论文检索

Zhihao Yuan, Xu Yan, Yinghong Liao, Ruimao Zhang, Sheng Wang, Zhen Li, Shuguang Cui

Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging. In this paper, we propose a new model, named InstanceRefer, to achieve a superior 3D visual grounding through the grounding-by-matching strategy. In practice, our model first predicts the target category from the language descriptions using a simple language classification model. Then based on the category, our model sifts out a small number of instance candidates (usually less than 20) from the panoptic segmentation on point clouds. Thus, the non-trivial 3D visual grounding task has been effectively re-formulated as a simplified instance-matching problem, considering that instance-level candidates are more rational than the redundant 3D object proposals. Subsequently, for each candidate, we perform the multi-level contextual inference, i.e., referring from instance attribute perception, instance-to-instance relation perception, and instance-to-background global localization perception, respectively. Eventually, the most relevant candidate is selected and localized by ranking confidence scores, which are obtained by the cooperative holistic visual-language feature matching. Experiments confirm that our method outperforms previous state-of-the-arts on ScanRefer online benchmark (ranked 1st place) and Nr3D/Sr3D datasets.

Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Luc Van Gool

Being able to learn dense semantic representations of images without supervision is an important problem in computer vision. However, despite its significance, this problem remains rather unexplored, with a few exceptions that considered unsupervised semantic segmentation on small-scale datasets with a narrow visual domain. In this paper, we make a first attempt to tackle the problem on datasets that have been traditionally utilized for the supervised case. To achieve this, we introduce a two-step framework that adopts a predetermined mid-level prior in a contrastive optimization objective to learn pixel embeddings. This marks a large deviation from existing works that relied on proxy tasks or end-to-end clustering. Additionally, we argue about the importance of having a prior that contains information about objects, or their parts, and discuss several possibilities to obtain such a prior in an unsupervised manner. Experimental evaluation shows that our method comes with key advantages over existing works. First, the learned pixel embeddings can be directly clustered in semantic groups using K-Means on PASCAL. Under the fully unsupervised setting, there is no precedent in solving the semantic segmentation task on such a challenging benchmark. Second, our representations can improve over strong baselines when transferred to new datasets, e.g. COCO and DAVIS. The code is available.

Xu Yang, Chongyang Gao, Hanwang Zhang, Jianfei Cai

We propose an Auto-Parsing Network (APN) to discover and exploit the input data's hidden tree structures for improving the effectiveness of the Transformer-based vision-language systems. Specifically, we impose a Probabilistic Graphical Model (PGM) parameterized by the attention operations on each self-attention layer to incorporate sparse assumption. We use this PGM to softly segment an input sequence into a few clusters where each cluster can be treated as the parent of the inside entities. By stacking these PGM constrained self-attention layers, the clusters in a lower layer compose into a new sequence, and the PGM in a higher layer will further segment this sequence. Iteratively, a sparse tree can be implicitly parsed, and this tree's hierarchical knowledge is incorporated into the transformed embeddings, which can be used for solving the target vision-language tasks. Specifically, we showcase that our APN can strengthen Transformer based networks in two major vision-language tasks: Captioning and Visual Question Answering. Also, a PGM probability-based parsing algorithm is developed by which we can discover what the hidden structure of input is during the inference.

Markus Schön, Michael Buchholz, Klaus Dietmayer

We introduce MGNet, a multi-task framework for monocular geometric scene understanding. We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised monocular depth estimation. Panoptic segmentation captures the full scene not only semantically, but also on an instance basis. Self-supervised monocular depth estimation uses geometric constraints derived from the camera measurement model in order to measure depth from monocular video sequences only. To the best of our knowledge, we are the first to propose the combination of these two tasks in one single model. Our model is designed with focus on low latency to provide fast inference in real-time on a single consumer-grade GPU. During deployment, our model produces dense 3D point clouds with instance aware semantic labels from single high-resolution camera images. We evaluate our model on two popular autonomous driving benchmarks, i.e., Cityscapes and KITTI, and show competitive performance among other real-time capable methods. Source code is available at https://github.com/markusschoen/MGNet.

