This paper introduces the point-axis representation for oriented object detection, emphasizing its flexibility and geometrically intuitive nature with two key components: points and axes. 1) Points delineate the spatial extent and contours of objects, providing detailed shape descriptions. 2) Axes define the primary directionalities of objects, providing essential orientation cues crucial for precise detection. The point-axis representation decouples location and rotation, addressing the loss discontinuity issues commonly encountered in traditional bounding box-based approaches. For effective optimization without introducing additional annotations, we propose the max-projection loss to supervise point set learning and the cross-axis loss for robust axis representation learning. Further, leveraging this representation, we present the Oriented DETR model, seamlessly integrating the DETR framework for precise point-axis prediction and end-to-end detection. Experimental results demonstrate significant performance improvements in oriented object detection tasks.
The impressive advancements in semi-supervised learning have driven researchers to explore its potential in object detection tasks within the field of computer vision. Semi-Supervised Object Detection (SSOD) leverages a combination of a small labeled dataset and a larger, unlabeled dataset. This approach effectively reduces the dependence on large labeled datasets, which are often expensive and time-consuming to obtain. Initially, SSOD models encountered challenges in effectively leveraging unlabeled data and managing noise in generated pseudo-labels for unlabeled data. However, numerous recent advancements have addressed these issues, resulting in substantial improvements in SSOD performance. This paper presents a comprehensive review of 27 cutting-edge developments in SSOD methodologies, from Convolutional Neural Networks (CNNs) to Transformers. We delve into the core components of semi-supervised learning and its integration into object detection frameworks, covering data augmentation techniques, pseudo-labeling strategies, consistency regularization, and adversarial training methods. Furthermore, we conduct a comparative analysis of various SSOD models, evaluating their performance and architectural differences. We aim to ignite further research interest in overcoming existing challenges and exploring new directions in semi-supervised learning for object detection.
The performance of object detection systems in automotive solutions must be as high as possible, with minimal response time and, due to the often battery-powered operation, low energy consumption. When designing such solutions, we therefore face challenges typical for embedded vision systems: the problem of fitting algorithms of high memory and computational complexity into small low-power devices. In this paper we propose PowerYOLO - a mixed precision solution, which targets three essential elements of such application. First, we propose a system based on a Dynamic Vision Sensor (DVS), a novel sensor, that offers low power requirements and operates well in conditions with variable illumination. It is these features that may make event cameras a preferential choice over frame cameras in some applications. Second, to ensure high accuracy and low memory and computational complexity, we propose to use 4-bit width Powers-of-Two (PoT) quantisation for convolution weights of the YOLO detector, with all other parameters quantised linearly. Finally, we embrace from PoT scheme and replace multiplication with bit-shifting to increase the efficiency of hardware acceleration of such solution, with a special convolution-batch normalisation fusion scheme. The use of specific sensor with PoT quantisation and special batch normalisation fusion leads to a unique system with almost 8x reduction in memory complexity and vast computational simplifications, with relation to a standard approach. This efficient system achieves high accuracy of mAP 0.301 on the GEN1 DVS dataset, marking the new state-of-the-art for such compressed model.
Data augmentation remains a widely utilized technique in deep learning, particularly in tasks such as image classification, semantic segmentation, and object detection. Among them, Copy-Paste is a simple yet effective method and gain great attention recently. However, existing Copy-Paste often overlook contextual relevance between source and target images, resulting in inconsistencies in generated outputs. To address this challenge, we propose a context-aware approach that integrates Bidirectional Latent Information Propagation (BLIP) for content extraction from source images. By matching extracted content information with category information, our method ensures cohesive integration of target objects using Segment Anything Model (SAM) and You Only Look Once (YOLO). This approach eliminates the need for manual annotation, offering an automated and user-friendly solution. Experimental evaluations across diverse datasets demonstrate the effectiveness of our method in enhancing data diversity and generating high-quality pseudo-images across various computer vision tasks.
