Object detection in low-light conditions remains a challenging but important problem with many practical implications. Some recent works show that, in low-light conditions, object detectors using raw image data are more robust than detectors using image data processed by a traditional ISP pipeline. To improve detection performance in low-light conditions, one can fine-tune the detector to use raw image data or use a dedicated low-light neural pipeline trained with paired low- and normal-light data to restore and enhance the image. However, different camera sensors have different spectral sensitivity and learning-based models using raw images process data in the sensor-specific color space. Thus, once trained, they do not guarantee generalization to other camera sensors. We propose to improve generalization to unseen camera sensors by implementing a minimal neural ISP pipeline for machine cognition, named GenISP, that explicitly incorporates Color Space Transformation to a device-independent color space. We also propose a two-stage color processing implemented by two image-to-parameter modules that take down-sized image as input and regress global color correction parameters. Moreover, we propose to train our proposed GenISP under the guidance of a pre-trained object detector and avoid making assumptions about perceptual quality of the image, but rather optimize the image representation for machine cognition. At the inference stage, GenISP can be paired with any object detector. We perform extensive experiments to compare our method to other low-light image restoration and enhancement methods in an extrinsic task-based evaluation and validate that GenISP can generalize to unseen sensors and object detectors. Finally, we contribute a low-light dataset of 7K raw images annotated with 46K bounding boxes for task-based benchmarking of future low-light image restoration and object detection.
Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense point clouds and performance drops significantly for sparse point clouds. Unsupervised domain adaption allows to minimise the discrepancy between dense and sparse point clouds with minimal unlabelled sparse point clouds, thereby saving additional sparse data collection, annotation and retraining costs. In this work, we propose a novel method for point cloud based object recognition with competitive performance with state-of-art methods on dense and sparse point clouds while being trained only with dense point clouds.
The widespread image applications have greatly promoted the vision-based tasks, in which the Image Quality Assessment (IQA) technique has become an increasingly significant issue. For user enjoyment in multimedia systems, the IQA exploits image fidelity and aesthetics to characterize user experience; while for other tasks such as popular object recognition, there exists a low correlation between utilities and perceptions. In such cases, the fidelity-based and aesthetics-based IQA methods cannot be directly applied. To address this issue, this paper proposes a utility-oriented IQA in object recognition. In particular, we initialize our research in the scenario of underwater fish detection, which is a critical task that has not yet been perfectly addressed. Based on this task, we build an Underwater Image Utility Database (UIUD) and a learning-based Underwater Image Utility Measure (UIUM). Inspired by the top-down design of fidelity-based IQA, we exploit the deep models of object recognition and transfer their features to our UIUM. Experiments validate that the proposed transfer-learning-based UIUM achieves promising performance in the recognition task. We envision our research provides insights to bridge the researches of IQA and computer vision.
In object detection, non-maximum suppression (NMS) methods are extensively adopted to remove horizontal duplicates of detected dense boxes for generating final object instances. However, due to the degraded quality of dense detection boxes and not explicit exploration of the context information, existing NMS methods via simple intersection-over-union (IoU) metrics tend to underperform on multi-oriented and long-size objects detection. Distinguishing with general NMS methods via duplicate removal, we propose a novel graph fusion network, named GFNet, for multi-oriented object detection. Our GFNet is extensible and adaptively fuse dense detection boxes to detect more accurate and holistic multi-oriented object instances. Specifically, we first adopt a locality-aware clustering algorithm to group dense detection boxes into different clusters. We will construct an instance sub-graph for the detection boxes belonging to one cluster. Then, we propose a graph-based fusion network via Graph Convolutional Network (GCN) to learn to reason and fuse the detection boxes for generating final instance boxes. Extensive experiments both on public available multi-oriented text datasets (including MSRA-TD500, ICDAR2015, ICDAR2017-MLT) and multi-oriented object datasets (DOTA) verify the effectiveness and robustness of our method against general NMS methods in multi-oriented object detection.
We present Panoptic Neural Fields (PNF), an object-aware neural scene representation that decomposes a scene into a set of objects (things) and background (stuff). Each object is represented by an oriented 3D bounding box and a multi-layer perceptron (MLP) that takes position, direction, and time and outputs density and radiance. The background stuff is represented by a similar MLP that additionally outputs semantic labels. Each object MLPs are instance-specific and thus can be smaller and faster than previous object-aware approaches, while still leveraging category-specific priors incorporated via meta-learned initialization. Our model builds a panoptic radiance field representation of any scene from just color images. We use off-the-shelf algorithms to predict camera poses, object tracks, and 2D image semantic segmentations. Then we jointly optimize the MLP weights and bounding box parameters using analysis-by-synthesis with self-supervision from color images and pseudo-supervision from predicted semantic segmentations. During experiments with real-world dynamic scenes, we find that our model can be used effectively for several tasks like novel view synthesis, 2D panoptic segmentation, 3D scene editing, and multiview depth prediction.
