Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far been unevaluated. In this work, we present the systematic review of VLM-based detection and segmentation, view VLM as the foundational model and conduct comprehensive evaluations across multiple downstream tasks for the first time: 1) The evaluation spans eight detection scenarios (closed-set detection, domain adaptation, crowded objects, etc.) and eight segmentation scenarios (few-shot, open-world, small object, etc.), revealing distinct performance advantages and limitations of various VLM architectures across tasks. 2) As for detection tasks, we evaluate VLMs under three finetuning granularities: \textit{zero prediction}, \textit{visual fine-tuning}, and \textit{text prompt}, and further analyze how different finetuning strategies impact performance under varied task. 3) Based on empirical findings, we provide in-depth analysis of the correlations between task characteristics, model architectures, and training methodologies, offering insights for future VLM design. 4) We believe that this work shall be valuable to the pattern recognition experts working in the fields of computer vision, multimodal learning, and vision foundation models by introducing them to the problem, and familiarizing them with the current status of the progress while providing promising directions for future research. A project associated with this review and evaluation has been created at https://github.com/better-chao/perceptual_abilities_evaluation.
Training heuristics greatly improve various image classification model accuracies~\cite{he2018bag}. Object detection models, however, have more complex neural network structures and optimization targets. The training strategies and pipelines dramatically vary among different models. In this works, we explore training tweaks that apply to various models including Faster R-CNN and YOLOv3. These tweaks do not change the model architectures, therefore, the inference costs remain the same. Our empirical results demonstrate that, however, these freebies can improve up to 5% absolute precision compared to state-of-the-art baselines.
Recent advance in 2D CNNs has revealed that large kernels are important. However, when directly applying large convolutional kernels in 3D CNNs, severe difficulties are met, where those successful module designs in 2D become surprisingly ineffective on 3D networks, including the popular depth-wise convolution. To address this vital challenge, we instead propose the spatial-wise partition convolution and its large-kernel module. As a result, it avoids the optimization and efficiency issues of naive 3D large kernels. Our large-kernel 3D CNN network, LargeKernel3D, yields notable improvement in 3D tasks of semantic segmentation and object detection. It achieves 73.9% mIoU on the ScanNetv2 semantic segmentation and 72.8% NDS nuScenes object detection benchmarks, ranking 1st on the nuScenes LIDAR leaderboard. The performance further boosts to 74.2% NDS with a simple multi-modal fusion. In addition, LargeKernel3D can be scaled to 17x17x17 kernel size on Waymo 3D object detection. For the first time, we show that large kernels are feasible and essential for 3D visual tasks.
Recent years have witnessed a trend of applying context frames to boost the performance of object detection as video object detection. Existing methods usually aggregate features at one stroke to enhance the feature. These methods, however, usually lack spatial information from neighboring frames and suffer from insufficient feature aggregation. To address the issues, we perform a progressive way to introduce both temporal information and spatial information for an integrated enhancement. The temporal information is introduced by the temporal feature aggregation model (TFAM), by conducting an attention mechanism between the context frames and the target frame (i.e., the frame to be detected). Meanwhile, we employ a Spatial Transition Awareness Model (STAM) to convey the location transition information between each context frame and target frame. Built upon a transformer-based detector DETR, our PTSEFormer also follows an end-to-end fashion to avoid heavy post-processing procedures while achieving 88.1% mAP on the ImageNet VID dataset. Codes are available at https://github.com/Hon-Wong/PTSEFormer.