Multispectral oriented object detection faces challenges due to both inter-modal and intra-modal discrepancies. Recent studies often rely on transformer-based models to address these issues and achieve cross-modal fusion detection. However, the quadratic computational complexity of transformers limits their performance. Inspired by the efficiency and lower complexity of Mamba in long sequence tasks, we propose Disparity-guided Multispectral Mamba (DMM), a multispectral oriented object detection framework comprised of a Disparity-guided Cross-modal Fusion Mamba (DCFM) module, a Multi-scale Target-aware Attention (MTA) module, and a Target-Prior Aware (TPA) auxiliary task. The DCFM module leverages disparity information between modalities to adaptively merge features from RGB and IR images, mitigating inter-modal conflicts. The MTA module aims to enhance feature representation by focusing on relevant target regions within the RGB modality, addressing intra-modal variations. The TPA auxiliary task utilizes single-modal labels to guide the optimization of the MTA module, ensuring it focuses on targets and their local context. Extensive experiments on the DroneVehicle and VEDAI datasets demonstrate the effectiveness of our method, which outperforms state-of-the-art methods while maintaining computational efficiency. Code will be available at https://github.com/Another-0/DMM.
We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. Through a comprehensive ablation study, we demonstrate the feasibility of integrating Vision Transformers (ViT) with Mamba. Our results show that equipping the Mamba architecture with self-attention blocks in the final layers greatly improves its capacity to capture long-range spatial dependencies. Based on these findings, we introduce a family of MambaVision models with a hierarchical architecture to meet various design criteria. For classification on the ImageNet-1K dataset, MambaVision variants achieve state-of-the-art (SOTA) performance in terms of both Top-1 accuracy and throughput. In downstream tasks such as object detection, instance segmentation, and semantic segmentation on MS COCO and ADE20K datasets, MambaVision outperforms comparably sized backbones while demonstrating favorable performance. Code: https://github.com/NVlabs/MambaVision
Acquiring fine-grained object detection annotations in unconstrained images is time-consuming, expensive, and prone to noise, especially in crowdsourcing scenarios. Most prior object detection methods assume accurate annotations; A few recent works have studied object detection with noisy crowdsourced annotations, with evaluation on distinct synthetic crowdsourced datasets of varying setups under artificial assumptions. To address these algorithmic limitations and evaluation inconsistency, we first propose a novel Bayesian Detector Combination (BDC) framework to more effectively train object detectors with noisy crowdsourced annotations, with the unique ability of automatically inferring the annotators' label qualities. Unlike previous approaches, BDC is model-agnostic, requires no prior knowledge of the annotators' skill level, and seamlessly integrates with existing object detection models. Due to the scarcity of real-world crowdsourced datasets, we introduce large synthetic datasets by simulating varying crowdsourcing scenarios. This allows consistent evaluation of different models at scale. Extensive experiments on both real and synthetic crowdsourced datasets show that BDC outperforms existing state-of-the-art methods, demonstrating its superiority in leveraging crowdsourced data for object detection. Our code and data are available at https://github.com/zhiqin1998/bdc.
Models based on convolutional neural networks (CNN) and transformers have steadily been improved. They also have been applied in various computer vision downstream tasks. However, in object detection tasks, accurately localizing and classifying almost infinite categories of foods in images remains challenging. To address these problems, we first segmented the food as the region-of-interest (ROI) by using the segment-anything model (SAM) and masked the rest of the region except ROI as black pixels. This process simplified the problems into a single classification for which annotation and training were much simpler than object detection. The images in which only the ROI was preserved were fed as inputs to fine-tune various off-the-shelf models that encoded their own inductive biases. Among them, Data-efficient image Transformers (DeiTs) had the best classification performance. Nonetheless, when foods' shapes and textures were similar, the contextual features of the ROI-only images were not enough for accurate classification. Therefore, we introduced a novel type of combined architecture, RveRNet, which consisted of ROI, extra-ROI, and integration modules that allowed it to account for both the ROI's and global contexts. The RveRNet's F1 score was 10% better than other individual models when classifying ambiguous food images. If the RveRNet's modules were DeiT with the knowledge distillation from the CNN, performed the best. We investigated how architectures can be made robust against input noise caused by permutation and translocation. The results indicated that there was a trade-off between how much the CNN teacher's knowledge could be distilled to DeiT and DeiT's innate strength. Code is publicly available at: https://github.com/Seonwhee-Genome/RveRNet.
