An object detector's ability to detect and flag \textit{novel} objects during open-world deployments is critical for many real-world applications. Unfortunately, much of the work in open object detection today is disjointed and fails to adequately address applications that prioritize unknown object recall \textit{in addition to} known-class accuracy. To close this gap, we present a new task called Open-Set Object Detection and Discovery (OSODD) and as a solution propose the Open-Set Regions with ViT features (OSR-ViT) detection framework. OSR-ViT combines a class-agnostic proposal network with a powerful ViT-based classifier. Its modular design simplifies optimization and allows users to easily swap proposal solutions and feature extractors to best suit their application. Using our multifaceted evaluation protocol, we show that OSR-ViT obtains performance levels that far exceed state-of-the-art supervised methods. Our method also excels in low-data settings, outperforming supervised baselines using a fraction of the training data.
This paper introduces Multi-Resolution Rescored Byte-Track (MR2-ByteTrack), a novel video object detection framework for ultra-low-power embedded processors. This method reduces the average compute load of an off-the-shelf Deep Neural Network (DNN) based object detector by up to 2.25$\times$ by alternating the processing of high-resolution images (320$\times$320 pixels) with multiple down-sized frames (192$\times$192 pixels). To tackle the accuracy degradation due to the reduced image input size, MR2-ByteTrack correlates the output detections over time using the ByteTrack tracker and corrects potential misclassification using a novel probabilistic Rescore algorithm. By interleaving two down-sized images for every high-resolution one as the input of different state-of-the-art DNN object detectors with our MR2-ByteTrack, we demonstrate an average accuracy increase of 2.16% and a latency reduction of 43% on the GAP9 microcontroller compared to a baseline frame-by-frame inference scheme using exclusively full-resolution images. Code available at: https://github.com/Bomps4/Multi_Resolution_Rescored_ByteTrack
Generating background scenes for salient objects plays a crucial role across various domains including creative design and e-commerce, as it enhances the presentation and context of subjects by integrating them into tailored environments. Background generation can be framed as a task of text-conditioned outpainting, where the goal is to extend image content beyond a salient object's boundaries on a blank background. Although popular diffusion models for text-guided inpainting can also be used for outpainting by mask inversion, they are trained to fill in missing parts of an image rather than to place an object into a scene. Consequently, when used for background creation, inpainting models frequently extend the salient object's boundaries and thereby change the object's identity, which is a phenomenon we call "object expansion." This paper introduces a model for adapting inpainting diffusion models to the salient object outpainting task using Stable Diffusion and ControlNet architectures. We present a series of qualitative and quantitative results across models and datasets, including a newly proposed metric to measure object expansion that does not require any human labeling. Compared to Stable Diffusion 2.0 Inpainting, our proposed approach reduces object expansion by 3.6x on average with no degradation in standard visual metrics across multiple datasets.
We present TeSMo, a method for text-controlled scene-aware motion generation based on denoising diffusion models. Previous text-to-motion methods focus on characters in isolation without considering scenes due to the limited availability of datasets that include motion, text descriptions, and interactive scenes. Our approach begins with pre-training a scene-agnostic text-to-motion diffusion model, emphasizing goal-reaching constraints on large-scale motion-capture datasets. We then enhance this model with a scene-aware component, fine-tuned using data augmented with detailed scene information, including ground plane and object shapes. To facilitate training, we embed annotated navigation and interaction motions within scenes. The proposed method produces realistic and diverse human-object interactions, such as navigation and sitting, in different scenes with various object shapes, orientations, initial body positions, and poses. Extensive experiments demonstrate that our approach surpasses prior techniques in terms of the plausibility of human-scene interactions, as well as the realism and variety of the generated motions. Code will be released upon publication of this work at https://research.nvidia.com/labs/toronto-ai/tesmo.
