PyTorchKR Papers

최신 논문

총 3,796편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2205.11098공식 코드 · Papers with Code

PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection

The remarkable breakthroughs in point cloud representation learning have boosted their usage in real-world applications such as self-driving cars and virtual reality. However, these applications usually have an urgent requirement for not only accurate but also efficient 3D object detection. Recently, knowledge distillation has been proposed as an effective model compression technique, which transfers the knowledge from an over-parameterized teacher to a lightweight student and achieves consistent effectiveness in 2D vision. However, due to point clouds' sparsity and irregularity, directly applying previous image-based knowledge distillation methods to point cloud detectors usually leads to unsatisfactory performance. To fill the gap, this paper proposes PointDistiller, a structured knowledge distillation framework for point clouds-based 3D detection. Concretely, PointDistiller includes local distillation which extracts and distills the local geometric structure of point clouds with dynamic graph convolution and reweighted learning strategy, which highlights student learning on the crucial points or voxels to improve knowledge distillation efficiency. Extensive experiments on both voxels-based and raw points-based detectors have demonstrated the effectiveness of our method over seven previous knowledge distillation methods. For instance, our 4X compressed PointPillars student achieves 2.8 and 3.4 mAP improvements on BEV and 3D object detection, outperforming its teacher by 0.9 and 1.8 mAP, respectively. Codes have been released at https://github.com/RunpeiDong/PointDistiller.

arXiv:2205.10536공식 코드 · Papers with Code

Knowledge Distillation from A Stronger Teacher

Unlike existing knowledge distillation methods focus on the baseline settings, where the teacher models and training strategies are not that strong and competing as state-of-the-art approaches, this paper presents a method dubbed DIST to distill better from a stronger teacher. We empirically find that the discrepancy of predictions between the student and a stronger teacher may tend to be fairly severer. As a result, the exact match of predictions in KL divergence would disturb the training and make existing methods perform poorly. In this paper, we show that simply preserving the relations between the predictions of teacher and student would suffice, and propose a correlation-based loss to capture the intrinsic inter-class relations from the teacher explicitly. Besides, considering that different instances have different semantic similarities to each class, we also extend this relational match to the intra-class level. Our method is simple yet practical, and extensive experiments demonstrate that it adapts well to various architectures, model sizes and training strategies, and can achieve state-of-the-art performance consistently on image classification, object detection, and semantic segmentation tasks. Code is available at: https://github.com/hunto/DIST_KD .

arXiv:2205.10063공식 코드 · Papers with Code

Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality

Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-training efficiency and fine-tuning accuracy. Notably, the success of the asymmetric structure relies on the "global" property of Vanilla Vision Transformer (ViT), whose self-attention mechanism reasons over arbitrary subset of discrete image patches. However, it is still unclear how the advanced Pyramid-based ViTs (e.g., PVT, Swin) can be adopted in MAE pre-training as they commonly introduce operators within "local" windows, making it difficult to handle the random sequence of partial vision tokens. In this paper, we propose Uniform Masking (UM), successfully enabling MAE pre-training for Pyramid-based ViTs with locality (termed "UM-MAE" for short). Specifically, UM includes a Uniform Sampling (US) that strictly samples $1$ random patch from each $2 \times 2$ grid, and a Secondary Masking (SM) which randomly masks a portion of (usually $25\%$) the already sampled regions as learnable tokens. US preserves equivalent elements across multiple non-overlapped local windows, resulting in the smooth support for popular Pyramid-based ViTs; whilst SM is designed for better transferable visual representations since US reduces the difficulty of pixel recovery pre-task that hinders the semantic learning. We demonstrate that UM-MAE significantly improves the pre-training efficiency (e.g., it speeds up and reduces the GPU memory by $\sim 2\times$) of Pyramid-based ViTs, but maintains the competitive fine-tuning performance across downstream tasks. For example using HTC++ detector, the pre-trained Swin-Large backbone self-supervised under UM-MAE only in ImageNet-1K can even outperform the one supervised in ImageNet-22K. The codes are available at https://github.com/implus/UM-MAE.

arXiv:2205.09616공식 코드 · Papers with Code

Masked Image Modeling with Denoising Contrast

Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision dictionary look-up. MIM recently dominates this line of research with state-of-the-art performance on vision Transformers (ViTs), where the core is to enhance the patch-level visual context capturing of the network via denoising auto-encoding mechanism. Rather than tailoring image tokenizers with extra training stages as in previous works, we unleash the great potential of contrastive learning on denoising auto-encoding and introduce a pure MIM method, ConMIM, to produce simple intra-image inter-patch contrastive constraints as the sole learning objectives for masked patch prediction. We further strengthen the denoising mechanism with asymmetric designs, including image perturbations and model progress rates, to improve the network pre-training. ConMIM-pretrained models with various scales achieve competitive results on downstream image classification, semantic segmentation, object detection, and instance segmentation tasks, e.g., on ImageNet-1K classification, we achieve 83.9% top-1 accuracy with ViT-Small and 85.3% with ViT-Base without extra data for pre-training.

