This paper studies the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions. However, by relying on appearance alone, these methods fail to separate objects from the background in cluttered scenes. This is a fundamental limitation since the definition of an object is inherently ambiguous and context-dependent. To resolve this ambiguity, we choose to focus on dynamic objects -- entities that can move independently in the world. We then scale the recent auto-encoder based frameworks for unsupervised object discovery from toy synthetic images to complex real-world scenes. To this end, we simplify their architecture, and augment the resulting model with a weak learning signal from general motion segmentation algorithms. Our experiments demonstrate that, despite only capturing a small subset of the objects that move, this signal is enough to generalize to segment both moving and static instances of dynamic objects. We show that our model scales to a newly collected, photo-realistic synthetic dataset with street driving scenarios. Additionally, we leverage ground truth segmentation and flow annotations in this dataset for thorough ablation and evaluation. Finally, our experiments on the real-world KITTI benchmark demonstrate that the proposed approach outperforms both heuristic- and learning-based methods by capitalizing on motion cues.
We study the problem of efficient object detection of 3D LiDAR point clouds. To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic random sampling or farthest point sampling to progressively downsample input point clouds, despite the fact that not all points are equally important to the task of object detection. In particular, the foreground points are inherently more important than background points for object detectors. Motivated by this, we propose a highly-efficient single-stage point-based 3D detector in this paper, termed IA-SSD. The key of our approach is to exploit two learnable, task-oriented, instance-aware downsampling strategies to hierarchically select the foreground points belonging to objects of interest. Additionally, we also introduce a contextual centroid perception module to further estimate precise instance centers. Finally, we build our IA-SSD following the encoder-only architecture for efficiency. Extensive experiments conducted on several large-scale detection benchmarks demonstrate the competitive performance of our IA-SSD. Thanks to the low memory footprint and a high degree of parallelism, it achieves a superior speed of 80+ frames-per-second on the KITTI dataset with a single RTX2080Ti GPU. The code is available at \url{https://github.com/yifanzhang713/IA-SSD}.
We propose a new object-centric framework for learning-based stereo 3D object detection. Previous studies build scene-centric representations that do not consider the significant variation among outdoor instances and thus lack the flexibility and functionalities that an instance-level model can offer. We build such an instance-level model by formulating and tackling a local update problem, i.e., how to predict a refined update given an initial 3D cuboid guess. We demonstrate how solving this problem can complement scene-centric approaches in (i) building a coarse-to-fine multi-resolution system, (ii) performing model-agnostic object location refinement, and (iii) conducting stereo 3D tracking-by-detection. Extensive experiments demonstrate the effectiveness of our approach, which achieves state-of-the-art performance on the KITTI benchmark. Code and pre-trained models are available at https://github.com/Nicholasli1995/SNVC.
Monocular 3D object detection is an important yet challenging task in autonomous driving. Some existing methods leverage depth information from an off-the-shelf depth estimator to assist 3D detection, but suffer from the additional computational burden and achieve limited performance caused by inaccurate depth priors. To alleviate this, we propose MonoDTR, a novel end-to-end depth-aware transformer network for monocular 3D object detection. It mainly consists of two components: (1) the Depth-Aware Feature Enhancement (DFE) module that implicitly learns depth-aware features with auxiliary supervision without requiring extra computation, and (2) the Depth-Aware Transformer (DTR) module that globally integrates context- and depth-aware features. Moreover, different from conventional pixel-wise positional encodings, we introduce a novel depth positional encoding (DPE) to inject depth positional hints into transformers. Our proposed depth-aware modules can be easily plugged into existing image-only monocular 3D object detectors to improve the performance. Extensive experiments on the KITTI dataset demonstrate that our approach outperforms previous state-of-the-art monocular-based methods and achieves real-time detection. Code is available at https://github.com/kuanchihhuang/MonoDTR
Training CNN for detection is time-consuming due to the large dataset and complex network modules, making it hard to search architectures on detection datasets directly, which usually requires vast search costs (usually tens and even hundreds of GPU-days). In contrast, this paper introduces an efficient framework, named EAutoDet, that can discover practical backbone and FPN architectures for object detection in 1.4 GPU-days. Specifically, we construct a supernet for both backbone and FPN modules and adopt the differentiable method. To reduce the GPU memory requirement and computational cost, we propose a kernel reusing technique by sharing the weights of candidate operations on one edge and consolidating them into one convolution. A dynamic channel refinement strategy is also introduced to search channel numbers. Extensive experiments show significant efficacy and efficiency of our method. In particular, the discovered architectures surpass state-of-the-art object detection NAS methods and achieve 40.1 mAP with 120 FPS and 49.2 mAP with 41.3 FPS on COCO test-dev set. We also transfer the discovered architectures to rotation detection task, which achieve 77.05 mAP$_{\text{50}}$ on DOTA-v1.0 test set with 21.1M parameters.