State-of-the-art Multiple Object Tracking (MOT) approaches have shown remarkable performance when trained and evaluated on current benchmarks. However, these benchmarks primarily consist of clear weather scenarios, overlooking adverse atmospheric conditions such as fog, haze, smoke and dust. As a result, the robustness of trackers against these challenging conditions remains underexplored. To address this gap, we introduce physics-based volumetric fog simulation method for arbitrary MOT datasets, utilizing frame-by-frame monocular depth estimation and a fog formation optical model. We enhance our simulation by rendering both homogeneous and heterogeneous fog and propose to use the dark channel prior method to estimate atmospheric light, showing promising results even in night and indoor scenes. We present the leading benchmark MOTChallenge (third release) augmented with fog (smoke for indoor scenes) of various intensities and conduct a comprehensive evaluation of MOT methods, revealing their limitations under fog and fog-like challenges.
Weakly Supervised Object Localization (WSOL) allows training deep learning models for classification and localization (LOC) using only global class-level labels. The absence of bounding box (bbox) supervision during training raises challenges in the literature for hyper-parameter tuning, model selection, and evaluation. WSOL methods rely on a validation set with bbox annotations for model selection, and a test set with bbox annotations for threshold estimation for producing bboxes from localization maps. This approach, however, is not aligned with the WSOL setting as these annotations are typically unavailable in real-world scenarios. Our initial empirical analysis shows a significant decline in LOC performance when model selection and threshold estimation rely solely on class labels and the image itself, respectively, compared to using manual bbox annotations. This highlights the importance of incorporating bbox labels for optimal model performance. In this paper, a new WSOL evaluation protocol is proposed that provides LOC information without the need for manual bbox annotations. In particular, we generated noisy pseudo-boxes from a pretrained off-the-shelf region proposal method such as Selective Search, CLIP, and RPN for model selection. These bboxes are also employed to estimate the threshold from LOC maps, circumventing the need for test-set bbox annotations. Our experiments with several WSOL methods on ILSVRC and CUB datasets show that using the proposed pseudo-bboxes for validation facilitates the model selection and threshold estimation, with LOC performance comparable to those selected using GT bboxes on the validation set and threshold estimation on the test set. It also outperforms models selected using class-level labels, and then dynamically thresholded based solely on LOC maps.
Large Vision Language Models (VLMs) are now the de facto state-of-the-art for a number of tasks including visual question answering, recognising objects, and spatial referral. In this work, we propose the HOI-Ref task for egocentric images that aims to understand interactions between hands and objects using VLMs. To enable HOI-Ref, we curate the HOI-QA dataset that consists of 3.9M question-answer pairs for training and evaluating VLMs. HOI-QA includes questions relating to locating hands, objects, and critically their interactions (e.g. referring to the object being manipulated by the hand). We train the first VLM for HOI-Ref on this dataset and call it VLM4HOI. Our results demonstrate that VLMs trained for referral on third person images fail to recognise and refer hands and objects in egocentric images. When fine-tuned on our egocentric HOI-QA dataset, performance improves by 27.9% for referring hands and objects, and by 26.7% for referring interactions.
Coreset selection is a method for selecting a small, representative subset of an entire dataset. It has been primarily researched in image classification, assuming there is only one object per image. However, coreset selection for object detection is more challenging as an image can contain multiple objects. As a result, much research has yet to be done on this topic. Therefore, we introduce a new approach, Coreset Selection for Object Detection (CSOD). CSOD generates imagewise and classwise representative feature vectors for multiple objects of the same class within each image. Subsequently, we adopt submodular optimization for considering both representativeness and diversity and utilize the representative vectors in the submodular optimization process to select a subset. When we evaluated CSOD on the Pascal VOC dataset, CSOD outperformed random selection by +6.4%p in AP$_{50}$ when selecting 200 images.
Degraded underwater images decrease the accuracy of underwater object detection. However, existing methods for underwater image enhancement mainly focus on improving the indicators in visual aspects, which may not benefit the tasks of underwater image detection, and may lead to serious degradation in performance. To alleviate this problem, we proposed a bidirectional-guided method for underwater object detection, referred to as BG-YOLO. In the proposed method, network is organized by constructing an enhancement branch and a detection branch in a parallel way. The enhancement branch consists of a cascade of an image enhancement subnet and an object detection subnet. And the detection branch only consists of a detection subnet. A feature guided module connects the shallow convolution layer of the two branches. When training the enhancement branch, the object detection subnet in the enhancement branch guides the image enhancement subnet to be optimized towards the direction that is most conducive to the detection task. The shallow feature map of the trained enhancement branch will be output to the feature guided module, constraining the optimization of detection branch through consistency loss and prompting detection branch to learn more detailed information of the objects. And hence the detection performance will be refined. During the detection tasks, only detection branch will be reserved so that no additional cost of computation will be introduced. Extensive experiments demonstrate that the proposed method shows significant improvement in performance of the detector in severely degraded underwater scenes while maintaining a remarkable detection speed.
