Despite that leveraging the transferability of adversarial examples can attain a fairly high attack success rate for non-targeted attacks, it does not work well in targeted attacks since the gradient directions from a source image to a targeted class are usually different in different DNNs. To increase the transferability of target attacks, recent studies make efforts in aligning the feature of the generated adversarial example with the feature distributions of the targeted class learned from an auxiliary network or a generative adversarial network. However, these works assume that the training dataset is available and require a lot of time to train networks, which makes it hard to apply to real-world scenarios. In this paper, we revisit adversarial examples with targeted transferability from the perspective of universality and find that highly universal adversarial perturbations tend to be more transferable. Based on this observation, we propose the Locality of Images (LI) attack to improve targeted transferability. Specifically, instead of using the classification loss only, LI introduces a feature similarity loss between intermediate features from adversarial perturbed original images and randomly cropped images, which makes the features from adversarial perturbations to be more dominant than that of benign images, hence improving targeted transferability. Through incorporating locality of images into optimizing perturbations, the LI attack emphasizes that targeted perturbations should be universal to diverse input patterns, even local image patches. Extensive experiments demonstrate that LI can achieve high success rates for transfer-based targeted attacks. On attacking the ImageNet-compatible dataset, LI yields an improvement of 12\% compared with existing state-of-the-art methods.
Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. However, this is challenging due to the difficulty of combining multi-granularity geometric and semantic features from two drastically different modalities. Recent approaches aim at exploring the semantic densities of camera features through lifting points in 2D camera images (referred to as seeds) into 3D space for fusion, and they can be roughly divided into 1) early fusion of raw points that aims at augmenting the 3D point cloud at the early input stage, and 2) late fusion of BEV (bird-eye view) maps that merges LiDAR and camera BEV features before the detection head. While both have their merits in enhancing the representation power of the combined features, this single-level fusion strategy is a suboptimal solution to the aforementioned challenge. Their major drawbacks are the inability to interact the multi-granularity semantic features from two distinct modalities sufficiently. To this end, we propose a novel framework that focuses on the multi-scale progressive interaction of the multi-granularity LiDAR and camera features. Our proposed method, abbreviated as MDMSFusion, achieves state-of-the-art results in 3D object detection, with 69.1 mAP and 71.8 NDS on nuScenes validation set, and 70.8 mAP and 73.2 NDS on nuScenes test set, which rank 1st and 2nd respectively among single-model non-ensemble approaches by the time of submission.
Transformer-based models have achieved top performance on major video recognition benchmarks. Benefiting from the self-attention mechanism, these models show stronger ability of modeling long-range dependencies compared to CNN-based models. However, significant computation overheads, resulted from the quadratic complexity of self-attention on top of a tremendous number of tokens, limit the use of existing video transformers in applications with limited resources like mobile devices. In this paper, we extend Mobile-Former to Video Mobile-Former, which decouples the video architecture into a lightweight 3D-CNNs for local context modeling and a Transformer modules for global interaction modeling in a parallel fashion. To avoid significant computational cost incurred by computing self-attention between the large number of local patches in videos, we propose to use very few global tokens (e.g., 6) for a whole video in Transformers to exchange information with 3D-CNNs with a cross-attention mechanism. Through efficient global spatial-temporal modeling, Video Mobile-Former significantly improves the video recognition performance of alternative lightweight baselines, and outperforms other efficient CNN-based models at the low FLOP regime from 500M to 6G total FLOPs on various video recognition tasks. It is worth noting that Video Mobile-Former is the first Transformer-based video model which constrains the computational budget within 1G FLOPs.
3D object detection in autonomous driving aims to reason "what" and "where" the objects of interest present in a 3D world. Following the conventional wisdom of previous 2D object detection, existing methods often adopt the canonical Cartesian coordinate system with perpendicular axis. However, we conjugate that this does not fit the nature of the ego car's perspective, as each onboard camera perceives the world in shape of wedge intrinsic to the imaging geometry with radical (non-perpendicular) axis. Hence, in this paper we advocate the exploitation of the Polar coordinate system and propose a new Polar Transformer (PolarFormer) for more accurate 3D object detection in the bird's-eye-view (BEV) taking as input only multi-camera 2D images. Specifically, we design a cross attention based Polar detection head without restriction to the shape of input structure to deal with irregular Polar grids. For tackling the unconstrained object scale variations along Polar's distance dimension, we further introduce a multi-scalePolar representation learning strategy. As a result, our model can make best use of the Polar representation rasterized via attending to the corresponding image observation in a sequence-to-sequence fashion subject to the geometric constraints. Thorough experiments on the nuScenes dataset demonstrate that our PolarFormer outperforms significantly state-of-the-art 3D object detection alternatives, as well as yielding competitive performance on BEV semantic segmentation task.
