deteriorated appearances. In this paper, we enhance features element-wisely before the object candidate region detection, proposing Video Sparse Transformer with Attention-guided Memory (VSTAM). Furthermore, we propose aggregating element-wise features sparsely to reduce processing time and memory cost. In addition, we introduce an external memory update strategy based on the utilization of the aggregation to hold long-term information effectively. Our method achieved 8.3% and 11.1% accuracy gain from the baseline on ImageNet VID and UA-DETRAC datasets. Our method demonstrates superior performance against state-of-the-art results on widely used VOD datasets.
We investigate the effect of style and category similarity in multiple datasets used for object detection pretraining. We find that including an additional stage of object-detection pretraining can increase the detection performance considerably. While our experiments suggest that style similarities between pre-training and target datasets are less important than matching categories, further experiments are needed to verify this hypothesis.
The Odeuropa Challenge on Olfactory Object Recognition aims to foster the development of object detection in the visual arts and to promote an olfactory perspective on digital heritage. Object detection in historical artworks is particularly challenging due to varying styles and artistic periods. Moreover, the task is complicated due to the particularity and historical variance of predefined target objects, which exhibit a large intra-class variance, and the long tail distribution of the dataset labels, with some objects having only very few training examples. These challenges should encourage participants to create innovative approaches using domain adaptation or few-shot learning. We provide a dataset of 2647 artworks annotated with 20 120 tightly fit bounding boxes that are split into a training and validation set (public). A test set containing 1140 artworks and 15 480 annotations is kept private for the challenge evaluation.
Large-scale object detection and instance segmentation face a severe data imbalance. The finer-grained object classes become, the less frequent they appear in our datasets. However, at test-time, we expect a detector that performs well for all classes and not just the most frequent ones. In this paper, we provide a theoretical understanding of the long-trail detection problem. We show how the commonly used mean average precision evaluation metric on an unknown test set is bound by a margin-based binary classification error on a long-tailed object detection training set. We optimize margin-based binary classification error with a novel surrogate objective called \textbf{Effective Class-Margin Loss} (ECM). The ECM loss is simple, theoretically well-motivated, and outperforms other heuristic counterparts on LVIS v1 benchmark over a wide range of architecture and detectors. Code is available at \url{https://github.com/janghyuncho/ECM-Loss}.
Object recognition systems are usually trained and evaluated on high resolution images. However, in real world applications, it is common that the images have low resolutions or have small sizes. In this study, we first track the performance of the state-of-the-art deep object recognition network, Faster- RCNN, as a function of image resolution. The results reveals negative effects of low resolution images on recognition performance. They also show that different spatial frequencies convey different information about the objects in recognition process. It means multi-resolution recognition system can provides better insight into optimal selection of features that results in better recognition of objects. This is similar to the mechanisms of the human visual systems that are able to implement multi-scale representation of a visual scene simultaneously. Then, we propose a multi-resolution object recognition framework rather than a single-resolution network. The proposed framework is evaluated on the PASCAL VOC2007 database. The experimental results show the performance of our adapted multi-resolution Faster-RCNN framework outperforms the single-resolution Faster-RCNN on input images with various resolutions with an increase in the mean Average Precision (mAP) of 9.14% across all resolutions and 1.2% on the full-spectrum images. Furthermore, the proposed model yields robustness of the performance over a wide range of spatial frequencies.
Future collaborative robots must be capable of finding objects. As such a fundamental skill, we expect object search to eventually become an off-the-shelf capability for any robot, similar to e.g., object detection, SLAM, and motion planning. However, existing approaches either make unrealistic compromises (e.g., reduce the problem from 3D to 2D), resort to ad-hoc, greedy search strategies, or attempt to learn end-to-end policies in simulation that are yet to generalize across real robots and environments. This thesis argues that through using Partially Observable Markov Decision Processes (POMDPs) to model object search while exploiting structures in the human world (e.g., octrees, correlations) and in human-robot interaction (e.g., spatial language), a practical and effective system for generalized object search can be achieved. In support of this argument, I develop methods and systems for (multi-)object search in 3D environments under uncertainty due to limited field of view, occlusion, noisy, unreliable detectors, spatial correlations between objects, and possibly ambiguous spatial language (e.g., "The red car is behind Chase Bank"). Besides evaluation in simulators such as PyGame, AirSim, and AI2-THOR, I design and implement a robot-independent, environment-agnostic system for generalized object search in 3D and deploy it on the Boston Dynamics Spot robot, the Kinova MOVO robot, and the Universal Robots UR5e robotic arm, to perform object search in different environments. The system enables, for example, a Spot robot to find a toy cat hidden underneath a couch in a kitchen area in under one minute. This thesis also broadly surveys the object search literature, proposing taxonomies in object search problem settings, methods and systems.