Humans are good at recomposing novel objects, i.e. they can identify commonalities between unknown objects from general structure to finer detail, an ability difficult to replicate by machines. We propose a framework, ISCO, to recompose an object using 3D superquadrics as semantic parts directly from 2D views without training a model that uses 3D supervision. To achieve this, we optimize the superquadric parameters that compose a specific instance of the object, comparing its rendered 3D view and 2D image silhouette. Our ISCO framework iteratively adds new superquadrics wherever the reconstruction error is high, abstracting first coarse regions and then finer details of the target object. With this simple coarse-to-fine inductive bias, ISCO provides consistent superquadrics for related object parts, despite not having any semantic supervision. Since ISCO does not train any neural network, it is also inherently robust to out-of-distribution objects. Experiments show that, compared to recent single instance superquadrics reconstruction approaches, ISCO provides consistently more accurate 3D reconstructions, even from images in the wild. Code available at https://github.com/ExplainableML/ISCO .
The annotation of 3D datasets is required for semantic-segmentation and object detection in scene understanding. In this paper we present a framework for the weakly supervision of a point clouds transformer that is used for 3D object detection. The aim is to decrease the required amount of supervision needed for training, as a result of the high cost of annotating a 3D datasets. We propose an Unsupervised Voting Proposal Module, which learns randomly preset anchor points and uses voting network to select prepared anchor points of high quality. Then it distills information into student and teacher network. In terms of student network, we apply ResNet network to efficiently extract local characteristics. However, it also can lose much global information. To provide the input which incorporates the global and local information as the input of student networks, we adopt the self-attention mechanism of transformer to extract global features, and the ResNet layers to extract region proposals. The teacher network supervises the classification and regression of the student network using the pre-trained model on ImageNet. On the challenging KITTI datasets, the experimental results have achieved the highest level of average precision compared with the most recent weakly supervised 3D object detectors.
Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. Benefiting from the capability of the self-attention mechanism to acquire long-range feature dependencies, Vision Transformer has been recently applied to alleviate the local activation drawbacks. However, since the transformer lacks the inductive localization bias that are inherent in CNNs, it may cause a divergent activation problem resulting in an uncertain distinction between foreground and background. In this work, we proposed a novel Semantic-Constraint Matching Network (SCMN) via a transformer to converge on the divergent activation. Specifically, we first propose a local patch shuffle strategy to construct the image pairs, disrupting local patches while guaranteeing global consistency. The paired images that contain the common object in spatial are then fed into the Siamese network encoder. We further design a semantic-constraint matching module, which aims to mine the co-object part by matching the coarse class activation maps (CAMs) extracted from the pair images, thus implicitly guiding and calibrating the transformer network to alleviate the divergent activation. Extensive experimental results conducted on two challenging benchmarks, including CUB-200-2011 and ILSVRC datasets show that our method can achieve the new state-of-the-art performance and outperform the previous method by a large margin.
The pre-trained text-image discriminative models, such as CLIP, has been explored for open-vocabulary semantic segmentation with unsatisfactory results due to the loss of crucial localization information and awareness of object shapes. Recently, there has been a growing interest in expanding the application of generative models from generation tasks to semantic segmentation. These approaches utilize generative models either for generating annotated data or extracting features to facilitate semantic segmentation. This typically involves generating a considerable amount of synthetic data or requiring additional mask annotations. To this end, we uncover the potential of generative text-to-image diffusion models (e.g., Stable Diffusion) as highly efficient open-vocabulary semantic segmenters, and introduce a novel training-free approach named DiffSegmenter. The insight is that to generate realistic objects that are semantically faithful to the input text, both the complete object shapes and the corresponding semantics are implicitly learned by diffusion models. We discover that the object shapes are characterized by the self-attention maps while the semantics are indicated through the cross-attention maps produced by the denoising U-Net, forming the basis of our segmentation results.Additionally, we carefully design effective textual prompts and a category filtering mechanism to further enhance the segmentation results. Extensive experiments on three benchmark datasets show that the proposed DiffSegmenter achieves impressive results for open-vocabulary semantic segmentation.
