We present PARQ - a multi-view 3D object detector with transformer and pixel-aligned recurrent queries. Unlike previous works that use learnable features or only encode 3D point positions as queries in the decoder, PARQ leverages appearance-enhanced queries initialized from reference points in 3D space and updates their 3D location with recurrent cross-attention operations. Incorporating pixel-aligned features and cross attention enables the model to encode the necessary 3D-to-2D correspondences and capture global contextual information of the input images. PARQ outperforms prior best methods on the ScanNet and ARKitScenes datasets, learns and detects faster, is more robust to distribution shifts in reference points, can leverage additional input views without retraining, and can adapt inference compute by changing the number of recurrent iterations.
Open-vocabulary object detection (OVOD) aims to detect the objects beyond the set of classes observed during training. This work introduces a straightforward and efficient strategy that utilizes pre-trained vision-language models (VLM), like CLIP, to identify potential novel classes through zero-shot classification. Previous methods use a class-agnostic region proposal network to detect object proposals and consider the proposals that do not match the ground truth as background. Unlike these methods, our method will select a subset of proposals that will be considered as background during the training. Then, we treat them as novel classes during training. We refer to this approach as the self-training strategy, which enhances recall and accuracy for novel classes without requiring extra annotations, datasets, and re-training. Compared to previous pseudo methods, our approach does not require re-training and offline labeling processing, which is more efficient and effective in one-shot training. Empirical evaluations on three datasets, including LVIS, V3Det, and COCO, demonstrate significant improvements over the baseline performance without incurring additional parameters or computational costs during inference. In addition, we also apply our method to various baselines. In particular, compared with the previous method, F-VLM, our method achieves a 1.7% improvement on the LVIS dataset. Combined with the recent method CLIPSelf, our method also achieves 46.7 novel class AP on COCO without introducing extra data for pertaining. We also achieve over 6.5% improvement over the F-VLM baseline in the recent challenging V3Det dataset. We release our code and models at https://github.com/xushilin1/dst-det.
In this paper we introduce the SCoRe (Submodular Combinatorial Representation Learning) framework, a novel approach in representation learning that addresses inter-class bias and intra-class variance. SCoRe provides a new combinatorial viewpoint to representation learning, by introducing a family of loss functions based on set-based submodular information measures. We develop two novel combinatorial formulations for loss functions, using the Total Information and Total Correlation, that naturally minimize intra-class variance and inter-class bias. Several commonly used metric/contrastive learning loss functions like supervised contrastive loss, orthogonal projection loss, and N-pairs loss, are all instances of SCoRe, thereby underlining the versatility and applicability of SCoRe in a broad spectrum of learning scenarios. Novel objectives in SCoRe naturally model class-imbalance with up to 7.6\% improvement in classification on CIFAR-10-LT, CIFAR-100-LT, MedMNIST, 2.1% on ImageNet-LT, and 19.4% in object detection on IDD and LVIS (v1.0), demonstrating its effectiveness over existing approaches.
LiDAR-based 3D object detectors have achieved unprecedented speed and accuracy in autonomous driving applications. However, similar to other neural networks, they are often biased toward high-confidence predictions or return detections where no real object is present. These types of detections can lead to a less reliable environment perception, severely affecting the functionality and safety of autonomous vehicles. We address this problem by proposing LS-VOS, a framework for identifying outliers in 3D object detections. Our approach builds on the idea of Virtual Outlier Synthesis (VOS), which incorporates outlier knowledge during training, enabling the model to learn more compact decision boundaries. In particular, we propose a new synthesis approach that relies on the latent space of an auto-encoder network to generate outlier features with a parametrizable degree of similarity to in-distribution features. In extensive experiments, we show that our approach improves the outlier detection capabilities of a state-of-the-art object detector while maintaining high 3D object detection performance.