Open-vocabulary object detection aims to detect novel object categories beyond the training set. The advanced open-vocabulary two-stage detectors employ instance-level visual-to-visual knowledge distillation to align the visual space of the detector with the semantic space of the Pre-trained Visual-Language Model (PVLM). However, in the more efficient one-stage detector, the absence of class-agnostic object proposals hinders the knowledge distillation on unseen objects, leading to severe performance degradation. In this paper, we propose a hierarchical visual-language knowledge distillation method, i.e., HierKD, for open-vocabulary one-stage detection. Specifically, a global-level knowledge distillation is explored to transfer the knowledge of unseen categories from the PVLM to the detector. Moreover, we combine the proposed global-level knowledge distillation and the common instance-level knowledge distillation to learn the knowledge of seen and unseen categories simultaneously. Extensive experiments on MS-COCO show that our method significantly surpasses the previous best one-stage detector with 11.9\% and 6.7\% $AP_{50}$ gains under the zero-shot detection and generalized zero-shot detection settings, and reduces the $AP_{50}$ performance gap from 14\% to 7.3\% compared to the best two-stage detector.
This paper presents a new vision Transformer, named Iwin Transformer, which is specifically designed for human-object interaction (HOI) detection, a detailed scene understanding task involving a sequential process of human/object detection and interaction recognition. Iwin Transformer is a hierarchical Transformer which progressively performs token representation learning and token agglomeration within irregular windows. The irregular windows, achieved by augmenting regular grid locations with learned offsets, 1) eliminate redundancy in token representation learning, which leads to efficient human/object detection, and 2) enable the agglomerated tokens to align with humans/objects with different shapes, which facilitates the acquisition of highly-abstracted visual semantics for interaction recognition. The effectiveness and efficiency of Iwin Transformer are verified on the two standard HOI detection benchmark datasets, HICO-DET and V-COCO. Results show our method outperforms existing Transformers-based methods by large margins (3.7 mAP gain on HICO-DET and 2.0 mAP gain on V-COCO) with fewer training epochs ($0.5 \times$).
The recent and rapid growth in Unmanned Aerial Vehicles (UAVs) deployment for various computer vision tasks has paved the path for numerous opportunities to make them more effective and valuable. Object detection in aerial images is challenging due to variations in appearance, pose, and scale. Autonomous aerial flight systems with their inherited limited memory and computational power demand accurate and computationally efficient detection algorithms for real-time applications. Our work shows the adaptation of the popular YOLOv4 framework for predicting the objects and their locations in aerial images with high accuracy and inference speed. We utilized transfer learning for faster convergence of the model on the VisDrone DET aerial object detection dataset. The trained model resulted in a mean average precision (mAP) of 45.64% with an inference speed reaching 8.7 FPS on the Tesla K80 GPU and was highly accurate in detecting truncated and occluded objects. We experimentally evaluated the impact of varying network resolution sizes and training epochs on the performance. A comparative study with several contemporary aerial object detectors proved that YOLOv4 performed better, implying a more suitable detection algorithm to incorporate on aerial platforms.
