Nowadays, deep neural networks for object detection in images are very prevalent. However, due to the complexity of these networks, users find it hard to understand why these objects are detected by models. We proposed Gaussian Class Activation Mapping Explainer (G-CAME), which generates a saliency map as the explanation for object detection models. G-CAME can be considered a CAM-based method that uses the activation maps of selected layers combined with the Gaussian kernel to highlight the important regions in the image for the predicted box. Compared with other Region-based methods, G-CAME can transcend time constraints as it takes a very short time to explain an object. We also evaluated our method qualitatively and quantitatively with YOLOX on the MS-COCO 2017 dataset and guided to apply G-CAME into the two-stage Faster-RCNN model.
Occluded and long-range objects are ubiquitous and challenging for 3D object detection. Point cloud sequence data provide unique opportunities to improve such cases, as an occluded or distant object can be observed from different viewpoints or gets better visibility over time. However, the efficiency and effectiveness in encoding long-term sequence data can still be improved. In this work, we propose MoDAR, using motion forecasting outputs as a type of virtual modality, to augment LiDAR point clouds. The MoDAR modality propagates object information from temporal contexts to a target frame, represented as a set of virtual points, one for each object from a waypoint on a forecasted trajectory. A fused point cloud of both raw sensor points and the virtual points can then be fed to any off-the-shelf point-cloud based 3D object detector. Evaluated on the Waymo Open Dataset, our method significantly improves prior art detectors by using motion forecasting from extra-long sequences (e.g. 18 seconds), achieving new state of the arts, while not adding much computation overhead.
Massive human-related data is collected to train neural networks for computer vision tasks. A major conflict is exposed relating to software engineers between better developing AI systems and distancing from the sensitive training data. To reconcile this conflict, this paper proposes an efficient privacy-preserving learning paradigm, where images are first encrypted to become ``human-imperceptible, machine-recognizable'' via one of the two encryption strategies: (1) random shuffling to a set of equally-sized patches and (2) mixing-up sub-patches of the images. Then, minimal adaptations are made to vision transformer to enable it to learn on the encrypted images for vision tasks, including image classification and object detection. Extensive experiments on ImageNet and COCO show that the proposed paradigm achieves comparable accuracy with the competitive methods. Decrypting the encrypted images requires solving an NP-hard jigsaw puzzle or an ill-posed inverse problem, which is empirically shown intractable to be recovered by various attackers, including the powerful vision transformer-based attacker. We thus show that the proposed paradigm can ensure the encrypted images have become human-imperceptible while preserving machine-recognizable information. The code is available at \url{https://github.com/FushengHao/PrivacyPreservingML.}
In recent years, with the successful application of DNN in fields such as NLP and CV, its security has also received widespread attention. (Author) proposed the method of backdoor attack in Badnet. Switch implanted backdoor into the model by poisoning the training samples. The model with backdoor did not exhibit any abnormalities on the normal validation sample set, but in the input with trigger, they were mistakenly classified as the attacker's designated category or randomly classified as a different category from the ground truth, This attack method seriously threatens the normal application of DNN in real life, such as autonomous driving, object detection, etc.This article proposes a new method to combat backdoor attacks. We refer to the features in the area covered by the trigger as trigger features, and the remaining areas as normal features. By introducing prerequisite calculation conditions during the training process, these conditions have little impact on normal features and trigger features, and can complete the training of a standard backdoor model. The model trained under these prerequisite calculation conditions can, In the verification set D'val with the same premise calculation conditions, the performance is consistent with that of the ordinary backdoor model. However, in the verification set Dval without the premise calculation conditions, the verification accuracy decreases very little (7%~12%), while the attack success rate (ASR) decreases from 90% to about 8%.Author call this method Prerequisite Transformation(PT).