Neel Dey, Mengwei Ren, Adrian V. Dalca, Guido Gerig

Deformable templates are essential to large-scale medical image registration, segmentation, and population analysis. Current conventional and deep network-based methods for template construction use only regularized registration objectives and often yield templates with blurry and/or anatomically implausible appearance, confounding downstream biomedical interpretation. We reformulate deformable registration and conditional template estimation as an adversarial game wherein we encourage realism in the moved templates with a generative adversarial registration framework conditioned on flexible image covariates. The resulting templates exhibit significant gain in specificity to attributes such as age and disease, better fit underlying group-wise spatiotemporal trends, and achieve improved sharpness and centrality. These improvements enable more accurate population modeling with diverse covariates for standardized downstream analyses and easier anatomical delineation for structures of interest.

Chi-Wei Hsiao, Cheng Sun, Hwann-Tzong Chen, Min Sun

We present a novel pyramidal output representation to ensure parsimony with our "specialize and fuse" process for semantic segmentation. A pyramidal "output" representation consists of coarse-to-fine levels, where each level is "specialize" in a different class distribution (e.g., more stuff than things classes at coarser levels). Two types of pyramidal outputs (i.e., unity and semantic pyramid) are "fused" into the final semantic output, where the unity pyramid indicates unity-cells (i.e., all pixels in such cell share the same semantic label). The process ensures parsimony by predicting a relatively small number of labels for unity-cells (e.g., a large cell of grass) to build the final semantic output. In addition to the "output" representation, we design a coarse-to-fine contextual module to aggregate the "features" representation from different levels. We validate the effectiveness of each key module in our method through comprehensive ablation studies. Finally, our approach achieves state-of-the-art performance on three widely-used semantic segmentation datasets---ADE20K, COCO-Stuff, and Pascal-Context.

Chenbin Pan, Senem Velipasalar

Capsule Networks (CapsNets) create internal representations by parsing inputs into various instances at different resolution levels via a two-phase process -- part-whole transformation and hierarchical component routing. Since both of these internal phases are computationally expensive, CapsNets have not found wider use. Existing variations of CapsNets mainly focus on performance comparison with the original CapsNet, and have not outperformed CNN-based models on complex tasks. To address the limitations of the existing CapsNet structures, we propose a novel Prediction-Tuning Capsule Network (PT-CapsNet), and also introduce fully connected PT-Capsules (FC-PT-Caps) and locally connected PT-Capsules (LC-PT-Caps). Different from existing CapsNet structures, our proposed model (i) allows the use of capsules for more difficult vision tasks and provides wider applicability; and (ii) provides better than or comparable performance to CNN-based baselines on these complex tasks. In our experiments, we show robustness to affine transformations, as well as the lightweight and scalability of PT-CapsNet via constructing larger and deeper networks and performing comparisons on classification, semantic segmentation and object detection tasks. The results show consistent performance improvement and significant parameter reduction compared to various baseline models. Code is available at https://github.com/Christinepan881/PT-CapsNet.git.

Jing Tan, Jiaqi Tang, Limin Wang, Gangshan Wu

Temporal action proposal generation is an important and challenging task in video understanding, which aims at detecting all temporal segments containing action instances of interest. The existing proposal generation approaches are generally based on pre-defined anchor windows or heuristic bottom-up boundary matching strategies. This paper presents a simple and efficient framework (RTD-Net) for direct action proposal generation, by re-purposing a Transformer-alike architecture. To tackle the essential visual difference between time and space, we make three important improvements over the original transformer detection framework (DETR). First, to deal with slowness prior in videos, we replace the original Transformer encoder with a boundary attentive module to better capture long-range temporal information. Second, due to the ambiguous temporal boundary and relatively sparse annotations, we present a relaxed matching scheme to relieve the strict criteria of single assignment to each groundtruth. Finally, we devise a three-branch head to further improve the proposal confidence estimation by explicitly predicting its completeness. Extensive experiments on THUMOS14 and ActivityNet-1.3 benchmarks demonstrate the effectiveness of RTD-Net, on both tasks of temporal action proposal generation and temporal action detection. Moreover, due to its simplicity in design, our framework is more efficient than previous proposal generation methods, without non-maximum suppression post-processing. The code and models are made available at https://github.com/MCG-NJU/RTD-Action.