This research paper proposes a novel methodology for image-to-image style transfer on objects utilizing a single deep convolutional neural network. The proposed approach leverages the You Only Look Once version 8 (YOLOv8) segmentation model and the backbone neural network of YOLOv8 for style transfer. The primary objective is to enhance the visual appeal of objects in images by seamlessly transferring artistic styles while preserving the original object characteristics. The proposed approach's novelty lies in combining segmentation and style transfer in a single deep convolutional neural network. This approach omits the need for multiple stages or models, thus resulting in simpler training and deployment of the model for practical applications. The results of this approach are shown on two content images by applying different style images. The paper also demonstrates the ability to apply style transfer on multiple objects in the same image.
Due to its cost-effectiveness and widespread availability, monocular 3D object detection, which relies solely on a single camera during inference, holds significant importance across various applications, including autonomous driving and robotics. Nevertheless, directly predicting the coordinates of objects in 3D space from monocular images poses challenges. Therefore, an effective solution involves transforming monocular images into LiDAR-like representations and employing a LiDAR-based 3D object detector to predict the 3D coordinates of objects. The key step in this method is accurately converting the monocular image into a reliable point cloud form. In this paper, we present VFMM3D, an innovative framework that leverages the capabilities of Vision Foundation Models (VFMs) to accurately transform single-view images into LiDAR point cloud representations. VFMM3D utilizes the Segment Anything Model (SAM) and Depth Anything Model (DAM) to generate high-quality pseudo-LiDAR data enriched with rich foreground information. Specifically, the Depth Anything Model (DAM) is employed to generate dense depth maps. Subsequently, the Segment Anything Model (SAM) is utilized to differentiate foreground and background regions by predicting instance masks. These predicted instance masks and depth maps are then combined and projected into 3D space to generate pseudo-LiDAR points. Finally, any object detectors based on point clouds can be utilized to predict the 3D coordinates of objects. Comprehensive experiments are conducted on two challenging 3D object detection datasets, KITTI and Waymo. Our VFMM3D establishes a new state-of-the-art performance on both datasets. Additionally, experimental results demonstrate the generality of VFMM3D, showcasing its seamless integration into various LiDAR-based 3D object detectors.
Existing open-vocabulary object detectors typically require a predefined set of categories from users, significantly confining their application scenarios. In this paper, we introduce DetCLIPv3, a high-performing detector that excels not only at both open-vocabulary object detection, but also generating hierarchical labels for detected objects. DetCLIPv3 is characterized by three core designs: 1. Versatile model architecture: we derive a robust open-set detection framework which is further empowered with generation ability via the integration of a caption head. 2. High information density data: we develop an auto-annotation pipeline leveraging visual large language model to refine captions for large-scale image-text pairs, providing rich, multi-granular object labels to enhance the training. 3. Efficient training strategy: we employ a pre-training stage with low-resolution inputs that enables the object captioner to efficiently learn a broad spectrum of visual concepts from extensive image-text paired data. This is followed by a fine-tuning stage that leverages a small number of high-resolution samples to further enhance detection performance. With these effective designs, DetCLIPv3 demonstrates superior open-vocabulary detection performance, \eg, our Swin-T backbone model achieves a notable 47.0 zero-shot fixed AP on the LVIS minival benchmark, outperforming GLIPv2, GroundingDINO, and DetCLIPv2 by 18.0/19.6/6.6 AP, respectively. DetCLIPv3 also achieves a state-of-the-art 19.7 AP in dense captioning task on VG dataset, showcasing its strong generative capability.
Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object localization, which aims to train a neural network capable of predicting both the object class and its location using only images and their image-level class labels. The proposed framework consists of a shared feature extractor, a classifier, and a localizer. The localizer predicts pixel-level class probabilities, while the classifier predicts the object class at the image level. Since image-level class labels are insufficient for training the localizer, weakly-supervised object localization methods often encounter challenges in accurately localizing the entire object region. To address this issue, the proposed method incorporates adversarial erasing and pseudo labels to improve localization accuracy. Specifically, novel losses are designed to utilize adversarially erased foreground features and adversarially erased feature maps, reducing dependence on the most discriminative region. Additionally, the proposed method employs pseudo labels to suppress activation values in the background while increasing them in the foreground. The proposed method is applied to two backbone networks (MobileNetV1 and InceptionV3) and is evaluated on three publicly available datasets (ILSVRC-2012, CUB-200-2011, and PASCAL VOC 2012). The experimental results demonstrate that the proposed method outperforms previous state-of-the-art methods across all evaluated metrics.
Research on diffusion model-based video generation has advanced rapidly. However, limitations in object fidelity and generation length hinder its practical applications. Additionally, specific domains like animated wallpapers require seamless looping, where the first and last frames of the video match seamlessly. To address these challenges, this paper proposes LoopAnimate, a novel method for generating videos with consistent start and end frames. To enhance object fidelity, we introduce a framework that decouples multi-level image appearance and textual semantic information. Building upon an image-to-image diffusion model, our approach incorporates both pixel-level and feature-level information from the input image, injecting image appearance and textual semantic embeddings at different positions of the diffusion model. Existing UNet-based video generation models require to input the entire videos during training to encode temporal and positional information at once. However, due to limitations in GPU memory, the number of frames is typically restricted to 16. To address this, this paper proposes a three-stage training strategy with progressively increasing frame numbers and reducing fine-tuning modules. Additionally, we introduce the Temporal E nhanced Motion Module(TEMM) to extend the capacity for encoding temporal and positional information up to 36 frames. The proposed LoopAnimate, which for the first time extends the single-pass generation length of UNet-based video generation models to 35 frames while maintaining high-quality video generation. Experiments demonstrate that LoopAnimate achieves state-of-the-art performance in both objective metrics, such as fidelity and temporal consistency, and subjective evaluation results.
Cross-modality fusing complementary information from different modalities effectively improves object detection performance, making it more useful and robust for a wider range of applications. Existing fusion strategies combine different types of images or merge different backbone features through elaborated neural network modules. However, these methods neglect that modality disparities affect cross-modality fusion performance, as different modalities with different camera focal lengths, placements, and angles are hardly fused. In this paper, we investigate cross-modality fusion by associating cross-modal features in a hidden state space based on an improved Mamba with a gating mechanism. We design a Fusion-Mamba block (FMB) to map cross-modal features into a hidden state space for interaction, thereby reducing disparities between cross-modal features and enhancing the representation consistency of fused features. FMB contains two modules: the State Space Channel Swapping (SSCS) module facilitates shallow feature fusion, and the Dual State Space Fusion (DSSF) enables deep fusion in a hidden state space. Through extensive experiments on public datasets, our proposed approach outperforms the state-of-the-art methods on $m$AP with 5.9% on $M^3FD$ and 4.9% on FLIR-Aligned datasets, demonstrating superior object detection performance. To the best of our knowledge, this is the first work to explore the potential of Mamba for cross-modal fusion and establish a new baseline for cross-modality object detection.
Open-vocabulary object detection (OVOD) aims at localizing and recognizing visual objects from novel classes unseen at the training time. Whereas, empirical studies reveal that advanced detectors generally assign lower scores to those novel instances, which are inadvertently suppressed during inference by commonly adopted greedy strategies like Non-Maximum Suppression (NMS), leading to sub-optimal detection performance for novel classes. This paper systematically investigates this problem with the commonly-adopted two-stage OVOD paradigm. Specifically, in the region-proposal stage, proposals that contain novel instances showcase lower objectness scores, since they are treated as background proposals during the training phase. Meanwhile, in the object-classification stage, novel objects share lower region-text similarities (i.e., classification scores) due to the biased visual-language alignment by seen training samples. To alleviate this problem, this paper introduces two advanced measures to adjust confidence scores and conserve erroneously dismissed objects: (1) a class-agnostic localization quality estimate via overlap degree of region/object proposals, and (2) a text-guided visual similarity estimate with proxy prototypes for novel classes. Integrated with adjusting techniques specifically designed for the region-proposal and object-classification stages, this paper derives the aggregated confidence estimate for the open-vocabulary object detection paradigm (AggDet). Our AggDet is a generic and training-free post-processing scheme, which consistently bolsters open-vocabulary detectors across model scales and architecture designs. For instance, AggDet receives 3.3% and 1.5% gains on OV-COCO and OV-LVIS benchmarks respectively, without any training cost.
