Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state. This work presents a new large-scale CNN-based foundation model, termed InternImage, which can obtain the gain from increasing parameters and training data like ViTs. Different from the recent CNNs that focus on large dense kernels, InternImage takes deformable convolution as the core operator, so that our model not only has the large effective receptive field required for downstream tasks such as detection and segmentation, but also has the adaptive spatial aggregation conditioned by input and task information. As a result, the proposed InternImage reduces the strict inductive bias of traditional CNNs and makes it possible to learn stronger and more robust patterns with large-scale parameters from massive data like ViTs. The effectiveness of our model is proven on challenging benchmarks including ImageNet, COCO, and ADE20K. It is worth mentioning that InternImage-H achieved the new record 65.4 mAP on COCO test-dev. The code will be released at https://github.com/OpenGVLab/InternImage.
Efficient trajectory generation in complex dynamic environment stills remains an open problem in the unmanned surface vehicle (USV) domain. In this paper, a cooperative trajectory planning algorithm for the coupled USV-UAV system is proposed, to ensure that USV can execute safe and smooth path in the process of autonomous advance in multi obstacle maps. Specifically, the unmanned aerial vehicle (UAV) plays the role as a flight sensor, and it provides real-time global map and obstacle information with lightweight semantic segmentation network and 3D projection transformation. And then an initial obstacle avoidance trajectory is generated by a graph-based search method. Concerning the unique under-actuated kinematic characteristics of the USV, a numerical optimization method based on hull dynamic constraints is introduced to make the trajectory easier to be tracked for motion control. Finally, a motion control method based on NMPC with the lowest energy consumption constraint during execution is proposed. Experimental results verify the effectiveness of whole system, and the generated trajectory is locally optimal for USV with considerable tracking accuracy.
Unmanned surface vessels (USVs) are widely used in ocean exploration and environmental protection fields. To ensure that USV can successfully perform its mission, trajectory planning and motion tracking are the two most critical technologies. In this paper, we propose a novel trajectory generation and tracking method for USV based on optimization theory. Specifically, the USV dynamic model is described with differential flatness, so that the trajectory can be generated by dynamic RRT* in a linear invariant system expression form under the objective of optimal boundary value. To reduce the sample number and improve efficiency, we adjust the trajectory through local optimization. The dynamic constraints are considered in the optimization process so that the generated trajectory conforms to the kinematic characteristics of the under-actuated hull, and makes it easier to be tracked. Finally, motion tracking is added with model predictive control under a sequential quadratic programming problem. Experimental results show the planned trajectory is more in line with the kinematic characteristics of USV, and the tracking accuracy remains a higher level.
Current object detectors typically have a feature pyramid (FP) module for multi-level feature fusion (MFF) which aims to mitigate the gap between features from different levels and form a comprehensive object representation to achieve better detection performance. However, they usually require heavy cross-level connections or iterative refinement to obtain better MFF result, making them complicated in structure and inefficient in computation. To address these issues, we propose a novel and efficient context modeling mechanism that can help existing FPs deliver better MFF results while reducing the computational costs effectively. In particular, we introduce a novel insight that comprehensive contexts can be decomposed and condensed into two types of representations for higher efficiency. The two representations include a locally concentrated representation and a globally summarized representation, where the former focuses on extracting context cues from nearby areas while the latter extracts key representations of the whole image scene as global context cues. By collecting the condensed contexts, we employ a Transformer decoder to investigate the relations between them and each local feature from the FP and then refine the MFF results accordingly. As a result, we obtain a simple and light-weight Transformer-based Context Condensation (TCC) module, which can boost various FPs and lower their computational costs simultaneously. Extensive experimental results on the challenging MS COCO dataset show that TCC is compatible to four representative FPs and consistently improves their detection accuracy by up to 7.8 % in terms of average precision and reduce their complexities by up to around 20% in terms of GFLOPs, helping them achieve state-of-the-art performance more efficiently. Code will be released.
Recently, animal pose estimation is attracting increasing interest from the academia (e.g., wildlife and conservation biology) focusing on animal behavior understanding. However, currently animal pose estimation suffers from small datasets and large data variances, making it difficult to obtain robust performance. To tackle this problem, we propose that the rich knowledge about relations between pose-related semantics learned by language models can be utilized to improve the animal pose estimation. Therefore, in this study, we introduce a novel PromptPose framework to effectively apply language models for better understanding the animal poses based on prompt training. In PromptPose, we propose that adapting the language knowledge to the visual animal poses is key to achieve effective animal pose estimation. To this end, we first introduce textual prompts to build connections between textual semantic descriptions and supporting animal keypoint features. Moreover, we further devise a pixel-level contrastive loss to build dense connections between textual descriptions and local image features, as well as a semantic-level contrastive loss to bridge the gap between global contrasts in language-image cross-modal pre-training and local contrasts in dense prediction. In practice, the PromptPose has shown great benefits for improving animal pose estimation. By conducting extensive experiments, we show that our PromptPose achieves superior performance under both supervised and few-shot settings, outperforming representative methods by a large margin. The source code and models will be made publicly available.