This paper introduces a new challenge for image similarity search in the context of fashion, addressing the inherent ambiguity in this domain stemming from complex images. We present Referred Visual Search (RVS), a task allowing users to define more precisely the desired similarity, following recent interest in the industry. We release a new large public dataset, LRVS-Fashion, consisting of 272k fashion products with 842k images extracted from fashion catalogs, designed explicitly for this task. However, unlike traditional visual search methods in the industry, we demonstrate that superior performance can be achieved by bypassing explicit object detection and adopting weakly-supervised conditional contrastive learning on image tuples. Our method is lightweight and demonstrates robustness, reaching Recall at one superior to strong detection-based baselines against 2M distractors. The dataset is available at https://huggingface.co/datasets/Slep/LAION-RVS-Fashion .
Asymmetric appearance between positive pair effectively reduces the risk of representation degradation in contrastive learning. However, there are still a mass of appearance similarities between positive pair constructed by the existing methods, which inhibits the further representation improvement. In this paper, we propose a novel asymmetric patch sampling strategy for contrastive learning, to further boost the appearance asymmetry for better representations. Specifically, dual patch sampling strategies are applied to the given image, to obtain asymmetric positive pairs. First, sparse patch sampling is conducted to obtain the first view, which reduces spatial redundancy of image and allows a more asymmetric view. Second, a selective patch sampling is proposed to construct another view with large appearance discrepancy relative to the first one. Due to the inappreciable appearance similarity between positive pair, the trained model is encouraged to capture the similarity on semantics, instead of low-level ones. Experimental results demonstrate that our proposed method significantly outperforms the existing self-supervised methods on both ImageNet-1K and CIFAR dataset, e.g., 2.5% finetune accuracy improvement on CIFAR100. Furthermore, our method achieves state-of-the-art performance on downstream tasks, object detection and instance segmentation on COCO.Additionally, compared to other self-supervised methods, our method is more efficient on both memory and computation during training. The source code is available at https://github.com/visresearch/aps.
A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud pre-training that learns 3D representations by leveraging pre-trained 2D networks. Different from the popular practice of predicting 2D features first and then obtaining 3D features through dimensionality lifting, our approach directly uses a 3D network for feature extraction. We train the 3D feature extraction network with the help of the novel 2D knowledge transfer loss, which enforces the 2D projections of the 3D feature to be consistent with the output of pre-trained 2D networks. To prevent the feature from discarding 3D signals, we introduce the multi-view consistency loss that additionally encourages the projected 2D feature representations to capture pixel-wise correspondences across different views. Such correspondences induce 3D geometry and effectively retain 3D features in the projected 2D features. Experimental results demonstrate that our pre-trained model can be successfully transferred to various downstream tasks, including 3D shape classification, part segmentation, 3D object detection, and semantic segmentation, achieving state-of-the-art performance.
Saliency methods are frequently used to explain Deep Neural Network-based models. Adebayo et al.'s work on evaluating saliency methods for classification models illustrate certain explanation methods fail the model and data randomization tests. However, on extending the tests for various state of the art object detectors we illustrate that the ability to explain a model is more dependent on the model itself than the explanation method. We perform sanity checks for object detection and define new qualitative criteria to evaluate the saliency explanations, both for object classification and bounding box decisions, using Guided Backpropagation, Integrated Gradients, and their Smoothgrad versions, together with Faster R-CNN, SSD, and EfficientDet-D0, trained on COCO. In addition, the sensitivity of the explanation method to model parameters and data labels varies class-wise motivating to perform the sanity checks for each class. We find that EfficientDet-D0 is the most interpretable method independent of the saliency method, which passes the sanity checks with little problems.
We present the RSSOD-Bench dataset for salient object detection (SOD) in optical remote sensing imagery. While SOD has achieved success in natural scene images with deep learning, research in SOD for remote sensing imagery (RSSOD) is still in its early stages. Existing RSSOD datasets have limitations in terms of scale, and scene categories, which make them misaligned with real-world applications. To address these shortcomings, we construct the RSSOD-Bench dataset, which contains images from four different cities in the USA. The dataset provides annotations for various salient object categories, such as buildings, lakes, rivers, highways, bridges, aircraft, ships, athletic fields, and more. The salient objects in RSSOD-Bench exhibit large-scale variations, cluttered backgrounds, and different seasons. Unlike existing datasets, RSSOD-Bench offers uniform distribution across scene categories. We benchmark 23 different state-of-the-art approaches from both the computer vision and remote sensing communities. Experimental results demonstrate that more research efforts are required for the RSSOD task.