LiDAR sensors are used in autonomous driving applications to accurately perceive the environment. However, they are affected by adverse weather conditions such as snow, fog, and rain. These everyday phenomena introduce unwanted noise into the measurements, severely degrading the performance of LiDAR-based perception systems. In this work, we propose a framework for improving the robustness of LiDAR-based 3D object detectors against road spray. Our approach uses a state-of-the-art adverse weather detection network to filter out spray from the LiDAR point cloud, which is then used as input for the object detector. In this way, the detected objects are less affected by the adverse weather in the scene, resulting in a more accurate perception of the environment. In addition to adverse weather filtering, we explore the use of radar targets to further filter false positive detections. Tests on real-world data show that our approach improves the robustness to road spray of several popular 3D object detectors.
Monocular 3D object detection plays a crucial role in autonomous driving. However, existing monocular 3D detection algorithms depend on 3D labels derived from LiDAR measurements, which are costly to acquire for new datasets and challenging to deploy in novel environments. Specifically, this study investigates the pipeline for training a monocular 3D object detection model on a diverse collection of 3D and 2D datasets. The proposed framework comprises three components: (1) a robust monocular 3D model capable of functioning across various camera settings, (2) a selective-training strategy to accommodate datasets with differing class annotations, and (3) a pseudo 3D training approach using 2D labels to enhance detection performance in scenes containing only 2D labels. With this framework, we could train models on a joint set of various open 3D/2D datasets to obtain models with significantly stronger generalization capability and enhanced performance on new dataset with only 2D labels. We conduct extensive experiments on KITTI/nuScenes/ONCE/Cityscapes/BDD100K datasets to demonstrate the scaling ability of the proposed method.
Camouflage object detection (COD) poses a significant challenge due to the high resemblance between camouflaged objects and their surroundings. Although current deep learning methods have made significant progress in detecting camouflaged objects, many of them heavily rely on additional prior information. However, acquiring such additional prior information is both expensive and impractical in real-world scenarios. Therefore, there is a need to develop a network for camouflage object detection that does not depend on additional priors. In this paper, we propose a novel adaptive feature aggregation method that effectively combines multi-layer feature information to generate guidance information. In contrast to previous approaches that rely on edge or ranking priors, our method directly leverages information extracted from image features to guide model training. Through extensive experimental results, we demonstrate that our proposed method achieves comparable or superior performance when compared to state-of-the-art approaches.
We present Contextualized Local Visual Embeddings (CLoVE), a self-supervised convolutional-based method that learns representations suited for dense prediction tasks. CLoVE deviates from current methods and optimizes a single loss function that operates at the level of contextualized local embeddings learned from output feature maps of convolution neural network (CNN) encoders. To learn contextualized embeddings, CLoVE proposes a normalized mult-head self-attention layer that combines local features from different parts of an image based on similarity. We extensively benchmark CLoVE's pre-trained representations on multiple datasets. CLoVE reaches state-of-the-art performance for CNN-based architectures in 4 dense prediction downstream tasks, including object detection, instance segmentation, keypoint detection, and dense pose estimation.
Although the majority of recent autonomous driving systems concentrate on developing perception methods based on ego-vehicle sensors, there is an overlooked alternative approach that involves leveraging intelligent roadside cameras to help extend the ego-vehicle perception ability beyond the visual range. We discover that most existing monocular 3D object detectors rely on the ego-vehicle prior assumption that the optical axis of the camera is parallel to the ground. However, the roadside camera is installed on a pole with a pitched angle, which makes the existing methods not optimal for roadside scenes. In this paper, we introduce a novel framework for Roadside Monocular 3D object detection with ground-aware embeddings, named MonoGAE. Specifically, the ground plane is a stable and strong prior knowledge due to the fixed installation of cameras in roadside scenarios. In order to reduce the domain gap between the ground geometry information and high-dimensional image features, we employ a supervised training paradigm with a ground plane to predict high-dimensional ground-aware embeddings. These embeddings are subsequently integrated with image features through cross-attention mechanisms. Furthermore, to improve the detector's robustness to the divergences in cameras' installation poses, we replace the ground plane depth map with a novel pixel-level refined ground plane equation map. Our approach demonstrates a substantial performance advantage over all previous monocular 3D object detectors on widely recognized 3D detection benchmarks for roadside cameras. The code and pre-trained models will be released soon.