In recent years, numerous domain adaptive strategies have been proposed to help deep learning models overcome the challenges posed by domain shift. However, even unsupervised domain adaptive strategies still require a large amount of target data. Medical imaging datasets are often characterized by class imbalance and scarcity of labeled and unlabeled data. Few-shot domain adaptive object detection (FSDAOD) addresses the challenge of adapting object detectors to target domains with limited labeled data. Existing works struggle with randomly selected target domain images that may not accurately represent the real population, resulting in overfitting to small validation sets and poor generalization to larger test sets. Medical datasets exhibit high class imbalance and background similarity, leading to increased false positives and lower mean Average Precision (map) in target domains. To overcome these challenges, we propose a novel FSDAOD strategy for microscopic imaging. Our contributions include a domain adaptive class balancing strategy for few-shot scenarios, multi-layer instance-level inter and intra-domain alignment to enhance similarity between class instances regardless of domain, and an instance-level classification loss applied in the middle layers of the object detector to enforce feature retention necessary for correct classification across domains. Extensive experimental results with competitive baselines demonstrate the effectiveness of our approach, achieving state-of-the-art results on two public microscopic datasets. Code available at https://github.co/intelligentMachinesLab/few-shot-domain-adaptive-microscopy
This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research has proposed various solutions for Source-Free Object Detection (SFOD), most being variations of teacher-student architectures with diverse feature alignment, regularization and pseudo-label selection strategies. Our work investigates simpler approaches and their performance compared to more complex SFOD methods in several adaptation scenarios. We highlight the importance of batch normalization layers in the detector backbone, and show that adapting only the batch statistics is a strong baseline for SFOD. We propose a simple extension of a Mean Teacher with strong-weak augmentation in the source-free setting, Source-Free Unbiased Teacher (SF-UT), and show that it actually outperforms most of the previous SFOD methods. Additionally, we showcase that an even simpler strategy consisting in training on a fixed set of pseudo-labels can achieve similar performance to the more complex teacher-student mutual learning, while being computationally efficient and mitigating the major issue of teacher-student collapse. We conduct experiments on several adaptation tasks using benchmark driving datasets including (Foggy)Cityscapes, Sim10k and KITTI, and achieve a notable improvement of 4.7\% AP50 on Cityscapes$\rightarrow$Foggy-Cityscapes compared with the latest state-of-the-art in SFOD. Source code is available at https://github.com/EPFL-IMOS/simple-SFOD.
Open-vocabulary detection is a challenging task due to the requirement of detecting objects based on class names, including those not encountered during training. Existing methods have shown strong zero-shot detection capabilities through pre-training and pseudo-labeling on diverse large-scale datasets. However, these approaches encounter two main challenges: (i) how to effectively eliminate data noise from pseudo-labeling, and (ii) how to efficiently leverage the language-aware capability for region-level cross-modality fusion and alignment. To address these challenges, we propose a novel unified open-vocabulary detection method called OV-DINO, which is pre-trained on diverse large-scale datasets with language-aware selective fusion in a unified framework. Specifically, we introduce a Unified Data Integration (UniDI) pipeline to enable end-to-end training and eliminate noise from pseudo-label generation by unifying different data sources into detection-centric data format. In addition, we propose a Language-Aware Selective Fusion (LASF) module to enhance the cross-modality alignment through a language-aware query selection and fusion process. We evaluate the performance of the proposed OV-DINO on popular open-vocabulary detection benchmarks, achieving state-of-the-art results with an AP of 50.6% on the COCO benchmark and 40.1% on the LVIS benchmark in a zero-shot manner, demonstrating its strong generalization ability. Furthermore, the fine-tuned OV-DINO on COCO achieves 58.4% AP, outperforming many existing methods with the same backbone. The code for OV-DINO is available at https://github.com/wanghao9610/OV-DINO.