Affordance grounding, a task to ground (i.e., localize) action possibility region in objects, which faces the challenge of establishing an explicit link with object parts due to the diversity of interactive affordance. Human has the ability that transform the various exocentric interactions to invariant egocentric affordance so as to counter the impact of interactive diversity. To empower an agent with such ability, this paper proposes a task of affordance grounding from exocentric view, i.e., given exocentric human-object interaction and egocentric object images, learning the affordance knowledge of the object and transferring it to the egocentric image using only the affordance label as supervision. To this end, we devise a cross-view knowledge transfer framework that extracts affordance-specific features from exocentric interactions and enhances the perception of affordance regions by preserving affordance correlation. Specifically, an Affordance Invariance Mining module is devised to extract specific clues by minimizing the intra-class differences originated from interaction habits in exocentric images. Besides, an Affordance Co-relation Preserving strategy is presented to perceive and localize affordance by aligning the co-relation matrix of predicted results between the two views. Particularly, an affordance grounding dataset named AGD20K is constructed by collecting and labeling over 20K images from 36 affordance categories. Experimental results demonstrate that our method outperforms the representative models in terms of objective metrics and visual quality. Code: github.com/lhc1224/Cross-View-AG.
We present Laneformer, a conceptually simple yet powerful transformer-based architecture tailored for lane detection that is a long-standing research topic for visual perception in autonomous driving. The dominant paradigms rely on purely CNN-based architectures which often fail in incorporating relations of long-range lane points and global contexts induced by surrounding objects (e.g., pedestrians, vehicles). Inspired by recent advances of the transformer encoder-decoder architecture in various vision tasks, we move forwards to design a new end-to-end Laneformer architecture that revolutionizes the conventional transformers into better capturing the shape and semantic characteristics of lanes, with minimal overhead in latency. First, coupling with deformable pixel-wise self-attention in the encoder, Laneformer presents two new row and column self-attention operations to efficiently mine point context along with the lane shapes. Second, motivated by the appearing objects would affect the decision of predicting lane segments, Laneformer further includes the detected object instances as extra inputs of multi-head attention blocks in the encoder and decoder to facilitate the lane point detection by sensing semantic contexts. Specifically, the bounding box locations of objects are added into Key module to provide interaction with each pixel and query while the ROI-aligned features are inserted into Value module. Extensive experiments demonstrate our Laneformer achieves state-of-the-art performances on CULane benchmark, in terms of 77.1% F1 score. We hope our simple and effective Laneformer will serve as a strong baseline for future research in self-attention models for lane detection.
Long-horizon dexterous robot manipulation of deformable objects, such as banana peeling, is a problematic task because of the difficulties in object modeling and a lack of knowledge about stable and dexterous manipulation skills. This paper presents a goal-conditioned dual-action (GC-DA) deep imitation learning (DIL) approach that can learn dexterous manipulation skills using human demonstration data. Previous DIL methods map the current sensory input and reactive action, which often fails because of compounding errors in imitation learning caused by the recurrent computation of actions. The method predicts reactive action only when the precise manipulation of the target object is required (local action) and generates the entire trajectory when precise manipulation is not required (global action). This dual-action formulation effectively prevents compounding error in the imitation learning using the trajectory-based global action while responding to unexpected changes in the target object during the reactive local action. The proposed method was tested in a real dual-arm robot and successfully accomplished the banana-peeling task. Data from this and related works are available at: https://sites.google.com/view/multi-task-fine.
Label assignment (LA), which aims to assign each training sample a positive (pos) and a negative (neg) loss weight, plays an important role in object detection. Existing LA methods mostly focus on the design of pos weighting function, while the neg weight is directly derived from the pos weight. Such a mechanism limits the learning capacity of detectors. In this paper, we explore a new weighting paradigm, termed dual weighting (DW), to specify pos and neg weights separately. We first identify the key influential factors of pos/neg weights by analyzing the evaluation metrics in object detection, and then design the pos and neg weighting functions based on them. Specifically, the pos weight of a sample is determined by the consistency degree between its classification and localization scores, while the neg weight is decomposed into two terms: the probability that it is a neg sample and its importance conditioned on being a neg sample. Such a weighting strategy offers greater flexibility to distinguish between important and less important samples, resulting in a more effective object detector. Equipped with the proposed DW method, a single FCOS-ResNet-50 detector can reach 41.5% mAP on COCO under 1x schedule, outperforming other existing LA methods. It consistently improves the baselines on COCO by a large margin under various backbones without bells and whistles. Code is available at https://github.com/strongwolf/DW.