Matteo Fabbri, Guillem Brasó, Gianluca Maugeri, Orcun Cetintas, Riccardo Gasparini, Aljoša Ošep, Simone Calderara, Laura Leal-Taixé, Rita Cucchiara

Deep learning-based methods for video pedestrian detection and tracking require large volumes of training data to achieve good performance. However, data acquisition in crowded public environments raises data privacy concerns -- we are not allowed to simply record and store data without the explicit consent of all participants. Furthermore, the annotation of such data for computer vision applications usually requires a substantial amount of manual effort, especially in the video domain. Labeling instances of pedestrians in highly crowded scenarios can be challenging even for human annotators and may introduce errors in the training data. In this paper, we study how we can advance different aspects of multi-person tracking using solely synthetic data. To this end, we generate MOTSynth, a large, highly diverse synthetic dataset for object detection and tracking using a rendering game engine. Our experiments show that MOTSynth can be used as a replacement for real data on tasks such as pedestrian detection, re-identification, segmentation, and tracking.

Hanchen Wang, Qi Liu, Xiangyu Yue, Joan Lasenby, Matt J. Kusner

We describe a simple pre-training approach for point clouds. It works in three steps: 1. Mask all points occluded in a camera view; 2. Learn an encoder-decoder model to reconstruct the occluded points; 3. Use the encoder weights as initialisation for downstream point cloud tasks. We find that even when we pre-train on a single dataset (ModelNet40), this method improves accuracy across different datasets and encoders, on a wide range of downstream tasks. Specifically, we show that our method outperforms previous pre-training methods in object classification, and both part-based and semantic segmentation tasks. We study the pre-trained features and find that they lead to wide downstream minima, have high transformation invariance, and have activations that are highly correlated with part labels. Code and data are available at https://github.com/hansen7/OcCo

Lin Wang, Yujeong Chae, Kuk-Jin Yoon

Event cameras are novel sensors that perceive the per-pixel intensity changes and output asynchronous event streams with high dynamic range and less motion blur. It has been shown that events alone can be used for end-task learning, e.g., semantic segmentation, based on encoder-decoder-like networks. However, as events are sparse and mostly reflect edge information, it is difficult to recover original details merely relying on the decoder. Moreover, most methods resort to the pixel-wise loss alone for supervision, which might be insufficient to fully exploit the visual details from sparse events, thus leading to less optimal performance. In this paper, we propose a simple yet flexible two-stream framework named Dual Transfer Learning (DTL) to effectively enhance the performance on the end-tasks without adding extra inference cost. The proposed approach consists of three parts: event to end-task learning (EEL) branch, event to image translation (EIT) branch, and transfer learning (TL) module that simultaneously explores the feature-level affinity information and pixel-level knowledge from the EIT branch to improve the EEL branch. This simple yet novel method leads to strong representation learning from events and is evidenced by the significant performance boost on the end-tasks such as semantic segmentation and depth estimation.

Jinyu Yang, Chunyuan Li, Weizhi An, Hehuan Ma, Yuzhi Guo, Yu Rong, Peilin Zhao, Junzhou Huang

Recent studies imply that deep neural networks are vulnerable to adversarial examples, i.e., inputs with a slight but intentional perturbation are incorrectly classified by the network. Such vulnerability makes it risky for some security-related applications (e.g., semantic segmentation in autonomous cars) and triggers tremendous concerns on the model reliability. For the first time, we comprehensively evaluate the robustness of existing UDA methods and propose a robust UDA approach. It is rooted in two observations: i) the robustness of UDA methods in semantic segmentation remains unexplored, which poses a security concern in this field; and ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits model robustness in classification and recognition tasks, they fail to provide the critical supervision signals that are essential in semantic segmentation. These observations motivate us to propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. Extensive empirical studies on commonly used benchmarks demonstrate that ASSUDA is resistant to adversarial attacks.