Cross domain object detection learns an object detector for an unlabeled target domain by transferring knowledge from an annotated source domain. Promising results have been achieved via Mean Teacher, however, pseudo labeling which is the bottleneck of mutual learning remains to be further explored. In this study, we find that confidence misalignment of the predictions, including category-level overconfidence, instance-level task confidence inconsistency, and image-level confidence misfocusing, leading to the injection of noisy pseudo label in the training process, will bring suboptimal performance on the target domain. To tackle this issue, we present a novel general framework termed Multi-Granularity Confidence Alignment Mean Teacher (MGCAMT) for cross domain object detection, which alleviates confidence misalignment across category-, instance-, and image-levels simultaneously to obtain high quality pseudo supervision for better teacher-student learning. Specifically, to align confidence with accuracy at category level, we propose Classification Confidence Alignment (CCA) to model category uncertainty based on Evidential Deep Learning (EDL) and filter out the category incorrect labels via an uncertainty-aware selection strategy. Furthermore, to mitigate the instance-level misalignment between classification and localization, we design Task Confidence Alignment (TCA) to enhance the interaction between the two task branches and allow each classification feature to adaptively locate the optimal feature for the regression. Finally, we develop imagery Focusing Confidence Alignment (FCA) adopting another way of pseudo label learning, i.e., we use the original outputs from the Mean Teacher network for supervised learning without label assignment to concentrate on holistic information in the target image. These three procedures benefit from each other from a cooperative learning perspective.
Comprehensive perception of the vehicle's environment and correct interpretation of the environment are crucial for the safe operation of autonomous vehicles. The perception of surrounding objects is the main component for further tasks such as trajectory planning. However, safe trajectory planning requires not only object detection, but also the detection of drivable areas and lane corridors. While first approaches consider an advanced safety evaluation of object detection, the evaluation of lane detection still lacks sufficient safety metrics. Similar to the safety metrics for object detection, additional factors such as the semantics of the scene with road type and road width, the detection range as well as the potential causes of missing detections, incorporated by vehicle speed, should be considered for the evaluation of lane detection. Therefore, we propose the Lane Safety Metric (LSM), which takes these factors into account and allows to evaluate the safety of lane detection systems by determining an easily interpretable safety score. We evaluate our offline safety metric on various virtual scenarios using different lane detection approaches and compare it with state-of-the-art performance metrics.
The cornerstone of autonomous vehicles (AV) is a solid perception system, where camera encoders play a crucial role. Existing works usually leverage pre-trained Convolutional Neural Networks (CNN) or Vision Transformers (ViTs) designed for general vision tasks, such as image classification, segmentation, and 2D detection. Although those well-known architectures have achieved state-of-the-art accuracy in AV-related tasks, e.g., 3D Object Detection, there remains significant potential for improvement in network design due to the nuanced complexities of industrial-level AV dataset. Moreover, existing public AV benchmarks usually contain insufficient data, which might lead to inaccurate evaluation of those architectures.To reveal the AV-specific model insights, we start from a standard general-purpose encoder, ConvNeXt and progressively transform the design. We adjust different design parameters including width and depth of the model, stage compute ratio, attention mechanisms, and input resolution, supported by systematic analysis to each modifications. This customization yields an architecture optimized for AV camera encoder achieving 8.79% mAP improvement over the baseline. We believe our effort could become a sweet cookbook of image encoders for AV and pave the way to the next-level drive system.
Learning from multiple sensors is challenging due to spatio-temporal misalignment and differences in resolution and captured spectra. To that end, we introduce GeoWATCH, a flexible framework for training models on long sequences of satellite images sourced from multiple sensor platforms, which is designed to handle image classification, activity recognition, object detection, or object tracking tasks. Our system includes a novel partial weight loading mechanism based on sub-graph isomorphism which allows for continually training and modifying a network over many training cycles. This has allowed us to train a lineage of models over a long period of time, which we have observed has improved performance as we adjust configurations while maintaining a core backbone.
We study the 3D object understanding task for manipulating everyday objects with different material properties (diffuse, specular, transparent and mixed). Existing monocular and RGB-D methods suffer from scale ambiguity due to missing or imprecise depth measurements. We present CODERS, a one-stage approach for Category-level Object Detection, pose Estimation and Reconstruction from Stereo images. The base of our pipeline is an implicit stereo matching module that combines stereo image features with 3D position information. Concatenating this presented module and the following transform-decoder architecture leads to end-to-end learning of multiple tasks required by robot manipulation. Our approach significantly outperforms all competing methods in the public TOD dataset. Furthermore, trained on simulated data, CODERS generalize well to unseen category-level object instances in real-world robot manipulation experiments. Our dataset, code, and demos will be available on our project page.