Learning semantic segmentation from weakly-labeled (e.g., image tags only) data is challenging since it is hard to infer dense object regions from sparse semantic tags. Despite being broadly studied, most current efforts directly learn from limited semantic annotations carried by individual image or image pairs, and struggle to obtain integral localization maps. Our work alleviates this from a novel perspective, by exploring rich semantic contexts synergistically among abundant weakly-labeled training data for network learning and inference. In particular, we propose regional semantic contrast and aggregation (RCA) . RCA is equipped with a regional memory bank to store massive, diverse object patterns appearing in training data, which acts as strong support for exploration of dataset-level semantic structure. Particularly, we propose i) semantic contrast to drive network learning by contrasting massive categorical object regions, leading to a more holistic object pattern understanding, and ii) semantic aggregation to gather diverse relational contexts in the memory to enrich semantic representations. In this manner, RCA earns a strong capability of fine-grained semantic understanding, and eventually establishes new state-of-the-art results on two popular benchmarks, i.e., PASCAL VOC 2012 and COCO 2014.
We present CoGS, a novel method for the style-conditioned, sketch-driven synthesis of images. CoGS enables exploration of diverse appearance possibilities for a given sketched object, enabling decoupled control over the structure and the appearance of the output. Coarse-grained control over object structure and appearance are enabled via an input sketch and an exemplar "style" conditioning image to a transformer-based sketch and style encoder to generate a discrete codebook representation. We map the codebook representation into a metric space, enabling fine-grained control over selection and interpolation between multiple synthesis options before generating the image via a vector quantized GAN (VQGAN) decoder. Our framework thereby unifies search and synthesis tasks, in that a sketch and style pair may be used to run an initial synthesis which may be refined via combination with similar results in a search corpus to produce an image more closely matching the user's intent. We show that our model, trained on the 125 object classes of our newly created Pseudosketches dataset, is capable of producing a diverse gamut of semantic content and appearance styles.
To perform adversarial attacks in the physical world, many studies have proposed adversarial camouflage, a method to hide a target object by applying camouflage patterns on 3D object surfaces. For obtaining optimal physical adversarial camouflage, previous studies have utilized the so-called neural renderer, as it supports differentiability. However, existing neural renderers cannot fully represent various real-world transformations due to a lack of control of scene parameters compared to the legacy photo-realistic renderers. In this paper, we propose the Differentiable Transformation Attack (DTA), a framework for generating a robust physical adversarial pattern on a target object to camouflage it against object detection models with a wide range of transformations. It utilizes our novel Differentiable Transformation Network (DTN), which learns the expected transformation of a rendered object when the texture is changed while preserving the original properties of the target object. Using our attack framework, an adversary can gain both the advantages of the legacy photo-realistic renderers including various physical-world transformations and the benefit of white-box access by offering differentiability. Our experiments show that our camouflaged 3D vehicles can successfully evade state-of-the-art object detection models in the photo-realistic environment (i.e., CARLA on Unreal Engine). Furthermore, our demonstration on a scaled Tesla Model 3 proves the applicability and transferability of our method to the real world.
Recent advancements in object shape completion have enabled impressive object reconstructions using only visual input. However, due to self-occlusion, the reconstructions have high uncertainty in the occluded object parts, which negatively impacts the performance of downstream robotic tasks such as grasping. In this work, we propose an active visuo-haptic shape completion method called Act-VH that actively computes where to touch the objects based on the reconstruction uncertainty. Act-VH reconstructs objects from point clouds and calculates the reconstruction uncertainty using IGR, a recent state-of-the-art implicit surface deep neural network. We experimentally evaluate the reconstruction accuracy of Act-VH against five baselines in simulation and in the real world. We also propose a new simulation environment for this purpose. The results show that Act-VH outperforms all baselines and that an uncertainty-driven haptic exploration policy leads to higher reconstruction accuracy than a random policy and a policy driven by Gaussian Process Implicit Surfaces. As a final experiment, we evaluate Act-VH and the best reconstruction baseline on grasping 10 novel objects. The results show that Act-VH reaches a significantly higher grasp success rate than the baseline on all objects. Together, this work opens up the door for using active visuo-haptic shape completion in more complex cluttered scenes.