The interactive segmentation task consists in the creation of object segmentation masks based on user interactions. The most common way to guide a model towards producing a correct segmentation consists in clicks on the object and background. The recently published Segment Anything Model (SAM) supports a generalized version of the interactive segmentation problem and has been trained on an object segmentation dataset which contains 1.1B masks. Though being trained extensively and with the explicit purpose of serving as a foundation model, we show significant limitations of SAM when being applied for interactive segmentation on novel domains or object types. On the used datasets, SAM displays a failure rate $\text{FR}_{30}@90$ of up to $72.6 \%$. Since we still want such foundation models to be immediately applicable, we present a framework that can adapt SAM during immediate usage. For this we will leverage the user interactions and masks, which are constructed during the interactive segmentation process. We use this information to generate pseudo-labels, which we use to compute a loss function and optimize a part of the SAM model. The presented method causes a relative reduction of up to $48.1 \%$ in the $\text{FR}_{20}@85$ and $46.6 \%$ in the $\text{FR}_{30}@90$ metrics.
The generalization of the end-to-end deep reinforcement learning (DRL) for object-goal visual navigation is a long-standing challenge since object classes and placements vary in new test environments. Learning domain-independent visual representation is critical for enabling the trained DRL agent with the ability to generalize to unseen scenes and objects. In this letter, a target-directed attention network (TDANet) is proposed to learn the end-to-end object-goal visual navigation policy with zero-shot ability. TDANet features a novel target attention (TA) module that learns both the spatial and semantic relationships among objects to help TDANet focus on the most relevant observed objects to the target. With the Siamese architecture (SA) design, TDANet distinguishes the difference between the current and target states and generates the domain-independent visual representation. To evaluate the navigation performance of TDANet, extensive experiments are conducted in the AI2-THOR embodied AI environment. The simulation results demonstrate a strong generalization ability of TDANet to unseen scenes and target objects, with higher navigation success rate (SR) and success weighted by length (SPL) than other state-of-the-art models. TDANet is finally deployed on a wheeled robot in real scenes, demonstrating satisfactory generalization of TDANet to the real world.
This paper focuses on improving object detection performance by addressing the issue of image distortions, commonly encountered in uncontrolled acquisition environments. High-level computer vision tasks such as object detection, recognition, and segmentation are particularly sensitive to image distortion. To address this issue, we propose a novel approach employing an image defilter to rectify image distortion prior to object detection. This method enhances object detection accuracy, as models perform optimally when trained on non-distorted images. Our experiments demonstrate that utilizing defiltered images significantly improves mean average precision compared to training object detection models on distorted images. Consequently, our proposed method offers considerable benefits for real-world applications plagued by image distortion. To our knowledge, the contribution lies in employing distortion-removal paradigm for object detection on images captured in natural settings. We achieved an improvement of 0.562 and 0.564 of mean Average precision on validation and test data.
Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. The complexity of this task increases with the intricacy of the sentences provided. Existing methods have relied mostly on visual features to generate the segmentation masks while treating text features as supporting components. However, this under-utilization of text understanding limits the model's capability to fully comprehend the given expressions. In this work, we propose a novel framework that specifically emphasizes object and context comprehension inspired by human cognitive processes through Vision-Aware Text Features. Firstly, we introduce a CLIP Prior module to localize the main object of interest and embed the object heatmap into the query initialization process. Secondly, we propose a combination of two components: Contextual Multimodal Decoder and Meaning Consistency Constraint, to further enhance the coherent and consistent interpretation of language cues with the contextual understanding obtained from the image. Our method achieves significant performance improvements on three benchmark datasets RefCOCO, RefCOCO+ and G-Ref. Project page: \url{https://vatex.hkustvgd.com/}.