Arthur Ouaknine, Alasdair Newson, Patrick Pérez, Florence Tupin, Julien Rebut

Understanding the scene around the ego-vehicle is key to assisted and autonomous driving. Nowadays, this is mostly conducted using cameras and laser scanners, despite their reduced performances in adverse weather conditions. Automotive radars are low-cost active sensors that measure properties of surrounding objects, including their relative speed, and have the key advantage of not being impacted by rain, snow or fog. However, they are seldom used for scene understanding due to the size and complexity of radar raw data and the lack of annotated datasets. Fortunately, recent open-sourced datasets have opened up research on classification, object detection and semantic segmentation with raw radar signals using end-to-end trainable models. In this work, we propose several novel architectures, and their associated losses, which analyse multiple "views" of the range-angle-Doppler radar tensor to segment it semantically. Experiments conducted on the recent CARRADA dataset demonstrate that our best model outperforms alternative models, derived either from the semantic segmentation of natural images or from radar scene understanding, while requiring significantly fewer parameters. Both our code and trained models are available at https://github.com/valeoai/MVRSS.

Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, Julien Mairal, Piotr Bojanowski, Armand Joulin

In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this architecture works particularly well, we make the following observations: first, self-supervised ViT features contain explicit information about the semantic segmentation of an image, which does not emerge as clearly with supervised ViTs, nor with convnets. Second, these features are also excellent k-NN classifiers, reaching 78.3% top-1 on ImageNet with a small ViT. Our study also underlines the importance of momentum encoder, multi-crop training, and the use of small patches with ViTs. We implement our findings into a simple self-supervised method, called DINO, which we interpret as a form of self-distillation with no labels. We show the synergy between DINO and ViTs by achieving 80.1% top-1 on ImageNet in linear evaluation with ViT-Base.

Fangxin Liu, Wenbo Zhao, Zhezhi He, Yanzhi Wang, Zongwu Wang, Changzhi Dai, Xiaoyao Liang, Li Jiang

Model quantization has emerged as a mandatory technique for efficient inference with advanced Deep Neural Networks (DNN). It converts the model parameters in full precision (32-bit floating point) to the hardware friendly data representation with shorter bit-width, to not only reduce the model size but also simplify the computation complexity. Nevertheless, prior model quantization either suffers from the inefficient data encoding method thus leading to noncompetitive model compression rate, or requires time-consuming quantization aware training process. In this work, we propose a novel Adaptive Floating-Point (AFP) as a variant of standard IEEE-754 floating-point format, with flexible configuration of exponent and mantissa segments. Leveraging the AFP for model quantization (i.e., encoding the parameter) could significantly enhance the model compression rate without accuracy degradation and model re-training. We also want to highlight that our proposed AFP could effectively eliminate the computationally intensive de-quantization step existing in the dynamic quantization technique adopted by the famous machine learning frameworks (e.g., pytorch, tensorRT and etc). Moreover, we develop a framework to automatically optimize and choose the adequate AFP configuration for each layer, thus maximizing the compression efficacy. Our experiments indicate that AFP-encoded ResNet-50/MobileNet-v2 only has ~0.04/0.6% accuracy degradation w.r.t its full-precision counterpart. It outperforms the state-of-the-art works by 1.1% in accuracy using the same bit-width while reducing the energy consumption by 11.2x, which is quite impressive for inference.

Kuniaki Saito, Donghyun Kim, Piotr Teterwak, Stan Sclaroff, Trevor Darrell, Kate Saenko

Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains. However, optimal hyper-parameter selection is critical to achieving high accuracy and avoiding negative transfer. Supervised hyper-parameter validation is not possible without labeled target data, which raises the question: How can we validate unsupervised adaptation techniques in a realistic way? We first empirically analyze existing criteria and demonstrate that they are not very effective for tuning hyper-parameters. Intuitively, a well-trained source classifier should embed target samples of the same class nearby, forming dense neighborhoods in feature space. Based on this assumption, we propose a novel unsupervised validation criterion that measures the density of soft neighborhoods by computing the entropy of the similarity distribution between points. Our criterion is simpler than competing validation methods, yet more effective; it can tune hyper-parameters and the number of training iterations in both image classification and semantic segmentation models.