Referring image segmentation aims to segment the target referent in an image conditioning on a natural language expression. Existing one-stage methods employ per-pixel classification frameworks, which attempt straightforwardly to align vision and language at the pixel level, thus failing to capture critical object-level information. In this paper, we propose a mask classification framework, Contrastive Grouping with Transformer network (CGFormer), which explicitly captures object-level information via token-based querying and grouping strategy. Specifically, CGFormer first introduces learnable query tokens to represent objects and then alternately queries linguistic features and groups visual features into the query tokens for object-aware cross-modal reasoning. In addition, CGFormer achieves cross-level interaction by jointly updating the query tokens and decoding masks in every two consecutive layers. Finally, CGFormer cooperates contrastive learning to the grouping strategy to identify the token and its mask corresponding to the referent. Experimental results demonstrate that CGFormer outperforms state-of-the-art methods in both segmentation and generalization settings consistently and significantly.
As an essential component part of the Intelligent Transportation System (ITS), the Internet of Vehicles (IoV) plays a vital role in alleviating traffic issues. Object detection is one of the key technologies in the IoV, which has been widely used to provide traffic management services by analyzing timely and sensitive vehicle-related information. However, the current object detection methods are mostly based on centralized deep training, that is, the sensitive data obtained by edge devices need to be uploaded to the server, which raises privacy concerns. To mitigate such privacy leakage, we first propose a federated learning-based framework, where well-trained local models are shared in the central server. However, since edge devices usually have limited computing power, plus a strict requirement of low latency in IoVs, we further propose a sparse training process on edge devices, which can effectively lighten the model, and ensure its training efficiency on edge devices, thereby reducing communication overheads. In addition, due to the diverse computing capabilities and dynamic environment, different sparsity rates are applied to edge devices. To further guarantee the performance, we propose, FedWeg, an improved aggregation scheme based on FedAvg, which is designed by the inverse ratio of sparsity rates. Experiments on the real-life dataset using YOLO show that the proposed scheme can achieve the required object detection rate while saving considerable communication costs.
3D dense captioning requires a model to translate its understanding of an input 3D scene into several captions associated with different object regions. Existing methods adopt a sophisticated "detect-then-describe" pipeline, which builds explicit relation modules upon a 3D detector with numerous hand-crafted components. While these methods have achieved initial success, the cascade pipeline tends to accumulate errors because of duplicated and inaccurate box estimations and messy 3D scenes. In this paper, we first propose Vote2Cap-DETR, a simple-yet-effective transformer framework that decouples the decoding process of caption generation and object localization through parallel decoding. Moreover, we argue that object localization and description generation require different levels of scene understanding, which could be challenging for a shared set of queries to capture. To this end, we propose an advanced version, Vote2Cap-DETR++, which decouples the queries into localization and caption queries to capture task-specific features. Additionally, we introduce the iterative spatial refinement strategy to vote queries for faster convergence and better localization performance. We also insert additional spatial information to the caption head for more accurate descriptions. Without bells and whistles, extensive experiments on two commonly used datasets, ScanRefer and Nr3D, demonstrate Vote2Cap-DETR and Vote2Cap-DETR++ surpass conventional "detect-then-describe" methods by a large margin. Codes will be made available at https://github.com/ch3cook-fdu/Vote2Cap-DETR.
Despite powering sensitive systems like autonomous vehicles, object detection remains fairly brittle in part due to annotation errors that plague most real-world training datasets. We propose ObjectLab, a straightforward algorithm to detect diverse errors in object detection labels, including: overlooked bounding boxes, badly located boxes, and incorrect class label assignments. ObjectLab utilizes any trained object detection model to score the label quality of each image, such that mislabeled images can be automatically prioritized for label review/correction. Properly handling erroneous data enables training a better version of the same object detection model, without any change in existing modeling code. Across different object detection datasets (including COCO) and different models (including Detectron-X101 and Faster-RCNN), ObjectLab consistently detects annotation errors with much better precision/recall compared to other label quality scores.
