Spiking neural networks (SNNs) operating with asynchronous discrete events show higher energy efficiency with sparse computation. A popular approach for implementing deep SNNs is ANN-SNN conversion combining both efficient training of ANNs and efficient inference of SNNs. However, the accuracy loss is usually non-negligible, especially under a few time steps, which restricts the applications of SNN on latency-sensitive edge devices greatly. In this paper, we first identify that such performance degradation stems from the misrepresentation of the negative or overflow residual membrane potential in SNNs. Inspired by this, we decompose the conversion error into three parts: quantization error, clipping error, and residual membrane potential representation error. With such insights, we propose a two-stage conversion algorithm to minimize those errors respectively. Besides, We show each stage achieves significant performance gains in a complementary manner. By evaluating on challenging datasets including CIFAR-10, CIFAR- 100 and ImageNet, the proposed method demonstrates the state-of-the-art performance in terms of accuracy, latency and energy preservation. Furthermore, our method is evaluated using a more challenging object detection task, revealing notable gains in regression performance under ultra-low latency when compared to existing spike-based detection algorithms. Codes are available at https://github.com/Windere/snn-cvt-dual-phase.
Global Positioning Systems (GPS) have played a crucial role in various navigation applications. Nevertheless, localizing the perfect destination within the last few meters remains an important but unresolved problem. Limited by the GPS positioning accuracy, navigation systems always show users a vicinity of a destination, but not its exact location. Street view images (SVI) in maps as an immersive media technology have served as an aid to provide the physical environment for human last-meters wayfinding. However, due to the large diversity of geographic context and acquisition conditions, the captured SVI always contains various distracting objects (e.g., pedestrians and vehicles), which will distract human visual attention from efficiently finding the destination in the last few meters. To address this problem, we highlight the importance of reducing visual distraction in image-based wayfinding by proposing a saliency-guided image inpainting framework. It aims at redirecting human visual attention from distracting objects to destination-related objects for more efficient and accurate wayfinding in the last meters. Specifically, a context-aware distracting object detection method driven by deep salient object detection has been designed to extract distracting objects from three semantic levels in SVI. Then we employ a large-mask inpainting method with fast Fourier convolutions to remove the detected distracting objects. Experimental results with both qualitative and quantitative analysis show that our saliency-guided inpainting method can not only achieve great perceptual quality in street view images but also redirect the human's visual attention to focus more on static location-related objects than distracting ones. The human-based evaluation also justified the effectiveness of our method in improving the efficiency of locating the target destination.
In the emerging field of video coding for machines, video datasets with pristine video quality and high-quality annotations are required for a comprehensive evaluation. However, existing video datasets with detailed annotations are severely limited in size and video quality. Thus, current methods have to either evaluate their codecs on still images or on already compressed data. To mitigate this problem, we propose an evaluation method based on pseudo ground-truth data from the field of semantic segmentation to the evaluation of video coding for machines. Through extensive evaluation, this paper shows that the proposed ground-truth-agnostic evaluation method results in an acceptable absolute measurement error below 0.7 percentage points on the Bjontegaard Delta Rate compared to using the true ground truth for mid-range bitrates. We evaluate on the three tasks of semantic segmentation, instance segmentation, and object detection. Lastly, we utilize the ground-truth-agnostic method to measure the coding performances of the VVC compared against HEVC on the Cityscapes sequences. This reveals that the coding position has a significant influence on the task performance.
Deep neural object detection or segmentation networks are commonly trained with pristine, uncompressed data. However, in practical applications the input images are usually deteriorated by compression that is applied to efficiently transmit the data. Thus, we propose to add deteriorated images to the training process in order to increase the robustness of the two state-of-the-art networks Faster and Mask R-CNN. Throughout our paper, we investigate an autonomous driving scenario by evaluating the newly trained models on the Cityscapes dataset that has been compressed with the upcoming video coding standard Versatile Video Coding (VVC). When employing the models that have been trained with the proposed method, the weighted average precision of the R-CNNs can be increased by up to 3.68 percentage points for compressed input images, which corresponds to bitrate savings of nearly 48 %.
