T-former: An Efficient Transformer for Image Inpainting

Benefiting from powerful convolutional neural networks (CNNs), learning-based image inpainting methods have made significant breakthroughs over the years. However, some nature of CNNs (e.g. local prior, spatially shared parameters) limit the performance in the face of broken images with diverse and complex forms. Recently, a class of attention-based network architectures, called transformer, has shown significant performance on natural language processing fields and high-level vision tasks. Compared with CNNs, attention operators are better at long-range modeling and have dynamic weights, but their computational complexity is quadratic in spatial resolution, and thus less suitable for applications involving higher resolution images, such as image inpainting. In this paper, we design a novel attention linearly related to the resolution according to Taylor expansion. And based on this attention, a network called $T$-former is designed for image inpainting. Experiments on several benchmark datasets demonstrate that our proposed method achieves state-of-the-art accuracy while maintaining a relatively low number of parameters and computational complexity. The code can be found at \href{https://github.com/dengyecode/T-former_image_inpainting}{github.com/dengyecode/T-former\_image\_inpainting}

VPFusion: Towards Robust Vertical Representation Learning for 3D Object Detection

Efficient point cloud representation is a fundamental element of Lidar-based 3D object detection. Recent grid-based detectors usually divide point clouds into voxels or pillars and construct single-stream networks in Bird's Eye View. However, these point cloud encoding paradigms underestimate the point representation in the vertical direction, which cause the loss of semantic or fine-grained information, especially for vertical sensitive objects like pedestrian and cyclists. In this paper, we propose an explicit vertical multi-scale representation learning framework, VPFusion, to combine the complementary information from both voxel and pillar streams. Specifically, VPFusion first builds upon a sparse voxel-pillar-based backbone. The backbone divides point clouds into voxels and pillars, then encodes features with 3D and 2D sparse convolution simultaneously. Next, we introduce the Sparse Fusion Layer (SFL), which establishes a bidirectional pathway for sparse voxel and pillar features to enable the interaction between them. Additionally, we present the Dense Fusion Neck (DFN) to effectively combine the dense feature maps from voxel and pillar branches with multi-scale. Extensive experiments on the large-scale Waymo Open Dataset and nuScenes Dataset demonstrate that VPFusion surpasses the single-stream baselines by a large margin and achieves state-of-the-art performance with real-time inference speed.

MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking

The main challenge of Multi-Object Tracking~(MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the same target between adjacent frames and discriminative appearance features to re-identify the lost targets after a long period. However, the reliability of motion prediction and the discriminability of appearances can be easily hurt by dense crowds and extreme occlusions in the tracking process. In this paper, we propose a simple yet effective multi-object tracker, i.e., MotionTrack, which learns robust short-term and long-term motions in a unified framework to associate trajectories from a short to long range. For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target. For extreme occlusions, we build a novel Refind Module to learn reliable long-term motions from the target's history trajectory, which can link the interrupted trajectory with its corresponding detection. Our Interaction Module and Refind Module are embedded in the well-known tracking-by-detection paradigm, which can work in tandem to maintain superior performance. Extensive experimental results on MOT17 and MOT20 datasets demonstrate the superiority of our approach in challenging scenarios, and it achieves state-of-the-art performances at various MOT metrics.

StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition

Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely on a time-consuming re-ranking step to exploit spatial structural information for better performance. In this paper, we propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features and thus improve feature stability in a constantly changing environment. Specifically, StructVPR uses segmentation images as a more definitive source of structural knowledge input into a CNN network and applies knowledge distillation to avoid online segmentation and inference of seg-branch in testing. Considering that not all samples contain high-quality and helpful knowledge, and some even hurt the performance of distillation, we partition samples and weigh each sample's distillation loss to enhance the expected knowledge precisely. Finally, StructVPR achieves impressive performance on several benchmarks using only global retrieval and even outperforms many two-stage approaches by a large margin. After adding additional re-ranking, ours achieves state-of-the-art performance while maintaining a low computational cost.

Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization

The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e.g., context and background, in an untrimmed video. While prior approaches have achieved substantial progress through devising advanced action detectors, they still suffer from these co-occurring ingredients which often dominate the actual action content in videos. In this paper, we explore two orthogonal but complementary aspects of a video snippet, i.e., the action features and the co-occurrence features. Especially, we develop a novel auxiliary task by decoupling these two types of features within a video snippet and recombining them to generate a new feature representation with more salient action information for accurate action localization. We term our method RefactorNet, which first explicitly factorizes the action content and regularizes its co-occurrence features, and then synthesizes a new action-dominated video representation. Extensive experimental results and ablation studies on THUMOS14 and ActivityNet v1.3 demonstrate that our new representation, combined with a simple action detector, can significantly improve the action localization performance.