Multimodal supervision has achieved promising results in many visual language understanding tasks, where the language plays an essential role as a hint or context for recognizing and locating instances. However, due to the defects of the human-annotated language corpus, multimodal supervision remains unexplored in fully supervised object detection scenarios. In this paper, we take advantage of language prompt to introduce effective and unbiased linguistic supervision into object detection, and propose a new mechanism called multimodal knowledge learning (\textbf{MKL}), which is required to learn knowledge from language supervision. Specifically, we design prompts and fill them with the bounding box annotations to generate descriptions containing extensive hints and context for instances recognition and localization. The knowledge from language is then distilled into the detection model via maximizing cross-modal mutual information in both image- and object-level. Moreover, the generated descriptions are manipulated to produce hard negatives to further boost the detector performance. Extensive experiments demonstrate that the proposed method yields a consistent performance gain by 1.6\% $\sim$ 2.1\% and achieves state-of-the-art on MS-COCO and OpenImages datasets.
Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on incremental object detection that rely on the availability of abundant training samples per novel class that substantially limits the scalability to real-world setting where novel data can be scarce. In this paper, we propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector. To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision from additional object proposals generated using Selective Search as pseudo labels. We further introduce an incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without forgetting the base classes. Extensive experiments conducted on standard incremental object detection and incremental few-shot object detection settings show that our approach significantly outperforms state-of-the-art methods by a large margin.
This paper studies the task of any objects grasping from the known categories by free-form language instructions. This task demands the technique in computer vision, natural language processing, and robotics. We bring these disciplines together on this open challenge, which is essential to human-robot interaction. Critically, the key challenge lies in inferring the category of objects from linguistic instructions and accurately estimating the 6-DoF information of unseen objects from the known classes. In contrast, previous works focus on inferring the pose of object candidates at the instance level. This significantly limits its applications in real-world scenarios.In this paper, we propose a language-guided 6-DoF category-level object localization model to achieve robotic grasping by comprehending human intention. To this end, we propose a novel two-stage method. Particularly, the first stage grounds the target in the RGB image through language description of names, attributes, and spatial relations of objects. The second stage extracts and segments point clouds from the cropped depth image and estimates the full 6-DoF object pose at category-level. Under such a manner, our approach can locate the specific object by following human instructions, and estimate the full 6-DoF pose of a category-known but unseen instance which is not utilized for training the model. Extensive experimental results show that our method is competitive with the state-of-the-art language-conditioned grasp method. Importantly, we deploy our approach on a physical robot to validate the usability of our framework in real-world applications. Please refer to the supplementary for the demo videos of our robot experiments.
In-memory computing is becoming a popular architecture for deep-learning hardware accelerators recently due to its highly parallel computing, low power, and low area cost. However, in-RRAM computing (IRC) suffered from large device variation and numerous nonideal effects in hardware. Although previous approaches including these effects in model training successfully improved variation tolerance, they only considered part of the nonideal effects and relatively simple classification tasks. This paper proposes a joint hardware and software optimization strategy to design a hardware-robust IRC macro for object detection. We lower the cell current by using a low word-line voltage to enable a complete convolution calculation in one operation that minimizes the impact of nonlinear addition. We also implement ternary weight mapping and remove batch normalization for better tolerance against device variation, sense amplifier variation, and IR drop problem. An extra bias is included to overcome the limitation of the current sensing range. The proposed approach has been successfully applied to a complex object detection task with only 3.85\% mAP drop, whereas a naive design suffers catastrophic failure under these nonideal effects.
Neural scene representations, both continuous and discrete, have recently emerged as a powerful new paradigm for 3D scene understanding. Recent efforts have tackled unsupervised discovery of object-centric neural scene representations. However, the high cost of ray-marching, exacerbated by the fact that each object representation has to be ray-marched separately, leads to insufficiently sampled radiance fields and thus, noisy renderings, poor framerates, and high memory and time complexity during training and rendering. Here, we propose to represent objects in an object-centric, compositional scene representation as light fields. We propose a novel light field compositor module that enables reconstructing the global light field from a set of object-centric light fields. Dubbed Compositional Object Light Fields (COLF), our method enables unsupervised learning of object-centric neural scene representations, state-of-the-art reconstruction and novel view synthesis performance on standard datasets, and rendering and training speeds at orders of magnitude faster than existing 3D approaches.
Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism. Existing transformer-based approaches adopt the pixel-to-pixel attention strategy on flattened image features and unavoidably ignore the integrity of objects. In this paper, we propose a new transformer architecture with multi-scale cyclic shifting window attention for visual object tracking, elevating the attention from pixel to window level. The cross-window multi-scale attention has the advantage of aggregating attention at different scales and generates the best fine-scale match for the target object. Furthermore, the cyclic shifting strategy brings greater accuracy by expanding the window samples with positional information, and at the same time saves huge amounts of computational power by removing redundant calculations. Extensive experiments demonstrate the superior performance of our method, which also sets the new state-of-the-art records on five challenging datasets, along with the VOT2020, UAV123, LaSOT, TrackingNet, and GOT-10k benchmarks.
Significant progress has been made on visual captioning, largely relying on pre-trained features and later fixed object detectors that serve as rich inputs to auto-regressive models. A key limitation of such methods, however, is that the output of the model is conditioned only on the object detector's outputs. The assumption that such outputs can represent all necessary information is unrealistic, especially when the detector is transferred across datasets. In this work, we reason about the graphical model induced by this assumption, and propose to add an auxiliary input to represent missing information such as object relationships. We specifically propose to mine attributes and relationships from the Visual Genome dataset and condition the captioning model on them. Crucially, we propose (and show to be important) the use of a multi-modal pre-trained model (CLIP) to retrieve such contextual descriptions. Further, object detector models are frozen and do not have sufficient richness to allow the captioning model to properly ground them. As a result, we propose to condition both the detector and description outputs on the image, and show qualitatively and quantitatively that this can improve grounding. We validate our method on image captioning, perform thorough analyses of each component and importance of the pre-trained multi-modal model, and demonstrate significant improvements over the current state of the art, specifically +7.5% in CIDEr and +1.3% in BLEU-4 metrics.
Dark environment becomes a challenge for computer vision algorithms owing to insufficient photons and undesirable noise. To enhance object detection in a dark environment, we propose a novel multitask auto encoding transformation (MAET) model which is able to explore the intrinsic pattern behind illumination translation. In a self-supervision manner, the MAET learns the intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation considering the physical noise model and image signal processing (ISP). Based on this representation, we achieve the object detection task by decoding the bounding box coordinates and classes. To avoid the over-entanglement of two tasks, our MAET disentangles the object and degrading features by imposing an orthogonal tangent regularity. This forms a parametric manifold along which multitask predictions can be geometrically formulated by maximizing the orthogonality between the tangents along the outputs of respective tasks. Our framework can be implemented based on the mainstream object detection architecture and directly trained end-to-end using normal target detection datasets, such as VOC and COCO. We have achieved the state-of-the-art performance using synthetic and real-world datasets. Code is available at https://github.com/cuiziteng/MAET.
Moving object segmentation (MOS) is a task to distinguish moving objects, e.g., moving vehicles and pedestrians, from the surrounding static environment. The segmentation accuracy of MOS can have an influence on odometry, map construction, and planning tasks. In this paper, we propose a semantics-guided convolutional neural network for moving object segmentation. The network takes sequential LiDAR range images as inputs. Instead of segmenting the moving objects directly, the network conducts single-scan-based semantic segmentation and multiple-scan-based moving object segmentation in turn. The semantic segmentation module provides semantic priors for the MOS module, where we propose an adjacent scan association (ASA) module to convert the semantic features of adjacent scans into the same coordinate system to fully exploit the cross-scan semantic features. Finally, by analyzing the difference between the transformed features, reliable MOS result can be obtained quickly. Experimental results on the SemanticKITTI MOS dataset proves the effectiveness of our work.
Continual learning is a challenging real-world problem for constructing a mature AI system when data are provided in a streaming fashion. Despite recent progress in continual classification, the researches of continual object detection are impeded by the diverse sizes and numbers of objects in each image. Different from previous works that tune the whole network for all tasks, in this work, we present a simple and flexible framework for continual object detection via pRotOtypical taSk corrElaTion guided gaTing mechAnism (ROSETTA). Concretely, a unified framework is shared by all tasks while task-aware gates are introduced to automatically select sub-models for specific tasks. In this way, various knowledge can be successively memorized by storing their corresponding sub-model weights in this system. To make ROSETTA automatically determine which experience is available and useful, a prototypical task correlation guided Gating Diversity Controller(GDC) is introduced to adaptively adjust the diversity of gates for the new task based on class-specific prototypes. GDC module computes class-to-class correlation matrix to depict the cross-task correlation, and hereby activates more exclusive gates for the new task if a significant domain gap is observed. Comprehensive experiments on COCO-VOC, KITTI-Kitchen, class-incremental detection on VOC and sequential learning of four tasks show that ROSETTA yields state-of-the-art performance on both task-based and class-based continual object detection.