Recent advances in generative diffusion models have enabled text-controlled synthesis of realistic and diverse images with impressive quality. Despite these remarkable advances, the application of text-to-image generative models in computer vision for standard visual recognition tasks remains limited. The current de facto approach for these tasks is to design model architectures and loss functions that are tailored to the task at hand. In this paper, we develop a unified language interface for computer vision tasks that abstracts away task-specific design choices and enables task execution by following natural language instructions. Our approach involves casting multiple computer vision tasks as text-to-image generation problems. Here, the text represents an instruction describing the task, and the resulting image is a visually-encoded task output. To train our model, we pool commonly-used computer vision datasets covering a range of tasks, including segmentation, object detection, depth estimation, and classification. We then use a large language model to paraphrase prompt templates that convey the specific tasks to be conducted on each image, and through this process, we create a multi-modal and multi-task training dataset comprising input and output images along with annotated instructions. Following the InstructPix2Pix architecture, we apply instruction-tuning to a text-to-image diffusion model using our constructed dataset, steering its functionality from a generative model to an instruction-guided multi-task vision learner. Experiments demonstrate that our model, dubbed InstructCV, performs competitively compared to other generalist and task-specific vision models. Moreover, it exhibits compelling generalization capabilities to unseen data, categories, and user instructions.
Obtaining annotations for complex computer vision tasks such as object detection is an expensive and time-intense endeavor involving a large number of human workers or expert opinions. Reducing the amount of annotations required while maintaining algorithm performance is, therefore, desirable for machine learning practitioners and has been successfully achieved by active learning algorithms. However, it is not merely the amount of annotations which influences model performance but also the annotation quality. In practice, the oracles that are queried for new annotations frequently contain significant amounts of noise. Therefore, cleansing procedures are oftentimes necessary to review and correct given labels. This process is subject to the same budget as the initial annotation itself since it requires human workers or even domain experts. Here, we propose a composite active learning framework including a label review module for deep object detection. We show that utilizing part of the annotation budget to correct the noisy annotations partially in the active dataset leads to early improvements in model performance, especially when coupled with uncertainty-based query strategies. The precision of the label error proposals has a significant influence on the measured effect of the label review. In our experiments we achieve improvements of up to 4.5 mAP points of object detection performance by incorporating label reviews at equal annotation budget.
A vast majority of conventional augmented reality devices are equipped with depth sensors. Depth images produced by such sensors contain complementary information for object detection when used with color images. Despite the benefits, it remains a complex task to simultaneously extract photometric and depth features in real time due to the immanent difference between depth and color images. Moreover, standard convolution operations are not sufficient to properly extract information directly from raw depth images leading to intermediate representations of depth which is inefficient. To address these issues, we propose a real-time and two stream RGBD object detection model. The proposed model consists of two new components: a depth guided hyper-involution that adapts dynamically based on the spatial interaction pattern in the raw depth map and an up-sampling based trainable fusion layer that combines the extracted depth and color image features without blocking the information transfer between them. We show that the proposed model outperforms other RGB-D based object detection models on NYU Depth v2 dataset and achieves comparable (second best) results on SUN RGB-D. Additionally, we introduce a new outdoor RGB-D object detection dataset where our proposed model outperforms other models. The performance evaluation on diverse synthetic data generated from CAD models and images shows the potential of the proposed model to be adapted to augmented reality based applications.