Open World Object Detection (OWOD) is a novel and challenging computer vision task that enables object detection with the ability to detect unknown objects. Existing methods typically estimate the object likelihood with an additional objectness branch, but ignore the conflict in learning objectness and classification boundaries, which oppose each other on the semantic manifold and training objective. To address this issue, we propose a simple yet effective learning strategy, namely Decoupled Objectness Learning (DOL), which divides the learning of these two boundaries into suitable decoder layers. Moreover, detecting unknown objects comprehensively requires a large amount of annotations, but labeling all unknown objects is both difficult and expensive. Therefore, we propose to take advantage of the recent Large Vision Model (LVM), specifically the Segment Anything Model (SAM), to enhance the detection of unknown objects. Nevertheless, the output results of SAM contain noise, including backgrounds and fragments, so we introduce an Auxiliary Supervision Framework (ASF) that uses a pseudo-labeling and a soft-weighting strategies to alleviate the negative impact of noise. Extensive experiments on popular benchmarks, including Pascal VOC and MS COCO, demonstrate the effectiveness of our approach. Our proposed Unknown Sensitive Detector (USD) outperforms the recent state-of-the-art methods in terms of Unknown Recall, achieving significant improvements of 14.3\%, 15.5\%, and 8.9\% on the M-OWODB, and 27.1\%, 29.1\%, and 25.1\% on the S-OWODB.
With the development of large language models, many remarkable linguistic systems like ChatGPT have thrived and achieved astonishing success on many tasks, showing the incredible power of foundation models. In the spirit of unleashing the capability of foundation models on vision tasks, the Segment Anything Model (SAM), a vision foundation model for image segmentation, has been proposed recently and presents strong zero-shot ability on many downstream 2D tasks. However, whether SAM can be adapted to 3D vision tasks has yet to be explored, especially 3D object detection. With this inspiration, we explore adapting the zero-shot ability of SAM to 3D object detection in this paper. We propose a SAM-powered BEV processing pipeline to detect objects and get promising results on the large-scale Waymo open dataset. As an early attempt, our method takes a step toward 3D object detection with vision foundation models and presents the opportunity to unleash their power on 3D vision tasks. The code is released at https://github.com/DYZhang09/SAM3D.
Detecting safety clothing and helmets is paramount for ensuring the safety of construction workers. However, the development of deep learning models in this domain has been impeded by the scarcity of high-quality datasets. In this study, we construct a large, complex, and realistic safety clothing and helmet detection (SFCHD) dataset. SFCHD is derived from two authentic chemical plants, comprising 12,373 images, 7 categories, and 50,552 annotations. We partition the SFCHD dataset into training and testing sets with a ratio of 4:1 and validate its utility by applying several classic object detection algorithms. Furthermore, drawing inspiration from spatial and channel attention mechanisms, we design a spatial and channel attention-based low-light enhancement (SCALE) module. SCALE is a plug-and-play component with a high degree of flexibility. Extensive evaluations of the SCALE module on both the ExDark and SFCHD datasets have empirically demonstrated its efficacy in enhancing the performance of detectors under low-light conditions. The dataset and code are publicly available at https://github.com/lijfrank-open/SFCHD-SCALE.
Semi-supervised object detection (SSOD) has made significant progress with the development of pseudo-label-based end-to-end methods. However, many of these methods face challenges due to class imbalance, which hinders the effectiveness of the pseudo-label generator. Furthermore, in the literature, it has been observed that low-quality pseudo-labels severely limit the performance of SSOD. In this paper, we examine the root causes of low-quality pseudo-labels and present novel learning mechanisms to improve the label generation quality. To cope with high false-negative and low precision rates, we introduce an adaptive thresholding mechanism that helps the proposed network to filter out optimal bounding boxes. We further introduce a Jitter-Bagging module to provide accurate information on localization to help refine the bounding boxes. Additionally, two new losses are introduced using the background and foreground scores predicted by the teacher and student networks to improvise the pseudo-label recall rate. Furthermore, our method applies strict supervision to the teacher network by feeding strong & weak augmented data to generate robust pseudo-labels so that it can detect small and complex objects. Finally, the extensive experiments show that the proposed network outperforms state-of-the-art methods on MS-COCO and Pascal VOC datasets and allows the baseline network to achieve 100% supervised performance with much less (i.e., 20%) labeled data.