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and open-vocabulary setting, where training data is relatively scarce. In this paper, we propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. Our analysis of the scaling properties of this setup shows that increasing image-level pre-training and model size yield consistent improvements on the downstream detection task. We provide the adaptation strategies and regularizations needed to attain very strong performance on zero-shot text-conditioned and one-shot image-conditioned object detection. Code and models are available on GitHub.
In this work, we propose an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes. It is a two-stage training approach that first uses a location-guided image-caption matching technique to learn class labels for both novel and known classes in a weakly-supervised manner and second specializes the model for the object detection task using known class annotations. We show that a simple language model fits better than a large contextualized language model for detecting novel objects. Moreover, we introduce a consistency-regularization technique to better exploit image-caption pair information. Our method compares favorably to existing open-vocabulary detection approaches while being data-efficient. Source code is available at https://github.com/lmb-freiburg/locov .
Accurate and reliable 3D detection is vital for many applications including autonomous driving vehicles and service robots. In this paper, we present a flexible and high-performance 3D detection framework, named MPPNet, for 3D temporal object detection with point cloud sequences. We propose a novel three-hierarchy framework with proxy points for multi-frame feature encoding and interactions to achieve better detection. The three hierarchies conduct per-frame feature encoding, short-clip feature fusion, and whole-sequence feature aggregation, respectively. To enable processing long-sequence point clouds with reasonable computational resources, intra-group feature mixing and inter-group feature attention are proposed to form the second and third feature encoding hierarchies, which are recurrently applied for aggregating multi-frame trajectory features. The proxy points not only act as consistent object representations for each frame, but also serve as the courier to facilitate feature interaction between frames. The experiments on large Waymo Open dataset show that our approach outperforms state-of-the-art methods with large margins when applied to both short (e.g., 4-frame) and long (e.g., 16-frame) point cloud sequences. Code is available at https://github.com/open-mmlab/OpenPCDet.
Small-object detection is a challenging problem. In the last few years, the convolution neural networks methods have been achieved considerable progress. However, the current detectors struggle with effective features extraction for small-scale objects. To address this challenge, we propose image pyramid single-shot detector (IPSSD). In IPSSD, single-shot detector is adopted combined with an image pyramid network to extract semantically strong features for generating candidate regions. The proposed network can enhance the small-scale features from a feature pyramid network. We evaluated the performance of the proposed model on two public datasets and the results show the superior performance of our model compared to the other state-of-the-art object detectors.
We study the problem of weakly semi-supervised object detection with points (WSSOD-P), where the training data is combined by a small set of fully annotated images with bounding boxes and a large set of weakly-labeled images with only a single point annotated for each instance. The core of this task is to train a point-to-box regressor on well-labeled images that can be used to predict credible bounding boxes for each point annotation. We challenge the prior belief that existing CNN-based detectors are not compatible with this task. Based on the classic R-CNN architecture, we propose an effective point-to-box regressor: Group R-CNN. Group R-CNN first uses instance-level proposal grouping to generate a group of proposals for each point annotation and thus can obtain a high recall rate. To better distinguish different instances and improve precision, we propose instance-level proposal assignment to replace the vanilla assignment strategy adopted in the original R-CNN methods. As naive instance-level assignment brings converging difficulty, we propose instance-aware representation learning which consists of instance-aware feature enhancement and instance-aware parameter generation to overcome this issue. Comprehensive experiments on the MS-COCO benchmark demonstrate the effectiveness of our method. Specifically, Group R-CNN significantly outperforms the prior method Point DETR by 3.9 mAP with 5% well-labeled images, which is the most challenging scenario. The source code can be found at https://github.com/jshilong/GroupRCNN
While multi-class 3D detectors are needed in many robotics applications, training them with fully labeled datasets can be expensive in labeling cost. An alternative approach is to have targeted single-class labels on disjoint data samples. In this paper, we are interested in training a multi-class 3D object detection model, while using these single-class labeled data. We begin by detailing the unique stance of our "Single-Class Supervision" (SCS) setting with respect to related concepts such as partial supervision and semi supervision. Then, based on the case study of training the multi-class version of Range Sparse Net (RSN), we adapt a spectrum of algorithms -- from supervised learning to pseudo-labeling -- to fully exploit the properties of our SCS setting, and perform extensive ablation studies to identify the most effective algorithm and practice. Empirical experiments on the Waymo Open Dataset show that proper training under SCS can approach or match full supervision training while saving labeling costs.
