In recent years, target tracking has made great progress in accuracy. This development is mainly attributed to powerful networks (such as transformers) and additional modules (such as online update and refinement modules). However, less attention has been paid to tracking speed. Most state-of-the-art trackers are satisfied with the real-time speed on powerful GPUs. However, practical applications necessitate higher requirements for tracking speed, especially when edge platforms with limited resources are used. In this work, we present an efficient tracking method via a hierarchical cross-attention transformer named HCAT. Our model runs about 195 fps on GPU, 45 fps on CPU, and 55 fps on the edge AI platform of NVidia Jetson AGX Xavier. Experiments show that our HCAT achieves promising results on LaSOT, GOT-10k, TrackingNet, NFS, OTB100, UAV123, and VOT2020. Code and models are available at https://github.com/chenxin-dlut/HCAT.
Correlation has a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion manner to consider the similarity between the template and the search region. However, the correlation operation is a local linear matching process, losing semantic information and falling into local optimum easily, which may be the bottleneck of designing high-accuracy tracking algorithms. In this work, to determine whether a better feature fusion method exists than correlation, a novel attention-based feature fusion network, inspired by Transformer, is presented. This network effectively combines the template and the search region features using attention. Specifically, the proposed method includes an ego-context augment module based on self-attention and a cross-feature augment module based on cross-attention. First, we present a Transformer tracking (named TransT) method based on the Siamese-like feature extraction backbone, the designed attention-based fusion mechanism, and the classification and regression head. Based on the TransT baseline, we further design a segmentation branch to generate an accurate mask. Finally, we propose a stronger version of TransT by extending TransT with a multi-template design and an IoU prediction head, named TransT-M. Experiments show that our TransT and TransT-M methods achieve promising results on seven popular datasets. Code and models are available at https://github.com/chenxin-dlut/TransT-M.
Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environments. However, high-quality depth sensors are expensive and can not be widely applied. While general depth sensors produce the noisy and sparse depth information, which brings the depth-based networks with irreversible interference. In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD). Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. In this way, the depth information can be completed and purified. Moreover, we introduce a multi-modal filtered transformer (MFT) module, which equips with three modality-specific filters to generate the transformer-enhanced feature for each modality. The proposed model works in a depth-free style during the testing phase. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time. And, the resulted depth map can help existing RGB-D SOD methods obtain significant performance gain.
Lane detection is one of the core functions in autonomous driving and has aroused widespread attention recently. The networks to segment lane instances, especially with bad appearance, must be able to explore lane distribution properties. Most existing methods tend to resort to CNN-based techniques. A few have a try on incorporating the recent adorable, the seq2seq Transformer \cite{transformer}. However, their innate drawbacks of weak global information collection ability and exorbitant computation overhead prohibit a wide range of the further applications. In this work, we propose Atrous Transformer (AtrousFormer) to solve the problem. Its variant local AtrousFormer is interleaved into feature extractor to enhance extraction. Their collecting information first by rows and then by columns in a dedicated manner finally equips our network with stronger information gleaning ability and better computation efficiency. To further improve the performance, we also propose a local semantic guided decoder to delineate the identities and shapes of lanes more accurately, in which the predicted Gaussian map of the starting point of each lane serves to guide the process. Extensive results on three challenging benchmarks (CULane, TuSimple, and BDD100K) show that our network performs favorably against the state of the arts.
Along with the rapid progress of visual tracking, existing benchmarks become less informative due to redundancy of samples and weak discrimination between current trackers, making evaluations on all datasets extremely time-consuming. Thus, a small and informative benchmark, which covers all typical challenging scenarios to facilitate assessing the tracker performance, is of great interest. In this work, we develop a principled way to construct a small and informative tracking benchmark (ITB) with 7% out of 1.2 M frames of existing and newly collected datasets, which enables efficient evaluation while ensuring effectiveness. Specifically, we first design a quality assessment mechanism to select the most informative sequences from existing benchmarks taking into account 1) challenging level, 2) discriminative strength, 3) and density of appearance variations. Furthermore, we collect additional sequences to ensure the diversity and balance of tracking scenarios, leading to a total of 20 sequences for each scenario. By analyzing the results of 15 state-of-the-art trackers re-trained on the same data, we determine the effective methods for robust tracking under each scenario and demonstrate new challenges for future research direction in this field.