Diffusion models have demonstrated impressive performance in text-to-image generation. They utilize a text encoder and cross-attention blocks to infuse textual information into images at a pixel level. However, their capability to generate images with text containing multiple objects is still restricted. Previous works identify the problem of information mixing in the CLIP text encoder and introduce the T5 text encoder or incorporate strong prior knowledge to assist with the alignment. We find that mixing problems also occur on the image side and in the cross-attention blocks. The noisy images can cause different objects to appear similar, and the cross-attention blocks inject information at a pixel level, leading to leakage of global object understanding and resulting in object mixing. In this paper, we introduce Detector Guidance (DG), which integrates a latent object detection model to separate different objects during the generation process. DG first performs latent object detection on cross-attention maps (CAMs) to obtain object information. Based on this information, DG then masks conflicting prompts and enhances related prompts by manipulating the following CAMs. We evaluate the effectiveness of DG using Stable Diffusion on COCO, CC, and a novel multi-related object benchmark, MRO. Human evaluations demonstrate that DG provides an 8-22\% advantage in preventing the amalgamation of conflicting concepts and ensuring that each object possesses its unique region without any human involvement and additional iterations. Our implementation is available at \url{https://github.com/luping-liu/Detector-Guidance}.
Recent advances in Artificial Intelligence (AI) technology have promoted their use in almost every field. The growing complexity of deep neural networks (DNNs) makes it increasingly difficult and important to explain the inner workings and decisions of the network. However, most current techniques for explaining DNNs focus mainly on interpreting classification tasks. This paper proposes a method to explain the decision for any object detection model called D-CLOSE. To closely track the model's behavior, we used multiple levels of segmentation on the image and a process to combine them. We performed tests on the MS-COCO dataset with the YOLOX model, which shows that our method outperforms D-RISE and can give a better quality and less noise explanation.
Multi-view 3D object detection is becoming popular in autonomous driving due to its high effectiveness and low cost. Most of the current state-of-the-art detectors follow the query-based bird's-eye-view (BEV) paradigm, which benefits from both BEV's strong perception power and end-to-end pipeline. Despite achieving substantial progress, existing works model objects via globally leveraging temporal and spatial information of BEV features, resulting in problems when handling the challenging complex and dynamic autonomous driving scenarios. In this paper, we proposed an Object-Centric query-BEV detector OCBEV, which can carve the temporal and spatial cues of moving targets more effectively. OCBEV comprises three designs: Object Aligned Temporal Fusion aligns the BEV feature based on ego-motion and estimated current locations of moving objects, leading to a precise instance-level feature fusion. Object Focused Multi-View Sampling samples more 3D features from an adaptive local height ranges of objects for each scene to enrich foreground information. Object Informed Query Enhancement replaces part of pre-defined decoder queries in common DETR-style decoders with positional features of objects on high-confidence locations, introducing more direct object positional priors. Extensive experimental evaluations are conducted on the challenging nuScenes dataset. Our approach achieves a state-of-the-art result, surpassing the traditional BEVFormer by 1.5 NDS points. Moreover, we have a faster convergence speed and only need half of the training iterations to get comparable performance, which further demonstrates its effectiveness.
