Accurately detecting and tracking multi-objects is important for safety-critical applications such as autonomous navigation. However, it remains challenging to provide guarantees on the performance of state-of-the-art techniques based on deep learning. We consider a strategy known as conformal prediction, which predicts sets of labels instead of a single label; in the classification and regression settings, these algorithms can guarantee that the true label lies within the prediction set with high probability. Building on these ideas, we propose multi-object detection and tracking algorithms that come with probably approximately correct (PAC) guarantees. They do so by constructing both a prediction set around each object detection as well as around the set of edge transitions; given an object, the detection prediction set contains its true bounding box with high probability, and the edge prediction set contains its true transition across frames with high probability. We empirically demonstrate that our method can detect and track objects with PAC guarantees on the COCO and MOT-17 datasets.
Object detection and tracking in videos represent essential and computationally demanding building blocks for current and future visual perception systems. In order to reduce the efficiency gap between available methods and computational requirements of real-world applications, we propose to re-think one of the most successful methods for image object detection, Faster R-CNN, and extend it to the video domain. Specifically, we extend the detection framework to learn instance-level embeddings which prove beneficial for data association and re-identification purposes. Focusing on the computational aspects of detection and tracking, our proposed method reaches a very high computational efficiency necessary for relevant applications, while still managing to compete with recent and state-of-the-art methods as shown in the experiments we conduct on standard object tracking benchmarks
Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data. Though various self-training based and consistency-regularization based SSOD methods have been proposed, most of them are anchor-based detectors, ignoring the fact that in many real-world applications anchor-free detectors are more demanded. In this paper, we intend to bridge this gap and propose a DenSe Learning (DSL) based anchor-free SSOD algorithm. Specifically, we achieve this goal by introducing several novel techniques, including an Adaptive Filtering strategy for assigning multi-level and accurate dense pixel-wise pseudo-labels, an Aggregated Teacher for producing stable and precise pseudo-labels, and an uncertainty-consistency-regularization term among scales and shuffled patches for improving the generalization capability of the detector. Extensive experiments are conducted on MS-COCO and PASCAL-VOC, and the results show that our proposed DSL method records new state-of-the-art SSOD performance, surpassing existing methods by a large margin. Codes can be found at \textcolor{blue}{https://github.com/chenbinghui1/DSL}.
We propose an interactive approach for 3D instance segmentation, where users can iteratively collaborate with a deep learning model to segment objects in a 3D point cloud directly. Current methods for 3D instance segmentation are generally trained in a fully-supervised fashion, which requires large amounts of costly training labels, and does not generalize well to classes unseen during training. Few works have attempted to obtain 3D segmentation masks using human interactions. Existing methods rely on user feedback in the 2D image domain. As a consequence, users are required to constantly switch between 2D images and 3D representations, and custom architectures are employed to combine multiple input modalities. Therefore, integration with existing standard 3D models is not straightforward. The core idea of this work is to enable users to interact directly with 3D point clouds by clicking on desired 3D objects of interest~(or their background) to interactively segment the scene in an open-world setting. Specifically, our method does not require training data from any target domain, and can adapt to new environments where no appropriate training sets are available. Our system continuously adjusts the object segmentation based on the user feedback and achieves accurate dense 3D segmentation masks with minimal human effort (few clicks per object). Besides its potential for efficient labeling of large-scale and varied 3D datasets, our approach, where the user directly interacts with the 3D environment, enables new applications in AR/VR and human-robot interaction.
Forecasting of a representation is important for safe and effective autonomy. For this, panoptic segmentations have been studied as a compelling representation in recent work. However, recent state-of-the-art on panoptic segmentation forecasting suffers from two issues: first, individual object instances are treated independently of each other; second, individual object instance forecasts are merged in a heuristic manner. To address both issues, we study a new panoptic segmentation forecasting model that jointly forecasts all object instances in a scene using a transformer model based on 'difference attention.' It further refines the predictions by taking depth estimates into account. We evaluate the proposed model on the Cityscapes and AIODrive datasets. We find difference attention to be particularly suitable for forecasting because the difference of quantities like locations enables a model to explicitly reason about velocities and acceleration. Because of this, we attain state-of-the-art on panoptic segmentation forecasting metrics.