3D object detection is an essential task for achieving autonomous driving. Existing anchor-based detection methods rely on empirical heuristics setting of anchors, which makes the algorithms lack elegance. In recent years, we have witnessed the rise of several generative models, among which diffusion models show great potential for learning the transformation of two distributions. Our proposed Diff3Det migrates the diffusion model to proposal generation for 3D object detection by considering the detection boxes as generative targets. During training, the object boxes diffuse from the ground truth boxes to the Gaussian distribution, and the decoder learns to reverse this noise process. In the inference stage, the model progressively refines a set of random boxes to the prediction results. We provide detailed experiments on the KITTI benchmark and achieve promising performance compared to classical anchor-based 3D detection methods.
Designing a video detection network based on state-of-the-art single-image object detectors may seem like an obvious choice. However, video object detection has extra challenges due to the lower quality of individual frames in a video, and hence the need to include temporal information for high-quality detection results. We design a novel interleaved architecture combining a 2D convolutional network and a 3D temporal network. To explore inter-frame information, we propose feature aggregation based on a temporal network. Our TemporalNet utilizes Appearance-preserving 3D convolution (AP3D) for extracting aligned features in the temporal dimension. Our temporal network functions at multiple scales for better performance, which allows communication between 2D and 3D blocks at each scale and also across scales. Our TemporalNet is a plug-and-play block that can be added to a multi-scale single-image detection network without any adjustments in the network architecture. When TemporalNet is applied to Yolov3 it is real-time with a running time of 35ms/frame on a low-end GPU. Our real-time approach achieves 77.1 % mAP (mean Average Precision) on ImageNet VID 2017 dataset with TemporalNet-4, where TemporalNet-16 achieves 80.9 % mAP which is a competitive result.
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines. Unfortunately, they lack two key properties: objects are often split into parts and are not consistently tracked over time. In fact, state-of-the-art models achieve pixel-level accuracy and temporal consistency by relying on supervised object detection with additional ID labels for the association through time. This paper proposes a video object-centric model for MOT. It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module that builds complete object prototypes to handle occlusions. Benefited from object-centric learning, we only require sparse detection labels (0%-6.25%) for object localization and feature binding. Relying on our self-supervised Expectation-Maximization-inspired loss for object association, our approach requires no ID labels. Our experiments significantly narrow the gap between the existing object-centric model and the fully supervised state-of-the-art and outperform several unsupervised trackers.
Open-vocabulary detection (OVD) is a new object detection paradigm, aiming to localize and recognize unseen objects defined by an unbounded vocabulary. This is challenging since traditional detectors can only learn from pre-defined categories and thus fail to detect and localize objects out of pre-defined vocabulary. To handle the challenge, OVD leverages pre-trained cross-modal VLM, such as CLIP, ALIGN, etc. Previous works mainly focus on the open vocabulary classification part, with less attention on the localization part. We argue that for a good OVD detector, both classification and localization should be parallelly studied for the novel object categories. We show in this work that improving localization as well as cross-modal classification complement each other, and compose a good OVD detector jointly. We analyze three families of OVD methods with different design emphases. We first propose a vanilla method,i.e., cropping a bounding box obtained by a localizer and resizing it into the CLIP. We next introduce another approach, which combines a standard two-stage object detector with CLIP. A two-stage object detector includes a visual backbone, a region proposal network (RPN), and a region of interest (RoI) head. We decouple RPN and ROI head (DRR) and use RoIAlign to extract meaningful features. In this case, it avoids resizing objects. To further accelerate the training time and reduce the model parameters, we couple RPN and ROI head (CRR) as the third approach. We conduct extensive experiments on these three types of approaches in different settings. On the OVD-COCO benchmark, DRR obtains the best performance and achieves 35.8 Novel AP$_{50}$, an absolute 2.8 gain over the previous state-of-the-art (SOTA). For OVD-LVIS, DRR surpasses the previous SOTA by 1.9 AP$_{50}$ in rare categories. We also provide an object detection dataset called PID and provide a baseline on PID.