Diffusion models are generative models with impressive text-to-image synthesis capabilities and have spurred a new wave of creative methods for classical machine learning tasks. However, the best way to harness the perceptual knowledge of these generative models for visual tasks is still an open question. Specifically, it is unclear how to use the prompting interface when applying diffusion backbones to vision tasks. We find that automatically generated captions can improve text-image alignment and significantly enhance a model's cross-attention maps, leading to better perceptual performance. Our approach improves upon the current state-of-the-art (SOTA) in diffusion-based semantic segmentation on ADE20K and the current overall SOTA for depth estimation on NYUv2. Furthermore, our method generalizes to the cross-domain setting. We use model personalization and caption modifications to align our model to the target domain and find improvements over unaligned baselines. Our cross-domain object detection model, trained on Pascal VOC, achieves SOTA results on Watercolor2K. Our cross-domain segmentation method, trained on Cityscapes, achieves SOTA results on Dark Zurich-val and Nighttime Driving. Project page: https://www.vision.caltech.edu/tadp/. Code: https://github.com/damaggu/TADP.
Learning representations through self-supervision on unlabeled data has proven highly effective for understanding diverse images. However, remote sensing images often have complex and densely populated scenes with multiple land objects and no clear foreground objects. This intrinsic property generates high object density, resulting in false positive pairs or missing contextual information in self-supervised learning. To address these problems, we propose a context-enhanced masked image modeling method (CtxMIM), a simple yet efficient MIM-based self-supervised learning for remote sensing image understanding. CtxMIM formulates original image patches as a reconstructive template and employs a Siamese framework to operate on two sets of image patches. A context-enhanced generative branch is introduced to provide contextual information through context consistency constraints in the reconstruction. With the simple and elegant design, CtxMIM encourages the pre-training model to learn object-level or pixel-level features on a large-scale dataset without specific temporal or geographical constraints. Finally, extensive experiments show that features learned by CtxMIM outperform fully supervised and state-of-the-art self-supervised learning methods on various downstream tasks, including land cover classification, semantic segmentation, object detection, and instance segmentation. These results demonstrate that CtxMIM learns impressive remote sensing representations with high generalization and transferability. Code and data will be made public available.
Background: Dental caries diagnosis requires the manual inspection of diagnostic bitewing images of the patient, followed by a visual inspection and probing of the identified dental pieces with potential lesions. Yet the use of artificial intelligence, and in particular deep-learning, has the potential to aid in the diagnosis by providing a quick and informative analysis of the bitewing images. Methods: A dataset of 13,887 bitewings from the HUNT4 Oral Health Study were annotated individually by six different experts, and used to train three different object detection deep-learning architectures: RetinaNet (ResNet50), YOLOv5 (M size), and EfficientDet (D0 and D1 sizes). A consensus dataset of 197 images, annotated jointly by the same six dentist, was used for evaluation. A five-fold cross validation scheme was used to evaluate the performance of the AI models. Results: he trained models show an increase in average precision and F1-score, and decrease of false negative rate, with respect to the dental clinicians. When compared against the dental clinicians, the YOLOv5 model shows the largest improvement, reporting 0.647 mean average precision, 0.548 mean F1-score, and 0.149 mean false negative rate. Whereas the best annotators on each of these metrics reported 0.299, 0.495, and 0.164 respectively. Conclusion: Deep-learning models have shown the potential to assist dental professionals in the diagnosis of caries. Yet, the task remains challenging due to the artifacts natural to the bitewing images.
We present a new open-vocabulary detection approach based on region-centric image-language pretraining to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we incorporate the detector architecture on top of the classification backbone, which better serves the region-level recognition needs of detection by enabling the detector heads to learn from large-scale image-text pairs. Using only standard contrastive loss and no pseudo-labeling, our approach is a simple yet effective extension of the contrastive learning method to learn emergent object-semantic cues. In addition, we propose a shifted-window learning approach upon window attention to make the backbone representation more robust, translation-invariant, and less biased by the window pattern. On the popular LVIS open-vocabulary detection benchmark, our approach sets a new state of the art of 37.6 mask APr using the common ViT-L backbone and public LAION dataset, and 40.5 mask APr using the DataComp-1B dataset, significantly outperforming the best existing approach by +3.7 mask APr at system level. On the COCO benchmark, we achieve very competitive 39.6 novel AP without pseudo labeling or weak supervision. In addition, we evaluate our approach on the transfer detection setup, where it demonstrates notable improvement over the baseline. Visualization reveals emerging object locality from the pretraining recipes compared to the baseline.