LiDAR and Radar are two complementary sensing approaches in that LiDAR specializes in capturing an object's 3D shape while Radar provides longer detection ranges as well as velocity hints. Though seemingly natural, how to efficiently combine them for improved feature representation is still unclear. The main challenge arises from that Radar data are extremely sparse and lack height information. Therefore, directly integrating Radar features into LiDAR-centric detection networks is not optimal. In this work, we introduce a bi-directional LiDAR-Radar fusion framework, termed Bi-LRFusion, to tackle the challenges and improve 3D detection for dynamic objects. Technically, Bi-LRFusion involves two steps: first, it enriches Radar's local features by learning important details from the LiDAR branch to alleviate the problems caused by the absence of height information and extreme sparsity; second, it combines LiDAR features with the enhanced Radar features in a unified bird's-eye-view representation. We conduct extensive experiments on nuScenes and ORR datasets, and show that our Bi-LRFusion achieves state-of-the-art performance for detecting dynamic objects. Notably, Radar data in these two datasets have different formats, which demonstrates the generalizability of our method. Codes are available at https://github.com/JessieW0806/BiLRFusion.
The performance of deep learning models is critically dependent on sophisticated optimization strategies. While existing optimizers have shown promising results, many rely on first-order Exponential Moving Average (EMA) techniques, which often limit their ability to track complex gradient trends accurately. This fact can lead to a significant lag in trend identification and suboptimal optimization, particularly in highly dynamic gradient behavior. To address this fundamental limitation, we introduce Fast Adaptive Moment Estimation (FAME), a novel optimization technique that leverages the power of Triple Exponential Moving Average. By incorporating an advanced tracking mechanism, FAME enhances responsiveness to data dynamics, mitigates trend identification lag, and optimizes learning efficiency. Our comprehensive evaluation encompasses different computer vision tasks including image classification, object detection, and semantic segmentation, integrating FAME into 30 distinct architectures ranging from lightweight CNNs to Vision Transformers. Through rigorous benchmarking against state-of-the-art optimizers, FAME demonstrates superior accuracy and robustness. Notably, it offers high scalability, delivering substantial improvements across diverse model complexities, architectures, tasks, and benchmarks.
Due to the over-parameterization of neural networks, many model compression methods based on pruning and quantization have emerged. They are remarkable in reducing the size, parameter number, and computational complexity of the model. However, most of the models compressed by such methods need the support of special hardware and software, which increases the deployment cost. Moreover, these methods are mainly used in classification tasks, and rarely directly used in detection tasks. To address these issues, for the object detection network we introduce a three-stage model compression method: dynamic sparse training, group channel pruning, and spatial attention distilling. Firstly, to select out the unimportant channels in the network and maintain a good balance between sparsity and accuracy, we put forward a dynamic sparse training method, which introduces a variable sparse rate, and the sparse rate will change with the training process of the network. Secondly, to reduce the effect of pruning on network accuracy, we propose a novel pruning method called group channel pruning. In particular, we divide the network into multiple groups according to the scales of the feature layer and the similarity of module structure in the network, and then we use different pruning thresholds to prune the channels in each group. Finally, to recover the accuracy of the pruned network, we use an improved knowledge distillation method for the pruned network. Especially, we extract spatial attention information from the feature maps of specific scales in each group as knowledge for distillation. In the experiments, we use YOLOv4 as the object detection network and PASCAL VOC as the training dataset. Our method reduces the parameters of the model by 64.7 % and the calculation by 34.9%.
This paper introduces a highly flexible, quantized, memory-efficient, and ultra-lightweight object detection network, called TinyissimoYOLO. It aims to enable object detection on microcontrollers in the power domain of milliwatts, with less than 0.5MB memory available for storing convolutional neural network (CNN) weights. The proposed quantized network architecture with 422k parameters, enables real-time object detection on embedded microcontrollers, and it has been evaluated to exploit CNN accelerators. In particular, the proposed network has been deployed on the MAX78000 microcontroller achieving high frame-rate of up to 180fps and an ultra-low energy consumption of only 196{\mu}J per inference with an inference efficiency of more than 106 MAC/Cycle. TinyissimoYOLO can be trained for any multi-object detection. However, considering the small network size, adding object detection classes will increase the size and memory consumption of the network, thus object detection with up to 3 classes is demonstrated. Furthermore, the network is trained using quantization-aware training and deployed with 8-bit quantization on different microcontrollers, such as STM32H7A3, STM32L4R9, Apollo4b and on the MAX78000's CNN accelerator. Performance evaluations are presented in this paper.