Which object detector is suitable for your context sensitive task? Deep object detectors exploit scene context for recognition differently. In this paper, we group object detectors into 3 categories in terms of context use: no context by cropping the input (RCNN), partial context by cropping the featuremap (two-stage methods) and full context without any cropping (single-stage methods). We systematically evaluate the effect of context for each deep detector category. We create a fully controlled dataset for varying context and investigate the context for deep detectors. We also evaluate gradually removing the background context and the foreground object on MS COCO. We demonstrate that single-stage and two-stage object detectors can and will use the context by virtue of their large receptive field. Thus, choosing the best object detector may depend on the application context.
Domain Generalization is a challenging topic in computer vision, especially in Gastrointestinal Endoscopy image analysis. Due to several device limitations and ethical reasons, current open-source datasets are typically collected on a limited number of patients using the same brand of sensors. Different brands of devices and individual differences will significantly affect the model's generalizability. Therefore, to address the generalization problem in GI(Gastrointestinal) endoscopy, we propose a multi-domain GI dataset and a light, plug-in block called InvNorm(Invertible Normalization), which could achieve a better generalization performance in any structure. Previous DG(Domain Generalization) methods fail to achieve invertible transformation, which would lead to some misleading augmentation. Moreover, these models would be more likely to lead to medical ethics issues. Our method utilizes normalizing flow to achieve invertible and explainable style normalization to address the problem. The effectiveness of InvNorm is demonstrated on a wide range of tasks, including GI recognition, GI object detection, and natural image recognition.
Our world is not static and humans naturally cause changes in their environments through interactions, e.g., opening doors or moving furniture. Modeling changes caused by humans is essential for building digital twins, e.g., in the context of shared physical-virtual spaces (metaverses) and robotics. In order for widespread adoption of such emerging applications, the sensor setup used to capture the interactions needs to be inexpensive and easy-to-use for non-expert users. I.e., interactions should be captured and modeled by simple ego-centric sensors such as a combination of cameras and IMU sensors, not relying on any external cameras or object trackers. Yet, to the best of our knowledge, no work tackling the challenging problem of modeling human-scene interactions via such an ego-centric sensor setup exists. This paper closes this gap in the literature by developing a novel approach that combines visual localization of humans in the scene with contact-based reasoning about human-scene interactions from IMU data. Interestingly, we can show that even without visual observations of the interactions, human-scene contacts and interactions can be realistically predicted from human pose sequences. Our method, iReplica (Interaction Replica), is an essential first step towards the egocentric capture of human interactions and modeling of dynamic scenes, which is required for future AR/VR applications in immersive virtual universes and for training machines to behave like humans. Our code, data and model are available on our project page at http://virtualhumans.mpi-inf.mpg.de/ireplica/
Deep neural networks are rapidly emerging as data analysis tools, often outperforming the conventional techniques used in complex microfluidic systems. One fundamental analysis frequently desired in microfluidic experiments is counting and tracking the droplets. Specifically, droplet tracking in dense emulsions is challenging as droplets move in tightly packed configurations. Sometimes the individual droplets in these dense clusters are hard to resolve, even for a human observer. Here, two deep learning-based cutting-edge algorithms for object detection (YOLO) and object tracking (DeepSORT) are combined into a single image analysis tool, DropTrack, to track droplets in microfluidic experiments. DropTrack analyzes input videos, extracts droplets' trajectories, and infers other observables of interest, such as droplet numbers. Training an object detector network for droplet recognition with manually annotated images is a labor-intensive task and a persistent bottleneck. This work partly resolves this problem by training object detector networks (YOLOv5) with hybrid datasets containing real and synthetic images. We present an analysis of a double emulsion experiment as a case study to measure DropTrack's performance. For our test case, the YOLO networks trained with 60% synthetic images show similar performance in droplet counting as with the one trained using 100% real images, meanwhile saving the image annotation work by 60%. DropTrack's performance is measured in terms of mean average precision (mAP), mean square error in counting the droplets, and inference speed. The fastest configuration of DropTrack runs inference at about 30 frames per second, well within the standards for real-time image analysis.
6D object pose estimation is a crucial prerequisite for autonomous robot manipulation applications. The state-of-the-art models for pose estimation are convolutional neural network (CNN)-based. Lately, Transformers, an architecture originally proposed for natural language processing, is achieving state-of-the-art results in many computer vision tasks as well. Equipped with the multi-head self-attention mechanism, Transformers enable simple single-stage end-to-end architectures for learning object detection and 6D object pose estimation jointly. In this work, we propose YOLOPose (short form for You Only Look Once Pose estimation), a Transformer-based multi-object 6D pose estimation method based on keypoint regression. In contrast to the standard heatmaps for predicting keypoints in an image, we directly regress the keypoints. Additionally, we employ a learnable orientation estimation module to predict the orientation from the keypoints. Along with a separate translation estimation module, our model is end-to-end differentiable. Our method is suitable for real-time applications and achieves results comparable to state-of-the-art methods.