arXiv:2205.09613공식 코드 · Papers with Code

Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection

Modern object detectors have taken the advantages of backbone networks pre-trained on large scale datasets. Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders fully tapping the potential of representation models. In this study, we propose to integrally migrate pre-trained transformer encoder-decoders (imTED) to a detector, constructing a feature extraction path which is ``fully pre-trained" so that detectors' generalization capacity is maximized. The essential differences between imTED with the baseline detector are twofold: (1) migrating the pre-trained transformer decoder to the detector head while removing the randomly initialized FPN from the feature extraction path; and (2) defining a multi-scale feature modulator (MFM) to enhance scale adaptability. Such designs not only reduce randomly initialized parameters significantly but also unify detector training with representation learning intendedly. Experiments on the MS COCO object detection dataset show that imTED consistently outperforms its counterparts by $\sim$2.4 AP. Without bells and whistles, imTED improves the state-of-the-art of few-shot object detection by up to 7.6 AP. Code is available at https://github.com/LiewFeng/imTED.

arXiv:2205.09743공식 코드 · Papers with Code

BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving

In this paper, we present BEVerse, a unified framework for 3D perception and prediction based on multi-camera systems. Unlike existing studies focusing on the improvement of single-task approaches, BEVerse features in producing spatio-temporal Birds-Eye-View (BEV) representations from multi-camera videos and jointly reasoning about multiple tasks for vision-centric autonomous driving. Specifically, BEVerse first performs shared feature extraction and lifting to generate 4D BEV representations from multi-timestamp and multi-view images. After the ego-motion alignment, the spatio-temporal encoder is utilized for further feature extraction in BEV. Finally, multiple task decoders are attached for joint reasoning and prediction. Within the decoders, we propose the grid sampler to generate BEV features with different ranges and granularities for different tasks. Also, we design the method of iterative flow for memory-efficient future prediction. We show that the temporal information improves 3D object detection and semantic map construction, while the multi-task learning can implicitly benefit motion prediction. With extensive experiments on the nuScenes dataset, we show that the multi-task BEVerse outperforms existing single-task methods on 3D object detection, semantic map construction, and motion prediction. Compared with the sequential paradigm, BEVerse also favors in significantly improved efficiency. The code and trained models will be released at https://github.com/zhangyp15/BEVerse.

arXiv:2205.08959공식 코드 · Papers with Code

A lightweight multi-scale context network for salient object detection in optical remote sensing images

Due to the more dramatic multi-scale variations and more complicated foregrounds and backgrounds in optical remote sensing images (RSIs), the salient object detection (SOD) for optical RSIs becomes a huge challenge. However, different from natural scene images (NSIs), the discussion on the optical RSI SOD task still remains scarce. In this paper, we propose a multi-scale context network, namely MSCNet, for SOD in optical RSIs. Specifically, a multi-scale context extraction module is adopted to address the scale variation of salient objects by effectively learning multi-scale contextual information. Meanwhile, in order to accurately detect complete salient objects in complex backgrounds, we design an attention-based pyramid feature aggregation mechanism for gradually aggregating and refining the salient regions from the multi-scale context extraction module. Extensive experiments on two benchmarks demonstrate that MSCNet achieves competitive performance with only 3.26M parameters. The code will be available at https://github.com/NuaaYH/MSCNet.

arXiv:2205.08534공식 코드 · Papers with Code

Vision Transformer Adapter for Dense Predictions

This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductive biases into their architectures, the plain ViT suffers inferior performance on dense predictions due to weak prior assumptions. To address this issue, we propose the ViT-Adapter, which allows plain ViT to achieve comparable performance to vision-specific transformers. Specifically, the backbone in our framework is a plain ViT that can learn powerful representations from large-scale multi-modal data. When transferring to downstream tasks, a pre-training-free adapter is used to introduce the image-related inductive biases into the model, making it suitable for these tasks. We verify ViT-Adapter on multiple dense prediction tasks, including object detection, instance segmentation, and semantic segmentation. Notably, without using extra detection data, our ViT-Adapter-L yields state-of-the-art 60.9 box AP and 53.0 mask AP on COCO test-dev. We hope that the ViT-Adapter could serve as an alternative for vision-specific transformers and facilitate future research. The code and models will be released at https://github.com/czczup/ViT-Adapter.