Deep Learning (DL) has become prevalent in today's image processing research due to its power and versatility. It has dominated the Single Image Super-Resolution (SISR) field with its ability to obtain High-Resolution (HR) images from their Low-Resolution (LR) counterparts, particularly using Generative Adversarial Networks (GANs). Interest in SISR comes from its potential to increase the performance of supplementary image processing tasks such as object detection, localization, and classification. This research applies a multi-agent Reinforcement Learning (RL) algorithm to SISR, creating an advanced ensemble approach for combining powerful GANs. In our implementation each agent chooses a particular action from a fixed action set comprised of results from existing GAN SISR algorithms to update its pixel values. The pixel-wise or patch-wise arrangement of agents and rewards encourages the algorithm to learn a strategy to increase the resolution of an image by choosing the best pixel values from each option.
Self-supervised learning (SSL) methods such as masked language modeling have shown massive performance gains by pretraining transformer models for a variety of natural language processing tasks. The follow-up research adapted similar methods like masked image modeling in vision transformer and demonstrated improvements in the image classification task. Such simple self-supervised methods are not exhaustively studied for object detection transformers (DETR, Deformable DETR) as their transformer encoder modules take input in the convolutional neural network (CNN) extracted feature space rather than the image space as in general vision transformers. However, the CNN feature maps still maintain the spatial relationship and we utilize this property to design self-supervised learning approaches to train the encoder of object detection transformers in pretraining and multi-task learning settings. We explore common self-supervised methods based on image reconstruction, masked image modeling and jigsaw. Preliminary experiments in the iSAID dataset demonstrate faster convergence of DETR in the initial epochs in both pretraining and multi-task learning settings; nonetheless, similar improvement is not observed in the case of multi-task learning with Deformable DETR. The code for our experiments with DETR and Deformable DETR are available at https://github.com/gokulkarthik/detr and https://github.com/gokulkarthik/Deformable-DETR respectively.
The success of fully supervised saliency detection models depends on a large number of pixel-wise labeling. In this paper, we work on bounding-box based weakly-supervised saliency detection to relieve the labeling effort. Given the bounding box annotation, we observe that pixels inside the bounding box may contain extensive labeling noise. However, as a large amount of background is excluded, the foreground bounding box region contains a less complex background, making it possible to perform handcrafted features-based saliency detection with only the cropped foreground region. As the conventional handcrafted features are not representative enough, leading to noisy saliency maps, we further introduce structure-aware self-supervised loss to regularize the structure of the prediction. Further, we claim that pixels outside the bounding box should be background, thus partial cross-entropy loss function can be used to accurately localize the accurate background region. Experimental results on six benchmark RGB saliency datasets illustrate the effectiveness of our model.
With the popularity of Internet of Things (IoT), edge computing and cloud computing, more and more stream analytics applications are being developed including real-time trend prediction and object detection on top of IoT sensing data. One popular type of stream analytics is the recurrent neural network (RNN) deep learning model based time series or sequence data prediction and forecasting. Different from traditional analytics that assumes data are available ahead of time and will not change, stream analytics deals with data that are being generated continuously and data trend/distribution could change (a.k.a. concept drift), which will cause prediction/forecasting accuracy to drop over time. One other challenge is to find the best resource provisioning for stream analytics to achieve good overall latency. In this paper, we study how to best leverage edge and cloud resources to achieve better accuracy and latency for stream analytics using a type of RNN model called long short-term memory (LSTM). We propose a novel edge-cloud integrated framework for hybrid stream analytics that supports low latency inference on the edge and high capacity training on the cloud. To achieve flexible deployment, we study different approaches of deploying our hybrid learning framework including edge-centric, cloud-centric and edge-cloud integrated. Further, our hybrid learning framework can dynamically combine inference results from an LSTM model pre-trained based on historical data and another LSTM model re-trained periodically based on the most recent data. Using real-world and simulated stream datasets, our experiments show the proposed edge-cloud deployment is the best among all three deployment types in terms of latency. For accuracy, the experiments show our dynamic learning approach performs the best among all learning approaches for all three concept drift scenarios.