Cristina González, Nicolás Ayobi, Isabela Hernández, José Hernández, Jordi Pont-Tuset, Pablo Arbeláez

This paper proposes Panoptic Narrative Grounding, a spatially fine and general formulation of the natural language visual grounding problem. We establish an experimental framework for the study of this new task, including new ground truth and metrics, and we propose a strong baseline method to serve as stepping stone for future work. We exploit the intrinsic semantic richness in an image by including panoptic categories, and we approach visual grounding at a fine-grained level by using segmentations. In terms of ground truth, we propose an algorithm to automatically transfer Localized Narratives annotations to specific regions in the panoptic segmentations of the MS COCO dataset. To guarantee the quality of our annotations, we take advantage of the semantic structure contained in WordNet to exclusively incorporate noun phrases that are grounded to a meaningfully related panoptic segmentation region. The proposed baseline achieves a performance of 55.4 absolute Average Recall points. This result is a suitable foundation to push the envelope further in the development of methods for Panoptic Narrative Grounding.

Sanghun Jung, Jungsoo Lee, Daehoon Gwak, Sungha Choi, Jaegul Choo

Identifying unexpected objects on roads in semantic segmentation (e.g., identifying dogs on roads) is crucial in safety-critical applications. Existing approaches use images of unexpected objects from external datasets or require additional training (e.g., retraining segmentation networks or training an extra network), which necessitate a non-trivial amount of labor intensity or lengthy inference time. One possible alternative is to use prediction scores of a pre-trained network such as the max logits (i.e., maximum values among classes before the final softmax layer) for detecting such objects. However, the distribution of max logits of each predicted class is significantly different from each other, which degrades the performance of identifying unexpected objects in urban-scene segmentation. To address this issue, we propose a simple yet effective approach that standardizes the max logits in order to align the different distributions and reflect the relative meanings of max logits within each predicted class. Moreover, we consider the local regions from two different perspectives based on the intuition that neighboring pixels share similar semantic information. In contrast to previous approaches, our method does not utilize any external datasets or require additional training, which makes our method widely applicable to existing pre-trained segmentation models. Such a straightforward approach achieves a new state-of-the-art performance on the publicly available Fishyscapes Lost & Found leaderboard with a large margin. Our code is publicly available at this link.

Yuanyi Zhong, Bodi Yuan, Hong Wu, Zhiqiang Yuan, Jian Peng, Yu-Xiong Wang

We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive property among different pixels. We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively. To address the computational efficiency issue and the false negative noise issue involved in the pixel contrastive loss, we further introduce and investigate several negative sampling techniques. Extensive experiments demonstrate the state-of-the-art performance of our method (PC2Seg) with the DeepLab-v3+ architecture, in several challenging semi-supervised settings derived from the VOC, Cityscapes, and COCO datasets.

Ye Chen, Jinxian Liu, Bingbing Ni, Hang Wang, Jiancheng Yang, Ning Liu, Teng Li, Qi Tian

We develop a novel self-supervised learning method named Shape Self-Correction for point cloud analysis. Our method is motivated by the principle that a good shape representation should be able to find distorted parts of a shape and correct them. To learn strong shape representations in an unsupervised manner, we first design a shape-disorganizing module to destroy certain local shape parts of an object. Then the destroyed shape and the normal shape are sent into a point cloud network to get representations, which are employed to segment points that belong to distorted parts and further reconstruct them to restore the shape to normal. To perform better in these two associated pretext tasks, the network is constrained to capture useful shape features from the object, which indicates that the point cloud network encodes rich geometric and contextual information. The learned feature extractor transfers well to downstream classification and segmentation tasks. Experimental results on ModelNet, ScanNet and ShapeNetPart demonstrate that our method achieves state-of-the-art performance among unsupervised methods. Our framework can be applied to a wide range of deep learning networks for point cloud analysis and we show experimentally that pre-training with our framework significantly boosts the performance of supervised models.