DAVIS camera, streaming two complementary sensing modalities of asynchronous events and frames, has gradually been used to address major object detection challenges (e.g., fast motion blur and low-light). However, how to effectively leverage rich temporal cues and fuse two heterogeneous visual streams remains a challenging endeavor. To address this challenge, we propose a novel streaming object detector with Transformer, namely SODFormer, which first integrates events and frames to continuously detect objects in an asynchronous manner. Technically, we first build a large-scale multimodal neuromorphic object detection dataset (i.e., PKU-DAVIS-SOD) over 1080.1k manual labels. Then, we design a spatiotemporal Transformer architecture to detect objects via an end-to-end sequence prediction problem, where the novel temporal Transformer module leverages rich temporal cues from two visual streams to improve the detection performance. Finally, an asynchronous attention-based fusion module is proposed to integrate two heterogeneous sensing modalities and take complementary advantages from each end, which can be queried at any time to locate objects and break through the limited output frequency from synchronized frame-based fusion strategies. The results show that the proposed SODFormer outperforms four state-of-the-art methods and our eight baselines by a significant margin. We also show that our unifying framework works well even in cases where the conventional frame-based camera fails, e.g., high-speed motion and low-light conditions. Our dataset and code can be available at https://github.com/dianzl/SODFormer.
Vision-based autonomous navigation systems rely on fast and accurate object detection algorithms to avoid obstacles. Algorithms and sensors designed for such systems need to be computationally efficient, due to the limited energy of the hardware used for deployment. Biologically inspired event cameras are a good candidate as a vision sensor for such systems due to their speed, energy efficiency, and robustness to varying lighting conditions. However, traditional computer vision algorithms fail to work on event-based outputs, as they lack photometric features such as light intensity and texture. In this work, we propose a novel technique that utilizes the temporal information inherently present in the events to efficiently detect moving objects. Our technique consists of a lightweight spiking neural architecture that is able to separate events based on the speed of the corresponding objects. These separated events are then further grouped spatially to determine object boundaries. This method of object detection is both asynchronous and robust to camera noise. In addition, it shows good performance in scenarios with events generated by static objects in the background, where existing event-based algorithms fail. We show that by utilizing our architecture, autonomous navigation systems can have minimal latency and energy overheads for performing object detection.
The goal of this paper is to perform object detection in satellite imagery with only a few examples, thus enabling users to specify any object class with minimal annotation. To this end, we explore recent methods and ideas from open-vocabulary detection for the remote sensing domain. We develop a few-shot object detector based on a traditional two-stage architecture, where the classification block is replaced by a prototype-based classifier. A large-scale pre-trained model is used to build class-reference embeddings or prototypes, which are compared to region proposal contents for label prediction. In addition, we propose to fine-tune prototypes on available training images to boost performance and learn differences between similar classes, such as aircraft types. We perform extensive evaluations on two remote sensing datasets containing challenging and rare objects. Moreover, we study the performance of both visual and image-text features, namely DINOv2 and CLIP, including two CLIP models specifically tailored for remote sensing applications. Results indicate that visual features are largely superior to vision-language models, as the latter lack the necessary domain-specific vocabulary. Lastly, the developed detector outperforms fully supervised and few-shot methods evaluated on the SIMD and DIOR datasets, despite minimal training parameters.
Enabling models to recognize vast open-world categories has been a longstanding pursuit in object detection. By leveraging the generalization capabilities of vision-language models, current open-world detectors can recognize a broader range of vocabularies, despite being trained on limited categories. However, when the scale of the category vocabularies during training expands to a real-world level, previous classifiers aligned with coarse class names significantly reduce the recognition performance of these detectors. In this paper, we introduce Prova, a multi-modal prototype classifier for vast-vocabulary object detection. Prova extracts comprehensive multi-modal prototypes as initialization of alignment classifiers to tackle the vast-vocabulary object recognition failure problem. On V3Det, this simple method greatly enhances the performance among one-stage, two-stage, and DETR-based detectors with only additional projection layers in both supervised and open-vocabulary settings. In particular, Prova improves Faster R-CNN, FCOS, and DINO by 3.3, 6.2, and 2.9 AP respectively in the supervised setting of V3Det. For the open-vocabulary setting, Prova achieves a new state-of-the-art performance with 32.8 base AP and 11.0 novel AP, which is of 2.6 and 4.3 gain over the previous methods.