Most of the existing RGB-D salient object detection methods utilize the convolution operation and construct complex interweave fusion structures to achieve cross-modal information integration. The inherent local connectivity of convolution operation constrains the performance of the convolution-based methods to a ceiling. In this work, we rethink this task from the perspective of global information alignment and transformation. Specifically, the proposed method (TransCMD) cascades several cross-modal integration units to construct a top-down transformer-based information propagation path (TIPP). TransCMD treats the multi-scale and multi-modal feature integration as a sequence-to-sequence context propagation and update process built on the transformer. Besides, considering the quadratic complexity w.r.t. the number of input tokens, we design a patch-wise token re-embedding strategy (PTRE) with acceptable computational cost. Experimental results on seven RGB-D SOD benchmark datasets demonstrate that a simple two-stream encoder-decoder framework can surpass the state-of-the-art purely CNN-based methods when it is equipped with the TIPP.
Weakly supervised salient object detection (WSOD) targets to train a CNNs-based saliency network using only low-cost annotations. Existing WSOD methods take various techniques to pursue single "high-quality" pseudo label from low-cost annotations and then develop their saliency networks. Though these methods have achieved good performance, the generated single label is inevitably affected by adopted refinement algorithms and shows prejudiced characteristics which further influence the saliency networks. In this work, we introduce a new multiple-pseudo-label framework to integrate more comprehensive and accurate saliency cues from multiple labels, avoiding the aforementioned problem. Specifically, we propose a multi-filter directive network (MFNet) including a saliency network as well as multiple directive filters. The directive filter (DF) is designed to extract and filter more accurate saliency cues from the noisy pseudo labels. The multiple accurate cues from multiple DFs are then simultaneously propagated to the saliency network with a multi-guidance loss. Extensive experiments on five datasets over four metrics demonstrate that our method outperforms all the existing congeneric methods. Moreover, it is also worth noting that our framework is flexible enough to apply to existing methods and improve their performance.
RGB-D saliency detection integrates information from both RGB images and depth maps to improve prediction of salient regions under challenging conditions. The key to RGB-D saliency detection is to fully mine and fuse information at multiple scales across the two modalities. Previous approaches tend to apply the multi-scale and multi-modal fusion separately via local operations, which fails to capture long-range dependencies. Here we propose a transformer-based network to address this issue. Our proposed architecture is composed of two modules: a transformer-based within-modality feature enhancement module (TWFEM) and a transformer-based feature fusion module (TFFM). TFFM conducts a sufficient feature fusion by integrating features from multiple scales and two modalities over all positions simultaneously. TWFEM enhances feature on each scale by selecting and integrating complementary information from other scales within the same modality before TFFM. We show that transformer is a uniform operation which presents great efficacy in both feature fusion and feature enhancement, and simplifies the model design. Extensive experimental results on six benchmark datasets demonstrate that our proposed network performs favorably against state-of-the-art RGB-D saliency detection methods.
To address the challenging portrait video matting problem more precisely, existing works typically apply some matting priors that require additional user efforts to obtain, such as annotated trimaps or background images. In this work, we observe that instead of asking the user to explicitly provide a background image, we may recover it from the input video itself. To this end, we first propose a novel background restoration module (BRM) to recover the background image dynamically from the input video. BRM is extremely lightweight and can be easily integrated into existing matting models. By combining BRM with a recent image matting model, MODNet, we then present MODNet-V for portrait video matting. Benefited from the strong background prior provided by BRM, MODNet-V has only 1/3 of the parameters of MODNet but achieves comparable or even better performances. Our design allows MODNet-V to be trained in an end-to-end manner on a single NVIDIA 3090 GPU. Finally, we introduce a new patch refinement module (PRM) to adapt MODNet-V for high-resolution videos while keeping MODNet-V lightweight and fast.
Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. Despite of the success of previous works, explorations on an effective training strategy for the saliency network and accurate matches between image-level annotations and salient objects are still inadequate. In this work, 1) we propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions, liberating the saliency network from error-prone propagation caused by pseudo labels. 2) we prove that even a much smaller dataset (merely 1.8% of ImageNet) with well-matched annotations can facilitate models to achieve better performance as well as generalizability. This sheds new light on the development of WSOD and encourages more contributions to the community. Comprehensive experiments demonstrate that our method outperforms all the existing WSOD methods by adopting the self-calibrated strategy only. Steady improvements are further achieved by training on the proposed dataset. Additionally, our method achieves 94.7% of the performance of fully-supervised methods on average. And what is more, the fully supervised models adopting our predicted results as "ground truths" achieve successful results (95.6% for BASNet and 97.3% for ITSD on F-measure), while costing only 0.32% of labeling time for pixel-level annotation.