Cue points indicate possible temporal boundaries in a transition between two pieces of music in DJ mixing and constitute a crucial element in autonomous DJ systems as well as for live mixing. In this work, we present a novel method for automatic cue point estimation, interpreted as a computer vision object detection task. Our proposed system is based on a pre-trained object detection transformer which we fine-tune on our novel cue point dataset. Our provided dataset contains 21k manually annotated cue points from human experts as well as metronome information for nearly 5k individual tracks, making this dataset 35x larger than the previously available cue point dataset. Unlike previous methods, our approach does not require low-level musical information analysis, while demonstrating increased precision in retrieving cue point positions. Moreover, our proposed method demonstrates high adherence to phrasing, a type of high-level music structure commonly emphasized in electronic dance music. The code, model checkpoints, and dataset are made publicly available.
The depth/thermal information is beneficial for detecting salient object with conventional RGB images. However, in dual-modal salient object detection (SOD) model, the robustness against noisy inputs and modality missing is crucial but rarely studied. To tackle this problem, we introduce \textbf{Co}nditional Dropout and \textbf{LA}nguage-driven(\textbf{CoLA}) framework comprising two core components. 1) Language-driven Quality Assessment (LQA): Leveraging a pretrained vision-language model with a prompt learner, the LQA recalibrates image contributions without requiring additional quality annotations. This approach effectively mitigates the impact of noisy inputs. 2) Conditional Dropout (CD): A learning method to strengthen the model's adaptability in scenarios with missing modalities, while preserving its performance under complete modalities. The CD serves as a plug-in training scheme that treats modality-missing as conditions, strengthening the overall robustness of various dual-modal SOD models. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art dual-modal SOD models, under both modality-complete and modality-missing conditions. We will release source code upon acceptance.
Humans describe complex scenes with compositionality, using simple text descriptions enriched with links and relationships. While vision-language research has aimed to develop models with compositional understanding capabilities, this is not reflected yet in existing datasets which, for the most part, still use plain text to describe images. In this work, we propose a new annotation strategy, graph-based captioning (GBC) that describes an image using a labelled graph structure, with nodes of various types. The nodes in GBC are created using, in a first stage, object detection and dense captioning tools nested recursively to uncover and describe entity nodes, further linked together in a second stage by highlighting, using new types of nodes, compositions and relations among entities. Since all GBC nodes hold plain text descriptions, GBC retains the flexibility found in natural language, but can also encode hierarchical information in its edges. We demonstrate that GBC can be produced automatically, using off-the-shelf multimodal LLMs and open-vocabulary detection models, by building a new dataset, GBC10M, gathering GBC annotations for about 10M images of the CC12M dataset. We use GBC10M to showcase the wealth of node captions uncovered by GBC, as measured with CLIP training. We show that using GBC nodes' annotations -- notably those stored in composition and relation nodes -- results in significant performance boost on downstream models when compared to other dataset formats. To further explore the opportunities provided by GBC, we also propose a new attention mechanism that can leverage the entire GBC graph, with encouraging experimental results that show the extra benefits of incorporating the graph structure. Our datasets are released at \url{https://huggingface.co/graph-based-captions}.
YOLO is a deep neural network (DNN) model presented for robust real-time object detection following the one-stage inference approach. It outperforms other real-time object detectors in terms of speed and accuracy by a wide margin. Nevertheless, since YOLO is developed upon a DNN backbone with numerous parameters, it will cause excessive memory load, thereby deploying it on memory-constrained devices is a severe challenge in practice. To overcome this limitation, model compression techniques, such as quantizing parameters to lower-precision values, can be adopted. As the most recent version of YOLO, YOLOv7 achieves such state-of-the-art performance in speed and accuracy in the range of 5 FPS to 160 FPS that it surpasses all former versions of YOLO and other existing models in this regard. So far, the robustness of several quantization schemes has been evaluated on older versions of YOLO. These methods may not necessarily yield similar results for YOLOv7 as it utilizes a different architecture. In this paper, we conduct in-depth research on the effectiveness of a variety of quantization schemes on the pre-trained weights of the state-of-the-art YOLOv7 model. Experimental results demonstrate that using 4-bit quantization coupled with the combination of different granularities results in ~3.92x and ~3.86x memory-saving for uniform and non-uniform quantization, respectively, with only 2.5% and 1% accuracy loss compared to the full-precision baseline model.