Unlike RGB cameras that use visible light bands (384$\sim$769 THz) and Lidars that use infrared bands (361$\sim$331 THz), Radars use relatively longer wavelength radio bands (77$\sim$81 GHz), resulting in robust measurements in adverse weathers. Unfortunately, existing Radar datasets only contain a relatively small number of samples compared to the existing camera and Lidar datasets. This may hinder the development of sophisticated data-driven deep learning techniques for Radar-based perception. Moreover, most of the existing Radar datasets only provide 3D Radar tensor (3DRT) data that contain power measurements along the Doppler, range, and azimuth dimensions. As there is no elevation information, it is challenging to estimate the 3D bounding box of an object from 3DRT. In this work, we introduce KAIST-Radar (K-Radar), a novel large-scale object detection dataset and benchmark that contains 35K frames of 4D Radar tensor (4DRT) data with power measurements along the Doppler, range, azimuth, and elevation dimensions, together with carefully annotated 3D bounding box labels of objects on the roads. K-Radar includes challenging driving conditions such as adverse weathers (fog, rain, and snow) on various road structures (urban, suburban roads, alleyways, and highways). In addition to the 4DRT, we provide auxiliary measurements from carefully calibrated high-resolution Lidars, surround stereo cameras, and RTK-GPS. We also provide 4DRT-based object detection baseline neural networks (baseline NNs) and show that the height information is crucial for 3D object detection. And by comparing the baseline NN with a similarly-structured Lidar-based neural network, we demonstrate that 4D Radar is a more robust sensor for adverse weather conditions. All codes are available at https://github.com/kaist-avelab/k-radar.
The task of localizing and categorizing objects in medical images often remains formulated as a semantic segmentation problem. This approach, however, only indirectly solves the coarse localization task by predicting pixel-level scores, requiring ad-hoc heuristics when mapping back to object-level scores. State-of-the-art object detectors on the other hand, allow for individual object scoring in an end-to-end fashion, while ironically trading in the ability to exploit the full pixel-wise supervision signal. This can be particularly disadvantageous in the setting of medical image analysis, where data sets are notoriously small. In this paper, we propose Retina U-Net, a simple architecture, which naturally fuses the Retina Net one-stage detector with the U-Net architecture widely used for semantic segmentation in medical images. The proposed architecture recaptures discarded supervision signals by complementing object detection with an auxiliary task in the form of semantic segmentation without introducing the additional complexity of previously proposed two-stage detectors. We evaluate the importance of full segmentation supervision on two medical data sets, provide an in-depth analysis on a series of toy experiments and show how the corresponding performance gain grows in the limit of small data sets. Retina U-Net yields strong detection performance only reached by its more complex two-staged counterparts. Our framework including all methods implemented for operation on 2D and 3D images is available at github.com/pfjaeger/medicaldetectiontoolkit.
Human drivers use their attentional mechanisms to focus on critical objects and make decisions while driving. As human attention can be revealed from gaze data, capturing and analyzing gaze information has emerged in recent years to benefit autonomous driving technology. Previous works in this context have primarily aimed at predicting "where" human drivers look at and lack knowledge of "what" objects drivers focus on. Our work bridges the gap between pixel-level and object-level attention prediction. Specifically, we propose to integrate an attention prediction module into a pretrained object detection framework and predict the attention in a grid-based style. Furthermore, critical objects are recognized based on predicted attended-to areas. We evaluate our proposed method on two driver attention datasets, BDD-A and DR(eye)VE. Our framework achieves competitive state-of-the-art performance in the attention prediction on both pixel-level and object-level but is far more efficient (75.3 GFLOPs less) in computation.