Object proposal generation serves as a standard pre-processing step in Vision-Language (VL) tasks (image captioning, visual question answering, etc.). The performance of object proposals generated for VL tasks is currently evaluated across all available annotations, a protocol that we show is misaligned - higher scores do not necessarily correspond to improved performance on downstream VL tasks. Our work serves as a study of this phenomenon and explores the effectiveness of semantic grounding to mitigate its effects. To this end, we propose evaluating object proposals against only a subset of available annotations, selected by thresholding an annotation importance score. Importance of object annotations to VL tasks is quantified by extracting relevant semantic information from text describing the image. We show that our method is consistent and demonstrates greatly improved alignment with annotations selected by image captioning metrics and human annotation when compared against existing techniques. Lastly, we compare current detectors used in the Scene Graph Generation (SGG) benchmark as a use case, which serves as an example of when traditional object proposal evaluation techniques are misaligned.
The proliferation of Deep Neural Networks has resulted in machine learning systems becoming increasingly more present in various real-world applications. Consequently, there is a growing demand for highly reliable models in many domains, making the problem of uncertainty calibration pivotal when considering the future of deep learning. This is especially true when considering object detection systems, that are commonly present in safety-critical applications such as autonomous driving, robotics and medical diagnosis. For this reason, this work presents a novel theoretical and practical framework to evaluate object detection systems in the context of uncertainty calibration. This encompasses a new comprehensive formulation of this concept through distinct formal definitions, and also three novel evaluation metrics derived from such theoretical foundation. The robustness of the proposed uncertainty calibration metrics is shown through a series of representative experiments.
Amodal object segmentation is a challenging task that involves segmenting both visible and occluded parts of an object. In this paper, we propose a novel approach, called Coarse-to-Fine Segmentation (C2F-Seg), that addresses this problem by progressively modeling the amodal segmentation. C2F-Seg initially reduces the learning space from the pixel-level image space to the vector-quantized latent space. This enables us to better handle long-range dependencies and learn a coarse-grained amodal segment from visual features and visible segments. However, this latent space lacks detailed information about the object, which makes it difficult to provide a precise segmentation directly. To address this issue, we propose a convolution refine module to inject fine-grained information and provide a more precise amodal object segmentation based on visual features and coarse-predicted segmentation. To help the studies of amodal object segmentation, we create a synthetic amodal dataset, named as MOViD-Amodal (MOViD-A), which can be used for both image and video amodal object segmentation. We extensively evaluate our model on two benchmark datasets: KINS and COCO-A. Our empirical results demonstrate the superiority of C2F-Seg. Moreover, we exhibit the potential of our approach for video amodal object segmentation tasks on FISHBOWL and our proposed MOViD-A. Project page at: http://jianxgao.github.io/C2F-Seg.
The SoccerNet 2023 tracking challenge requires the detection and tracking of soccer players and the ball. In this work, we present our approach to tackle these tasks separately. We employ a state-of-the-art online multi-object tracker and a contemporary object detector for player tracking. To overcome the limitations of our online approach, we incorporate a post-processing stage using interpolation and appearance-free track merging. Additionally, an appearance-based track merging technique is used to handle the termination and creation of tracks far from the image boundaries. Ball tracking is formulated as single object detection, and a fine-tuned YOLOv8l detector with proprietary filtering improves the detection precision. Our method achieves 3rd place on the SoccerNet 2023 tracking challenge with a HOTA score of 66.27.