Our work aims to reconstruct hand-held objects given a single RGB image. In contrast to prior works that typically assume known 3D templates and reduce the problem to 3D pose estimation, our work reconstructs generic hand-held object without knowing their 3D templates. Our key insight is that hand articulation is highly predictive of the object shape, and we propose an approach that conditionally reconstructs the object based on the articulation and the visual input. Given an image depicting a hand-held object, we first use off-the-shelf systems to estimate the underlying hand pose and then infer the object shape in a normalized hand-centric coordinate frame. We parameterized the object by signed distance which are inferred by an implicit network which leverages the information from both visual feature and articulation-aware coordinates to process a query point. We perform experiments across three datasets and show that our method consistently outperforms baselines and is able to reconstruct a diverse set of objects. We analyze the benefits and robustness of explicit articulation conditioning and also show that this allows the hand pose estimation to further improve in test-time optimization.
We consider the problem of detecting and recognizing the objects observed by visitors (i.e., attended objects) in cultural sites from egocentric vision. A standard approach to the problem involves detecting all objects and selecting the one which best overlaps with the gaze of the visitor, measured through a gaze tracker. Since labeling large amounts of data to train a standard object detector is expensive in terms of costs and time, we propose a weakly supervised version of the task which leans only on gaze data and a frame-level label indicating the class of the attended object. To study the problem, we present a new dataset composed of egocentric videos and gaze coordinates of subjects visiting a museum. We hence compare three different baselines for weakly supervised attended object detection on the collected data. Results show that the considered approaches achieve satisfactory performance in a weakly supervised manner, which allows for significant time savings with respect to a fully supervised detector based on Faster R-CNN. To encourage research on the topic, we publicly release the code and the dataset at the following url: https://iplab.dmi.unict.it/WS_OBJ_DET/
We consider the problem of detecting Egocentric HumanObject Interactions (EHOIs) in industrial contexts. Since collecting and labeling large amounts of real images is challenging, we propose a pipeline and a tool to generate photo-realistic synthetic First Person Vision (FPV) images automatically labeled for EHOI detection in a specific industrial scenario. To tackle the problem of EHOI detection, we propose a method that detects the hands, the objects in the scene, and determines which objects are currently involved in an interaction. We compare the performance of our method with a set of state-of-the-art baselines. Results show that using a synthetic dataset improves the performance of an EHOI detection system, especially when few real data are available. To encourage research on this topic, we publicly release the proposed dataset at the following url: https://iplab.dmi.unict.it/EHOI_SYNTH/.
Modelling interactions between humans and objects in natural environments is central to many applications including gaming, virtual and mixed reality, as well as human behavior analysis and human-robot collaboration. This challenging operation scenario requires generalization to vast number of objects, scenes, and human actions. Unfortunately, there exist no such dataset. Moreover, this data needs to be acquired in diverse natural environments, which rules out 4D scanners and marker based capture systems. We present BEHAVE dataset, the first full body human- object interaction dataset with multi-view RGBD frames and corresponding 3D SMPL and object fits along with the annotated contacts between them. We record around 15k frames at 5 locations with 8 subjects performing a wide range of interactions with 20 common objects. We use this data to learn a model that can jointly track humans and objects in natural environments with an easy-to-use portable multi-camera setup. Our key insight is to predict correspondences from the human and the object to a statistical body model to obtain human-object contacts during interactions. Our approach can record and track not just the humans and objects but also their interactions, modeled as surface contacts, in 3D. Our code and data can be found at: http://virtualhumans.mpi-inf.mpg.de/behave
Weakly supervised object localization (WSOL) aims at predicting object locations in an image using only image-level category labels. Common challenges that image classification models encounter when localizing objects are, (a) they tend to look at the most discriminative features in an image that confines the localization map to a very small region, (b) the localization maps are class agnostic, and the models highlight objects of multiple classes in the same image and, (c) the localization performance is affected by background noise. To alleviate the above challenges we introduce the following simple changes through our proposed method ViTOL. We leverage the vision-based transformer for self-attention and introduce a patch-based attention dropout layer (p-ADL) to increase the coverage of the localization map and a gradient attention rollout mechanism to generate class-dependent attention maps. We conduct extensive quantitative, qualitative and ablation experiments on the ImageNet-1K and CUB datasets. We achieve state-of-the-art MaxBoxAcc-V2 localization scores of 70.47% and 73.17% on the two datasets respectively. Code is available on https://github.com/Saurav-31/ViTOL
Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing every-k frames in an external memory bank for future inference. Storing the intermediate frames' predictions provides the network with richer cues for segmenting an object in the current frame. However, the size of the memory bank gradually increases with the length of the video, which slows down inference speed and makes it impractical to handle arbitrary length videos. This paper proposes an adaptive memory bank strategy for matching-based networks for semi-supervised video object segmentation (VOS) that can handle videos of arbitrary length by discarding obsolete features. Features are indexed based on their importance in the segmentation of the objects in previous frames. Based on the index, we discard unimportant features to accommodate new features. We present our experiments on DAVIS 2016, DAVIS 2017, and Youtube-VOS that demonstrate that our method outperforms state-of-the-art that employ first-and-latest strategy with fixed-sized memory banks and achieves comparable performance to the every-k strategy with increasing-sized memory banks. Furthermore, experiments show that our method increases inference speed by up to 80% over the every-k and 35% over first-and-latest strategies.