Object detection systems using deep learning models have become increasingly popular in robotics thanks to the rising power of CPUs and GPUs in embedded systems. However, these models are susceptible to adversarial attacks. While some attacks are limited by strict assumptions on access to the detection system, we propose a novel hardware attack inspired by Man-in-the-Middle attacks in cryptography. This attack generates a Universal Adversarial Perturbations (UAP) and injects the perturbation between the USB camera and the detection system via a hardware attack. Besides, prior research is misled by an evaluation metric that measures the model accuracy rather than the attack performance. In combination with our proposed evaluation metrics, we significantly increased the strength of adversarial perturbations. These findings raise serious concerns for applications of deep learning models in safety-critical systems, such as autonomous driving.
This paper tackles the 3D object detection problem, which is of vital importance for applications such as autonomous driving. Our framework uses a Machine Learning (ML) pipeline on a combination of monocular camera and LiDAR data to detect vehicles in the surrounding 3D space of a moving platform. It uses frustum region proposals generated by State-Of-The-Art (SOTA) 2D object detectors to segment LiDAR point clouds into point clusters which represent potentially individual objects. We evaluate the performance of classical ML algorithms as part of an holistic pipeline for estimating the parameters of 3D bounding boxes which surround the vehicles around the moving platform. Our results demonstrate an efficient and accurate inference on a validation set, achieving an overall accuracy of 87.1%.
This paper presents a fast and modular framework for Multi-Object Tracking (MOT) based on the Markov descision process (MDP) tracking-by-detection paradigm. It is designed to allow its various functional components to be replaced by custom-designed alternatives to suit a given application. An interactive GUI with integrated object detection, segmentation, MOT and semi-automated labeling is also provided to help make it easier to get started with this framework. Though not breaking new ground in terms of performance, Deep MDP has a large code-base that should be useful for the community to try out new ideas or simply to have an easy-to-use and easy-to-adapt system for any MOT application. Deep MDP is available at https://github.com/abhineet123/deep_mdp.
There has been increasing interest in smart factories powered by robotics systems to tackle repetitive, laborious tasks. One impactful yet challenging task in robotics-powered smart factory applications is robotic grasping: using robotic arms to grasp objects autonomously in different settings. Robotic grasping requires a variety of computer vision tasks such as object detection, segmentation, grasp prediction, pick planning, etc. While significant progress has been made in leveraging of machine learning for robotic grasping, particularly with deep learning, a big challenge remains in the need for large-scale, high-quality RGBD datasets that cover a wide diversity of scenarios and permutations. To tackle this big, diverse data problem, we are inspired by the recent rise in the concept of metaverse, which has greatly closed the gap between virtual worlds and the physical world. Metaverses allow us to create digital twins of real-world manufacturing scenarios and to virtually create different scenarios from which large volumes of data can be generated for training models. In this paper, we present MetaGraspNet: a large-scale benchmark dataset for vision-driven robotic grasping via physics-based metaverse synthesis. The proposed dataset contains 100,000 images and 25 different object types and is split into 5 difficulties to evaluate object detection and segmentation model performance in different grasping scenarios. We also propose a new layout-weighted performance metric alongside the dataset for evaluating object detection and segmentation performance in a manner that is more appropriate for robotic grasp applications compared to existing general-purpose performance metrics. Our benchmark dataset is available open-source on Kaggle, with the first phase consisting of detailed object detection, segmentation, layout annotations, and a layout-weighted performance metric script.
During training, supervised object detection tries to correctly match the predicted bounding boxes and associated classification scores to the ground truth. This is essential to determine which predictions are to be pushed towards which solutions, or to be discarded. Popular matching strategies include matching to the closest ground truth box (mostly used in combination with anchors), or matching via the Hungarian algorithm (mostly used in anchor-free methods). Each of these strategies comes with its own properties, underlying losses, and heuristics. We show how Unbalanced Optimal Transport unifies these different approaches and opens a whole continuum of methods in between. This allows for a finer selection of the desired properties. Experimentally, we show that training an object detection model with Unbalanced Optimal Transport is able to reach the state-of-the-art both in terms of Average Precision and Average Recall as well as to provide a faster initial convergence. The approach is well suited for GPU implementation, which proves to be an advantage for large-scale models.