Existing trackers usually select a location or proposal with the maximum score as tracking result for each frame. However, such greedy search scheme maybe not the optimal choice, especially when encountering challenging tracking scenarios like heavy occlusions and fast motion. Since the accumulated errors would make response scores not reliable anymore. In this paper, we propose a novel multi-agent reinforcement learning based beam search strategy (termed BeamTracking) to address this issue. Specifically, we formulate the tracking as a sample selection problem fulfilled by multiple parallel decision-making processes, each of which aims at picking out one sample as their tracking result in each frame. We take the target feature, proposal feature, and its response score as state, and also consider actions predicted by nearby agent, to train multi-agents to select their actions. When all the frames are processed, we select the trajectory with the maximum accumulated score as the tracking result. Extensive experiments on seven popular tracking benchmark datasets validated the effectiveness of the proposed algorithm.
This work investigates a simple yet powerful adapter for Vision Transformer (ViT). Unlike recent visual transformers that introduce vision-specific inductive biases into their architectures, ViT achieves inferior performance on dense prediction tasks due to lacking prior information of images. To solve this issue, we propose a Vision Transformer Adapter (ViT-Adapter), which can remedy the defects of ViT and achieve comparable performance to vision-specific models by introducing inductive biases via an additional architecture. Specifically, the backbone in our framework is a vanilla transformer that can be pre-trained with multi-modal data. When fine-tuning on downstream tasks, a modality-specific adapter is used to introduce the data and tasks' prior information into the model, making it suitable for these tasks. We verify the effectiveness of our ViT-Adapter on multiple downstream tasks, including object detection, instance segmentation, and semantic segmentation. Notably, when using HTC++, our ViT-Adapter-L yields 60.1 box AP and 52.1 mask AP on COCO test-dev, surpassing Swin-L by 1.4 box AP and 1.0 mask AP. For semantic segmentation, our ViT-Adapter-L establishes a new state-of-the-art of 60.5 mIoU on ADE20K val, 0.6 points higher than SwinV2-G. We hope that the proposed 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.
Point cloud segmentation is fundamental in understanding 3D environments. However, current 3D point cloud segmentation methods usually perform poorly on scene boundaries, which degenerates the overall segmentation performance. In this paper, we focus on the segmentation of scene boundaries. Accordingly, we first explore metrics to evaluate the segmentation performance on scene boundaries. To address the unsatisfactory performance on boundaries, we then propose a novel contrastive boundary learning (CBL) framework for point cloud segmentation. Specifically, the proposed CBL enhances feature discrimination between points across boundaries by contrasting their representations with the assistance of scene contexts at multiple scales. By applying CBL on three different baseline methods, we experimentally show that CBL consistently improves different baselines and assists them to achieve compelling performance on boundaries, as well as the overall performance, eg in mIoU. The experimental results demonstrate the effectiveness of our method and the importance of boundaries for 3D point cloud segmentation. Code and model will be made publicly available at https://github.com/LiyaoTang/contrastBoundary.
Linear regression is a supervised method that has been widely used in classification tasks. In order to apply linear regression to classification tasks, a technique for relaxing regression targets was proposed. However, methods based on this technique ignore the pressure on a single transformation matrix due to the complex information contained in the data. A single transformation matrix in this case is too strict to provide a flexible projection, thus it is necessary to adopt relaxation on transformation matrix. This paper proposes a double transformation matrices learning method based on latent low-rank feature extraction. The core idea is to use double transformation matrices for relaxation, and jointly projecting the learned principal and salient features from two directions into the label space, which can share the pressure of a single transformation matrix. Firstly, the low-rank features are learned by the latent low rank representation (LatLRR) method which processes the original data from two directions. In this process, sparse noise is also separated, which alleviates its interference on projection learning to some extent. Then, two transformation matrices are introduced to process the two features separately, and the information useful for the classification is extracted. Finally, the two transformation matrices can be easily obtained by alternate optimization methods. Through such processing, even when a large amount of redundant information is contained in samples, our method can also obtain projection results that are easy to classify. Experiments on multiple data sets demonstrate the effectiveness of our approach for classification, especially for complex scenarios.