Ground-truth depth, when combined with color data, helps improve object detection accuracy over baseline models that only use color. However, estimated depth does not always yield improvements. Many factors affect the performance of object detection when estimated depth is used. In this paper, we comprehensively investigate these factors with detailed experiments, such as using ground-truth vs. estimated depth, effects of different state-of-the-art depth estimation networks, effects of using different indoor and outdoor RGB-D datasets as training data for depth estimation, and different architectural choices for integrating depth to the base object detector network. We propose an early concatenation strategy of depth, which yields higher mAP than previous works' while using significantly fewer parameters.
Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the prediction logits due to its inefficiency in distilling the localization information. In this paper, we investigate whether logit mimicking always lags behind feature imitation. Towards this goal, we first present a novel localization distillation (LD) method which can efficiently transfer the localization knowledge from the teacher to the student. Second, we introduce the concept of valuable localization region that can aid to selectively distill the classification and localization knowledge for a certain region. Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking underperforms for years. The thorough studies exhibit the great potential of logit mimicking that can significantly alleviate the localization ambiguity, learn robust feature representation, and ease the training difficulty in the early stage. We also provide the theoretical connection between the proposed LD and the classification KD, that they share the equivalent optimization effect. Our distillation scheme is simple as well as effective and can be easily applied to both dense horizontal object detectors and rotated object detectors. Extensive experiments on the MS COCO, PASCAL VOC, and DOTA benchmarks demonstrate that our method can achieve considerable AP improvement without any sacrifice on the inference speed. Our source code and pretrained models are publicly available at https://github.com/HikariTJU/LD.
This paper presents an approach to estimating the continuous 6-DoF pose of an object from a single RGB image. The approach combines semantic keypoints predicted by a convolutional network (convnet) with a deformable shape model. Unlike prior investigators, we are agnostic to whether the object is textured or textureless, as the convnet learns the optimal representation from the available training-image data. Furthermore, the approach can be applied to instance- and class-based pose recovery. Additionally, we accompany our main pipeline with a technique for semi-automatic data generation from unlabeled videos. This procedure allows us to train the learnable components of our method with minimal manual intervention in the labeling process. Empirically, we show that our approach can accurately recover the 6-DoF object pose for both instance- and class-based scenarios even against a cluttered background. We apply our approach both to several, existing, large-scale datasets - including PASCAL3D+, LineMOD-Occluded, YCB-Video, and TUD-Light - and, using our labeling pipeline, to a new dataset with novel object classes that we introduce here. Extensive empirical evaluations show that our approach is able to provide pose estimation results comparable to the state of the art.
With the human pursuit of knowledge, open-set object detection (OSOD) has been designed to identify unknown objects in a dynamic world. However, an issue with the current setting is that all the predicted unknown objects share the same category as "unknown", which require incremental learning via a human-in-the-loop approach to label novel classes. In order to address this problem, we present a new task, namely Open-Set Object Detection and Discovery (OSODD). This new task aims to extend the ability of open-set object detectors to further discover the categories of unknown objects based on their visual appearance without human effort. We propose a two-stage method that first uses an open-set object detector to predict both known and unknown objects. Then, we study the representation of predicted objects in an unsupervised manner and discover new categories from the set of unknown objects. With this method, a detector is able to detect objects belonging to known classes and define novel categories for objects of unknown classes with minimal supervision. We show the performance of our model on the MS-COCO dataset under a thorough evaluation protocol. We hope that our work will promote further research towards a more robust real-world detection system.