Establishing correspondences from image to 3D has been a key task of 6DoF object pose estimation for a long time. To predict pose more accurately, deeply learned dense maps replaced sparse templates. Dense methods also improved pose estimation in the presence of occlusion. More recently researchers have shown improvements by learning object fragments as segmentation. In this work, we present a discrete descriptor, which can represent the object surface densely. By incorporating a hierarchical binary grouping, we can encode the object surface very efficiently. Moreover, we propose a coarse to fine training strategy, which enables fine-grained correspondence prediction. Finally, by matching predicted codes with object surface and using a PnP solver, we estimate the 6DoF pose. Results on the public LM-O and YCB-V datasets show major improvement over the state of the art w.r.t. ADD(-S) metric, even surpassing RGB-D based methods in some cases.
The saliency ranking task is recently proposed to study the visual behavior that humans would typically shift their attention over different objects of a scene based on their degrees of saliency. Existing approaches focus on learning either object-object or object-scene relations. Such a strategy follows the idea of object-based attention in Psychology, but it tends to favor those objects with strong semantics (e.g., humans), resulting in unrealistic saliency ranking. We observe that spatial attention works concurrently with object-based attention in the human visual recognition system. During the recognition process, the human spatial attention mechanism would move, engage, and disengage from region to region (i.e., context to context). This inspires us to model the region-level interactions, in addition to the object-level reasoning, for saliency ranking. To this end, we propose a novel bi-directional method to unify spatial attention and object-based attention for saliency ranking. Our model includes two novel modules: (1) a selective object saliency (SOS) module that models objectbased attention via inferring the semantic representation of the salient object, and (2) an object-context-object relation (OCOR) module that allocates saliency ranks to objects by jointly modeling the object-context and context-object interactions of the salient objects. Extensive experiments show that our approach outperforms existing state-of-theart methods. Our code and pretrained model are available at https://github.com/GrassBro/OCOR.
3D object recognition has seen significant advances in recent years, showing impressive performance on real-world 3D scan benchmarks, but lacking in object part reasoning, which is fundamental to higher-level scene understanding such as inter-object similarities or object functionality. Thus, we propose to leverage large-scale synthetic datasets of 3D shapes annotated with part information to learn Neural Part Priors (NPPs), optimizable spaces characterizing geometric part priors. Crucially, we can optimize over the learned part priors in order to fit to real-world scanned 3D scenes at test time, enabling robust part decomposition of the real objects in these scenes that also estimates the complete geometry of the object while fitting accurately to the observed real geometry. Moreover, this enables global optimization over geometrically similar detected objects in a scene, which often share strong geometric commonalities, enabling scene-consistent part decompositions. Experiments on the ScanNet dataset demonstrate that NPPs significantly outperforms state of the art in part decomposition and object completion in real-world scenes.
Many recent approaches in contrastive learning have worked to close the gap between pretraining on iconic images like ImageNet and pretraining on complex scenes like COCO. This gap exists largely because commonly used random crop augmentations obtain semantically inconsistent content in crowded scene images of diverse objects. Previous works use preprocessing pipelines to localize salient objects for improved cropping, but an end-to-end solution is still elusive. In this work, we propose a framework which accomplishes this goal via joint learning of representations and segmentation. We leverage segmentation masks to train a model with a mask-dependent contrastive loss, and use the partially trained model to bootstrap better masks. By iterating between these two components, we ground the contrastive updates in segmentation information, and simultaneously improve segmentation throughout pretraining. Experiments show our representations transfer robustly to downstream tasks in classification, detection and segmentation.