Object detection is a well-known problem in computer vision. Despite this, its usage and pervasiveness in the traditional Indian food dishes has been limited. Particularly, recognizing Indian food dishes present in a single photo is challenging due to three reasons: 1. Lack of annotated Indian food datasets 2. Non-distinct boundaries between the dishes 3. High intra-class variation. We solve these issues by providing a comprehensively labelled Indian food dataset- IndianFood10, which contains 10 food classes that appear frequently in a staple Indian meal and using transfer learning with YOLOv4 object detector model. Our model is able to achieve an overall mAP score of 91.8% and f1-score of 0.90 for our 10 class dataset. We also provide an extension of our 10 class dataset- IndianFood20, which contains 10 more traditional Indian food classes.
The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded transfer performance on downstream tasks such as object detection. To bridge the performance gap, we propose a novel object-level self-supervised learning method, called Contrastive learning with Downstream background invariance (CoDo). The pretext task is converted to focus on instance location modeling for various backgrounds, especially for downstream datasets. The ability of background invariance is considered vital for object detection. Firstly, a data augmentation strategy is proposed to paste the instances onto background images, and then jitter the bounding box to involve background information. Secondly, we implement architecture alignment between our pretraining network and the mainstream detection pipelines. Thirdly, hierarchical and multi views contrastive learning is designed to improve performance of visual representation learning. Experiments on MSCOCO demonstrate that the proposed CoDo with common backbones, ResNet50-FPN, yields strong transfer learning results for object detection.
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.
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.
Automotive embedded algorithms have very high constraints in terms of latency, accuracy and power consumption. In this work, we propose to train spiking neural networks (SNNs) directly on data coming from event cameras to design fast and efficient automotive embedded applications. Indeed, SNNs are more biologically realistic neural networks where neurons communicate using discrete and asynchronous spikes, a naturally energy-efficient and hardware friendly operating mode. Event data, which are binary and sparse in space and time, are therefore the ideal input for spiking neural networks. But to date, their performance was insufficient for automotive real-world problems, such as detecting complex objects in an uncontrolled environment. To address this issue, we took advantage of the latest advancements in matter of spike backpropagation - surrogate gradient learning, parametric LIF, SpikingJelly framework - and of our new \textit{voxel cube} event encoding to train 4 different SNNs based on popular deep learning networks: SqueezeNet, VGG, MobileNet, and DenseNet. As a result, we managed to increase the size and the complexity of SNNs usually considered in the literature. In this paper, we conducted experiments on two automotive event datasets, establishing new state-of-the-art classification results for spiking neural networks. Based on these results, we combined our SNNs with SSD to propose the first spiking neural networks capable of performing object detection on the complex GEN1 Automotive Detection event dataset.
In the last decades, the area under cultivation of maize products has increased because of its essential role in the food cycle for humans, livestock, and poultry. Moreover, the diseases of plants impact food safety and can significantly reduce both the quality and quantity of agricultural products. There are many challenges to accurate and timely diagnosis of the disease. This research presents a novel scheme based on a deep neural network to overcome the mentioned challenges. Due to the limited number of data, the transfer learning technique is employed with the help of two well-known architectures. In this way, a new effective model is adopted by a combination of pre-trained MobileNetV2 and Inception Networks due to their effective performance on object detection problems. The convolution layers of MoblieNetV2 and Inception modules are parallelly arranged as earlier layers to extract crucial features. In addition, the imbalance problem of classes has been solved by an augmentation strategy. The proposed scheme has a superior performance compared to other state-of-the-art models published in recent years. The accuracy of the model reaches 97%, approximately. In summary, experimental results prove the method's validity and significant performance in diagnosing disease in plant leaves.