Open-world autonomous driving encompasses domain generalization and open-vocabulary. Domain generalization refers to the capabilities of autonomous driving systems across different scenarios and sensor parameter configurations. Open vocabulary pertains to the ability to recognize various semantic categories not encountered during training. In this paper, we introduce OpenAD, the first real-world open-world autonomous driving benchmark for 3D object detection. OpenAD is built on a corner case discovery and annotation pipeline integrating with a multimodal large language model (MLLM). The proposed pipeline annotates corner case objects in a unified format for five autonomous driving perception datasets with 2000 scenarios. In addition, we devise evaluation methodologies and evaluate various 2D and 3D open-world and specialized models. Moreover, we propose a vision-centric 3D open-world object detection baseline and further introduce an ensemble method by fusing general and specialized models to address the issue of lower precision in existing open-world methods for the OpenAD benchmark. Annotations, toolkit code, and all evaluation codes will be released.
Object detection is a fundamental challenge in computer vision, centered on recognizing objects within images, with diverse applications in areas like image analysis, robotics, and autonomous vehicles. Although existing methods have achieved great success, they are often constrained by a fixed vocabulary of objects. To overcome this limitation, approaches like MDETR have redefined object detection by incorporating region-level vision-language pre-training, enabling open-vocabulary object detectors. However, these methods are computationally heavy due to the simultaneous training of large models for both vision and language representations. To address this, we introduce a lightweight framework that significantly reduces the number of parameters while preserving, or even improving, performance. Our solution is applied to MDETR, resulting in the development of Lightweight MDETR (LightMDETR), an optimized version of MDETR designed to enhance computational efficiency without sacrificing accuracy. The core of our approach involves freezing the MDETR backbone and training only the Universal Projection module (UP), which bridges vision and language representations. A learnable modality token parameter allows the UP to seamlessly switch between modalities. Evaluations on tasks like phrase grounding, referring expression comprehension, and segmentation show that LightMDETR not only reduces computational costs but also outperforms several state-of-the-art methods in terms of accuracy.
Object discovery is a core task in computer vision. While fast progresses have been made in supervised object detection, its unsupervised counterpart remains largely unexplored. With the growth of data volume, the expensive cost of annotations is the major limitation hindering further study. Therefore, discovering objects without annotations has great significance. However, this task seems impractical on still-image or point cloud alone due to the lack of discriminative information. Previous studies underlook the crucial temporal information and constraints naturally behind multi-modal inputs. In this paper, we propose 4D unsupervised object discovery, jointly discovering objects from 4D data -- 3D point clouds and 2D RGB images with temporal information. We present the first practical approach for this task by proposing a ClusterNet on 3D point clouds, which is jointly iteratively optimized with a 2D localization network. Extensive experiments on the large-scale Waymo Open Dataset suggest that the localization network and ClusterNet achieve competitive performance on both class-agnostic 2D object detection and 3D instance segmentation, bridging the gap between unsupervised methods and full supervised ones. Codes and models will be made available at https://github.com/Robertwyq/LSMOL.
This paper addresses the challenging problem of open-vocabulary object detection (OVOD) where an object detector must identify both seen and unseen classes in test images without labeled examples of the unseen classes in training. A typical approach for OVOD is to use joint text-image embeddings of CLIP to assign box proposals to their closest text label. However, this method has a critical issue: many low-quality boxes, such as over- and under-covered-object boxes, have the same similarity score as high-quality boxes since CLIP is not trained on exact object location information. To address this issue, we propose a novel method, LP-OVOD, that discards low-quality boxes by training a sigmoid linear classifier on pseudo labels retrieved from the top relevant region proposals to the novel text. Experimental results on COCO affirm the superior performance of our approach over the state of the art, achieving $\textbf{40.5}$ in $\text{AP}_{novel}$ using ResNet50 as the backbone and without external datasets or knowing novel classes during training. Our code will be available at https://github.com/VinAIResearch/LP-OVOD.