arXiv:2205.07708공식 코드 · Papers with Code

Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Driving

3D object detection has recently received much attention due to its great potential in autonomous vehicle (AV). The success of deep learning based object detectors relies on the availability of large-scale annotated datasets, which is time-consuming and expensive to compile, especially for 3D bounding box annotation. In this work, we investigate diversity-based active learning (AL) as a potential solution to alleviate the annotation burden. Given limited annotation budget, only the most informative frames and objects are automatically selected for human to annotate. Technically, we take the advantage of the multimodal information provided in an AV dataset, and propose a novel acquisition function that enforces spatial and temporal diversity in the selected samples. We benchmark the proposed method against other AL strategies under realistic annotation cost measurement, where the realistic costs for annotating a frame and a 3D bounding box are both taken into consideration. We demonstrate the effectiveness of the proposed method on the nuScenes dataset and show that it outperforms existing AL strategies significantly. Code is available at https://github.com/Linkon87/Exploring-Diversity-based-Active-Learning-for-3D-Object-Detection-in-Autonomous-Driving

arXiv:2205.07403공식 코드 · Papers with Code

PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

Real-time and high-performance 3D object detection is of critical importance for autonomous driving. Recent top-performing 3D object detectors mainly rely on point-based or 3D voxel-based convolutions, which are both computationally inefficient for onboard deployment. In contrast, pillar-based methods use solely 2D convolutions, which consume less computation resources, but they lag far behind their voxel-based counterparts in detection accuracy. In this paper, by examining the primary performance gap between pillar- and voxel-based detectors, we develop a real-time and high-performance pillar-based detector, dubbed PillarNet.The proposed PillarNet consists of a powerful encoder network for effective pillar feature learning, a neck network for spatial-semantic feature fusion and the commonly used detect head. Using only 2D convolutions, PillarNet is flexible to an optional pillar size and compatible with classical 2D CNN backbones, such as VGGNet and ResNet. Additionally, PillarNet benefits from our designed orientation-decoupled IoU regression loss along with the IoU-aware prediction branch. Extensive experimental results on the large-scale nuScenes Dataset and Waymo Open Dataset demonstrate that the proposed PillarNet performs well over state-of-the-art 3D detectors in terms of effectiveness and efficiency. Code is available at \url{https://github.com/agent-sgs/PillarNet}.

arXiv:2205.07179공식 코드 · Papers with Code

Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection

Growing interests in RGB-D salient object detection (RGB-D SOD) have been witnessed in recent years, owing partly to the popularity of depth sensors and the rapid progress of deep learning techniques. Unfortunately, existing RGB-D SOD methods typically demand large quantity of training images being thoroughly annotated at pixel-level. The laborious and time-consuming manual annotation has become a real bottleneck in various practical scenarios. On the other hand, current unsupervised RGB-D SOD methods still heavily rely on handcrafted feature representations. This inspires us to propose in this paper a deep unsupervised RGB-D saliency detection approach, which requires no manual pixel-level annotation during training. It is realized by two key ingredients in our training pipeline. First, a depth-disentangled saliency update (DSU) framework is designed to automatically produce pseudo-labels with iterative follow-up refinements, which provides more trustworthy supervision signals for training the saliency network. Second, an attentive training strategy is introduced to tackle the issue of noisy pseudo-labels, by properly re-weighting to highlight the more reliable pseudo-labels. Extensive experiments demonstrate the superior efficiency and effectiveness of our approach in tackling the challenging unsupervised RGB-D SOD scenarios. Moreover, our approach can also be adapted to work in fully-supervised situation. Empirical studies show the incorporation of our approach gives rise to notably performance improvement in existing supervised RGB-D SOD models.

arXiv:2205.07473공식 코드 · Papers with Code

Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimization

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.

arXiv:2205.06934공식 코드 · Papers with Code

A Saliency-Guided Street View Image Inpainting Framework for Efficient Last-Meters Wayfinding

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.

arXiv:2205.06230공식 코드 · Papers with Code

Simple Open-Vocabulary Object Detection with Vision Transformers

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.

arXiv:2205.06160공식 코드 · Papers with Code

Localized Vision-Language Matching for Open-vocabulary Object Detection

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 .

arXiv:2205.05979공식 코드 · Papers with Code

MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection

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.

arXiv:2205.05920공식 코드 · Papers with Code

Group R-CNN for Weakly Semi-supervised Object Detection with Points

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

arXiv:2205.05543공식 코드 · Papers with Code

An Empirical Study Of Self-supervised Learning Approaches For Object Detection With Transformers

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.

arXiv:2205.03688공식 코드 · Papers with Code

GenISP: Neural ISP for Low-Light Machine Cognition

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.

arXiv:2205.04339공식 코드 · Papers with Code

Object Detection with Spiking Neural Networks on Automotive Event Data

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.