3D object detection in autonomous driving aims to reason "what" and "where" the objects of interest present in a 3D world. Following the conventional wisdom of previous 2D object detection, existing methods often adopt the canonical Cartesian coordinate system with perpendicular axis. However, we conjugate that this does not fit the nature of the ego car's perspective, as each onboard camera perceives the world in shape of wedge intrinsic to the imaging geometry with radical (non-perpendicular) axis. Hence, in this paper we advocate the exploitation of the Polar coordinate system and propose a new Polar Transformer (PolarFormer) for more accurate 3D object detection in the bird's-eye-view (BEV) taking as input only multi-camera 2D images. Specifically, we design a cross attention based Polar detection head without restriction to the shape of input structure to deal with irregular Polar grids. For tackling the unconstrained object scale variations along Polar's distance dimension, we further introduce a multi-scalePolar representation learning strategy. As a result, our model can make best use of the Polar representation rasterized via attending to the corresponding image observation in a sequence-to-sequence fashion subject to the geometric constraints. Thorough experiments on the nuScenes dataset demonstrate that our PolarFormer outperforms significantly state-of-the-art 3D object detection alternatives, as well as yielding competitive performance on BEV semantic segmentation task.
Leveraging large-scale data can introduce performance gains on many computer vision tasks. Unfortunately, this does not happen in object detection when training a single model under multiple datasets together. We observe two main obstacles: taxonomy difference and bounding box annotation inconsistency, which introduces domain gaps in different datasets that prevents us from joint training. In this paper, we show that these two challenges can be effectively addressed by simply adapting object queries on language embedding of categories per dataset. We design a detection hub to dynamically adapt queries on category embedding based on the different distributions of datasets. Unlike previous methods attempted to learn a joint embedding for all datasets, our adaptation method can utilize the language embedding as semantic centers for common categories, while learning the semantic bias towards specific categories belonging to different datasets to handle annotation differences and make up the domain gaps. These novel improvements enable us to end-to-end train a single detector on multiple datasets simultaneously to fully take their advantages. Further experiments on joint training on multiple datasets demonstrate the significant performance gains over separate individual fine-tuned detectors.
Dominant scene text recognition models commonly contain two building blocks, a visual model for feature extraction and a sequence model for text transcription. This hybrid architecture, although accurate, is complex and less efficient. In this study, we propose a Single Visual model for Scene Text recognition within the patch-wise image tokenization framework, which dispenses with the sequential modeling entirely. The method, termed SVTR, firstly decomposes an image text into small patches named character components. Afterward, hierarchical stages are recurrently carried out by component-level mixing, merging and/or combining. Global and local mixing blocks are devised to perceive the inter-character and intra-character patterns, leading to a multi-grained character component perception. Thus, characters are recognized by a simple linear prediction. Experimental results on both English and Chinese scene text recognition tasks demonstrate the effectiveness of SVTR. SVTR-L (Large) achieves highly competitive accuracy in English and outperforms existing methods by a large margin in Chinese, while running faster. In addition, SVTR-T (Tiny) is an effective and much smaller model, which shows appealing speed at inference. The code is publicly available at https://github.com/PaddlePaddle/PaddleOCR.
Recent literature have shown design strategies from Convolutions Neural Networks (CNNs) benefit Vision Transformers (ViTs) in various vision tasks. However, it remains unclear how these design choices impact on robustness when transferred to ViTs. In this paper, we make the first attempt to investigate how CNN-like architectural designs and CNN-based data augmentation strategies impact on ViTs' robustness towards common corruptions through an extensive and rigorous benchmarking. We demonstrate that overlapping patch embedding and convolutional Feed-Forward Network (FFN) boost performance on robustness. Furthermore, adversarial noise training is powerful on ViTs while fourier-domain augmentation fails. Moreover, we introduce a novel conditional method enabling input-varied augmentations from two angles: (1) Generating dynamic augmentation parameters conditioned on input images. It conduces to state-of-the-art performance on robustness through conditional convolutions; (2) Selecting most suitable augmentation strategy by an extra predictor helps to achieve the best trade-off between clean accuracy and robustness.
Video moment retrieval aims at finding the start and end timestamps of a moment (part of a video) described by a given natural language query. Fully supervised methods need complete temporal boundary annotations to achieve promising results, which is costly since the annotator needs to watch the whole moment. Weakly supervised methods only rely on the paired video and query, but the performance is relatively poor. In this paper, we look closer into the annotation process and propose a new paradigm called "glance annotation". This paradigm requires the timestamp of only one single random frame, which we refer to as a "glance", within the temporal boundary of the fully supervised counterpart. We argue this is beneficial because comparing to weak supervision, trivial cost is added yet more potential in performance is provided. Under the glance annotation setting, we propose a method named as Video moment retrieval via Glance Annotation (ViGA) based on contrastive learning. ViGA cuts the input video into clips and contrasts between clips and queries, in which glance guided Gaussian distributed weights are assigned to all clips. Our extensive experiments indicate that ViGA achieves better results than the state-of-the-art weakly supervised methods by a large margin, even comparable to fully supervised methods in some cases.