Social Interpretable Tree for Pedestrian Trajectory Prediction

Understanding the multiple socially-acceptable future behaviors is an essential task for many vision applications. In this paper, we propose a tree-based method, termed as Social Interpretable Tree (SIT), to address this multi-modal prediction task, where a hand-crafted tree is built depending on the prior information of observed trajectory to model multiple future trajectories. Specifically, a path in the tree from the root to leaf represents an individual possible future trajectory. SIT employs a coarse-to-fine optimization strategy, in which the tree is first built by high-order velocity to balance the complexity and coverage of the tree and then optimized greedily to encourage multimodality. Finally, a teacher-forcing refining operation is used to predict the final fine trajectory. Compared with prior methods which leverage implicit latent variables to represent possible future trajectories, the path in the tree can explicitly explain the rough moving behaviors (e.g., go straight and then turn right), and thus provides better interpretability. Despite the hand-crafted tree, the experimental results on ETH-UCY and Stanford Drone datasets demonstrate that our method is capable of matching or exceeding the performance of state-of-the-art methods. Interestingly, the experiments show that the raw built tree without training outperforms many prior deep neural network based approaches. Meanwhile, our method presents sufficient flexibility in long-term prediction and different best-of-$K$ predictions.

TransVPR: Transformer-based place recognition with multi-level attention aggregation

Visual place recognition is a challenging task for applications such as autonomous driving navigation and mobile robot localization. Distracting elements presenting in complex scenes often lead to deviations in the perception of visual place. To address this problem, it is crucial to integrate information from only task-relevant regions into image representations. In this paper, we introduce a novel holistic place recognition model, TransVPR, based on vision Transformers. It benefits from the desirable property of the self-attention operation in Transformers which can naturally aggregate task-relevant features. Attentions from multiple levels of the Transformer, which focus on different regions of interest, are further combined to generate a global image representation. In addition, the output tokens from Transformer layers filtered by the fused attention mask are considered as key-patch descriptors, which are used to perform spatial matching to re-rank the candidates retrieved by the global image features. The whole model allows end-to-end training with a single objective and image-level supervision. TransVPR achieves state-of-the-art performance on several real-world benchmarks while maintaining low computational time and storage requirements.

Auxiliary Loss Adaptation for Image Inpainting

Auxiliary losses commonly used in image inpainting lead to better reconstruction performance by incorporating prior knowledge of missing regions. However, it usually requires a lot of effort to fully exploit the potential of auxiliary losses, or otherwise, improperly weighted auxiliary losses would distract the model from the inpainting task, and the effectiveness of an auxiliary loss might vary during the training process. Hence the design of auxiliary losses takes strong domain expertise. To mitigate the problem, in this work, we introduce the Auxiliary Loss Adaptation for Image Inpainting (ALA) algorithm to dynamically adjust the parameters of the auxiliary loss. Our method is based on the principle that the best auxiliary loss is the one that helps increase the performance of the main loss most through several steps of gradient descent. We then examined two commonly used auxiliary losses in inpainting and used ALA to adapt their parameters. Experimental results show that ALA induces more competitive inpainting results than fixed auxiliary losses. In particular, simply combining auxiliary loss with ALA, existing inpainting methods can achieve increased performances without explicitly incorporating delicate network design or structure knowledge prior.

Auxiliary Loss Adaption for Image Inpainting

Auxiliary losses commonly used in image inpainting lead to better reconstruction performance by incorporating prior knowledge of missing regions. However, it usually takes a lot of effort to fully exploit the potential of auxiliary losses, since improperly weighted auxiliary losses would distract the model from the inpainting task, and the effectiveness of an auxiliary loss might vary during the training process. Furthermore, the design of auxiliary losses takes domain expertise. In this work, we introduce the Auxiliary Loss Adaption (Adaption) algorithm to dynamically adjust the parameters of the auxiliary loss, to better assist the primary task. Our algorithm is based on the principle that better auxiliary loss is the one that helps increase the performance of the main loss through several steps of gradient descent. We then examined two commonly used auxiliary losses in inpainting and use \ac{ALA} to adapt their parameters. Experimental results show that ALA induces more competitive inpainting results than fixed auxiliary losses. In particular, simply combining auxiliary loss with \ac{ALA}, existing inpainting methods can achieve increased performances without explicitly incorporating delicate network design or structure knowledge prior.