A bathtub in a library, a sink in an office, a bed in a laundry room -- the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar objects. In this paper, we propose HyperDet3D to explore scene-conditioned prior knowledge for 3D object detection. Existing methods strive for better representation of local elements and their relations without scene-conditioned knowledge, which may cause ambiguity merely based on the understanding of individual points and object candidates. Instead, HyperDet3D simultaneously learns scene-agnostic embeddings and scene-specific knowledge through scene-conditioned hypernetworks. More specifically, our HyperDet3D not only explores the sharable abstracts from various 3D scenes, but also adapts the detector to the given scene at test time. We propose a discriminative Multi-head Scene-specific Attention (MSA) module to dynamically control the layer parameters of the detector conditioned on the fusion of scene-conditioned knowledge. Our HyperDet3D achieves state-of-the-art results on the 3D object detection benchmark of the ScanNet and SUN RGB-D datasets. Moreover, through cross-dataset evaluation, we show the acquired scene-conditioned prior knowledge still takes effect when facing 3D scenes with domain gap.
Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a trained classifier are widely used to provide pixel-level localization, but their focus tends to be restricted to a small discriminative region of the target object. An AdvCAM is an attribution map of an image that is manipulated to increase the classification score produced by a classifier before the final softmax or sigmoid layer. This manipulation is realized in an anti-adversarial manner, so that the original image is perturbed along pixel gradients in directions opposite to those used in an adversarial attack. This process enhances non-discriminative yet class-relevant features, which make an insufficient contribution to previous attribution maps, so that the resulting AdvCAM identifies more regions of the target object. In addition, we introduce a new regularization procedure that inhibits the incorrect attribution of regions unrelated to the target object and the excessive concentration of attributions on a small region of the target object. Our method achieves a new state-of-the-art performance in weakly and semi-supervised semantic segmentation, on both the PASCAL VOC 2012 and MS COCO 2014 datasets. In weakly supervised object localization, it achieves a new state-of-the-art performance on the CUB-200-2011 and ImageNet-1K datasets.
Single-stage detectors suffer from extreme foreground-background class imbalance, while two-stage detectors do not. Therefore, in semi-supervised object detection, two-stage detectors can deliver remarkable performance by only selecting high-quality pseudo labels based on classification scores. However, directly applying this strategy to single-stage detectors would aggravate the class imbalance with fewer positive samples. Thus, single-stage detectors have to consider both quality and quantity of pseudo labels simultaneously. In this paper, we design a dynamic self-adaptive threshold (DSAT) strategy in classification branch, which can automatically select pseudo labels to achieve an optimal trade-off between quality and quantity. Besides, to assess the regression quality of pseudo labels in single-stage detectors, we propose a module to compute the regression uncertainty of boxes based on Non-Maximum Suppression. By leveraging only 10% labeled data from COCO, our method achieves 35.0% AP on anchor-free detector (FCOS) and 32.9% on anchor-based detector (RetinaNet).
Existing object detection models assume both the training and test data are sampled from the same source domain. This assumption does not hold true when these detectors are deployed in real-world applications, where they encounter new visual domain. Unsupervised Domain Adaptation (UDA) methods are generally employed to mitigate the adverse effects caused by domain shift. Existing UDA methods operate in an offline manner where the model is first adapted towards the target domain and then deployed in real-world applications. However, this offline adaptation strategy is not suitable for real-world applications as the model frequently encounters new domain shifts. Hence, it becomes critical to develop a feasible UDA method that generalizes to these domain shifts encountered during deployment time in a continuous online manner. To this end, we propose a novel unified adaptation framework that adapts and improves generalization on the target domain in online settings. In particular, we introduce MemXformer - a cross-attention transformer-based memory module where items in the memory take advantage of domain shifts and record prototypical patterns of the target distribution. Further, MemXformer produces strong positive and negative pairs to guide a novel contrastive loss, which enhances target specific representation learning. Experiments on diverse detection benchmarks show that the proposed strategy can produce state-of-the-art performance in both online and offline settings. To the best of our knowledge, this is the first work to address online and offline adaptation settings for object detection. Code at https://github.com/Vibashan/memXformer-online-da
Evaluating tracking model performance is a complicated task, particularly for non-contiguous, multi-object trackers that are crucial in defense applications. While there are various excellent tracking benchmarks available, this work expands them to quantify the performance of long-term, non-contiguous, multi-object and detection model assisted trackers. We propose a suite of MONCE (Multi-Object Non-Contiguous Entities) image tracking metrics that provide both objective tracking model performance benchmarks as well as diagnostic insight for driving tracking model development in the form of Expected Average Overlap, Short/Long Term Re-Identification, Tracking Recall, Tracking Precision, Longevity, Localization and Absence Prediction.