To enable meaningful robotic manipulation of objects in the real-world, 6D pose estimation is one of the critical aspects. Most existing approaches have difficulties to extend predictions to scenarios where novel object instances are continuously introduced, especially with heavy occlusions. In this work, we propose a few-shot pose estimation (FSPE) approach called SA6D, which uses a self-adaptive segmentation module to identify the novel target object and construct a point cloud model of the target object using only a small number of cluttered reference images. Unlike existing methods, SA6D does not require object-centric reference images or any additional object information, making it a more generalizable and scalable solution across categories. We evaluate SA6D on real-world tabletop object datasets and demonstrate that SA6D outperforms existing FSPE methods, particularly in cluttered scenes with occlusions, while requiring fewer reference images.
Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly introduced knowledge. Current OWOD models, such as ORE and OW-DETR, focus on pseudo-labeling regions with high objectness scores as unknowns, whose performance relies heavily on the supervision of known objects. While they can detect the unknowns that exhibit similar features to the known objects, they suffer from a severe label bias problem that they tend to detect all regions (including unknown object regions) that are dissimilar to the known objects as part of the background. To eliminate the label bias, this paper proposes a novel approach that learns an unsupervised discriminative model to recognize true unknown objects from raw pseudo labels generated by unsupervised region proposal methods. The resulting model can be further refined by a classification-free self-training method which iteratively extends pseudo unknown objects to the unlabeled regions. Experimental results show that our method 1) significantly outperforms the prior SOTA in detecting unknown objects while maintaining competitive performance of detecting known object classes on the MS COCO dataset, and 2) achieves better generalization ability on the LVIS and Objects365 datasets.
LiDAR point clouds can effectively depict the motion and posture of objects in three-dimensional space. Many studies accomplish the 3D object detection by voxelizing point clouds. However, in autonomous driving scenarios, the sparsity and hollowness of point clouds create some difficulties for voxel-based methods. The sparsity of point clouds makes it challenging to describe the geometric features of objects. The hollowness of point clouds poses difficulties for the aggregation of 3D features. We propose a two-stage 3D object detection framework, called MS23D. (1) We propose a method using voxel feature points from multi-branch to construct the 3D feature layer. Using voxel feature points from different branches, we construct a relatively compact 3D feature layer with rich semantic features. Additionally, we propose a distance-weighted sampling method, reducing the loss of foreground points caused by downsampling and allowing the 3D feature layer to retain more foreground points. (2) In response to the hollowness of point clouds, we predict the offsets between deep-level feature points and the object's centroid, making them as close as possible to the object's centroid. This enables the aggregation of these feature points with abundant semantic features. For feature points from shallow-level, we retain them on the object's surface to describe the geometric features of the object. To validate our approach, we evaluated its effectiveness on both the KITTI and ONCE datasets.
The unprecedented advancements in Large Language Models (LLMs) have shown a profound impact on natural language processing but are yet to fully embrace the realm of 3D understanding. This paper introduces PointLLM, a preliminary effort to fill this gap, enabling LLMs to understand point clouds and offering a new avenue beyond 2D visual data. PointLLM understands colored object point clouds with human instructions and generates contextually appropriate responses, illustrating its grasp of point clouds and common sense. Specifically, it leverages a point cloud encoder with a powerful LLM to effectively fuse geometric, appearance, and linguistic information. We collect a novel dataset comprising 660K simple and 70K complex point-text instruction pairs to enable a two-stage training strategy: aligning latent spaces and subsequently instruction-tuning the unified model. To rigorously evaluate the perceptual and generalization capabilities of PointLLM, we establish two benchmarks: Generative 3D Object Classification and 3D Object Captioning, assessed through three different methods, including human evaluation, GPT-4/ChatGPT evaluation, and traditional metrics. Experimental results reveal PointLLM's superior performance over existing 2D and 3D baselines, with a notable achievement in human-evaluated object captioning tasks where it surpasses human annotators in over 50% of the samples. Codes, datasets, and benchmarks are available at https://github.com/OpenRobotLab/PointLLM .