Automatic visual inspection of synthetic fibre ropes (SFRs) is a challenging task in the field of offshore, wind turbine industries, etc. The presence of any defect in SFRs can compromise their structural integrity and pose significant safety risks. Due to the large size and weight of these ropes, it is often impractical to detach and inspect them frequently. Therefore, there is a critical need to develop efficient defect detection methods to assess their remaining useful life (RUL). To address this challenge, a comprehensive dataset has been generated, comprising a total of 6,942 raw images representing both normal and defective SFRs. The dataset encompasses a wide array of defect scenarios which may occur throughout their operational lifespan, including but not limited to placking defects, cut strands, chafings, compressions, core outs and normal. This dataset serves as a resource to support computer vision applications, including object detection, classification, and segmentation, aimed at detecting and analyzing defects in SFRs. The availability of this dataset will facilitate the development and evaluation of robust defect detection algorithms. The aim of generating this dataset is to assist in the development of automated defect detection systems that outperform traditional visual inspection methods, thereby paving the way for safer and more efficient utilization of SFRs across a wide range of applications.
We propose a late-to-early recurrent feature fusion scheme for 3D object detection using temporal LiDAR point clouds. Our main motivation is fusing object-aware latent embeddings into the early stages of a 3D object detector. This feature fusion strategy enables the model to better capture the shapes and poses for challenging objects, compared with learning from raw points directly. Our method conducts late-to-early feature fusion in a recurrent manner. This is achieved by enforcing window-based attention blocks upon temporally calibrated and aligned sparse pillar tokens. Leveraging bird's eye view foreground pillar segmentation, we reduce the number of sparse history features that our model needs to fuse into its current frame by 10$\times$. We also propose a stochastic-length FrameDrop training technique, which generalizes the model to variable frame lengths at inference for improved performance without retraining. We evaluate our method on the widely adopted Waymo Open Dataset and demonstrate improvement on 3D object detection against the baseline model, especially for the challenging category of large objects.
This paper presents a novel framework for robust 3D object detection from point clouds via cross-modal hallucination. Our proposed approach is agnostic to either hallucination direction between LiDAR and 4D radar. We introduce multiple alignments on both spatial and feature levels to achieve simultaneous backbone refinement and hallucination generation. Specifically, spatial alignment is proposed to deal with the geometry discrepancy for better instance matching between LiDAR and radar. The feature alignment step further bridges the intrinsic attribute gap between the sensing modalities and stabilizes the training. The trained object detection models can deal with difficult detection cases better, even though only single-modal data is used as the input during the inference stage. Extensive experiments on the View-of-Delft (VoD) dataset show that our proposed method outperforms the state-of-the-art (SOTA) methods for both radar and LiDAR object detection while maintaining competitive efficiency in runtime. Code is available at https://github.com/DJNing/See_beyond_seeing.
Multi-task learning (MTL) aims to learn multiple tasks using a single model and jointly improve all of them assuming generalization and shared semantics. Reducing conflicts between tasks during joint learning is difficult and generally requires careful network design and extremely large models. We propose building on You Only Learn One Representation (YOLOR), a network architecture specifically designed for multitasking. YOLOR leverages both explicit and implicit knowledge, from data observations and learned latents, respectively, to improve a shared representation while minimizing the number of training parameters. However, YOLOR and its follow-up, YOLOv7, only trained two tasks at once. In this paper, we jointly train object detection, instance segmentation, semantic segmentation, and image captioning. We analyze tradeoffs and attempt to maximize sharing of semantic information. Through our architecture and training strategies, we find that our method achieves competitive performance on all tasks while maintaining a low parameter count and without any pre-training. We will release code soon.