We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training inefficiency; (2) DETR-based detectors lack deterministic correspondence between the input query and its prediction output, which hinders the applicability of the consistency-based regularization widely used in current SSOD methods. We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector, to tackle these problems. Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage. Besides, we introduce a Crossview Query Consistency method to learn the semantic feature invariance of object queries from different views while avoiding the need to find deterministic query correspondence. Furthermore, we propose a Cost-based Pseudo Label Mining module to dynamically mine more pseudo boxes based on the matching cost of pseudo ground truth bounding boxes for consistency training. Extensive experiments on all SSOD settings of both COCO and Pascal VOC benchmark datasets show that our Semi-DETR method outperforms all state-of-the-art methods by clear margins. The PaddlePaddle version code1 is at https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/semi_det/semi_detr.
One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network. Existing methods typically improve the quality of heatmaps by customized architectures, such as high-resolution representation and vision Transformers. In this paper, we propose \textbf{DiffusionPose}, a new scheme that formulates 2D HPE as a keypoints heatmaps generation problem from noised heatmaps. During training, the keypoints are diffused to random distribution by adding noises and the diffusion model learns to recover ground-truth heatmaps from noised heatmaps with respect to conditions constructed by image feature. During inference, the diffusion model generates heatmaps from initialized heatmaps in a progressive denoising way. Moreover, we further explore improving the performance of DiffusionPose with conditions from human structural information. Extensive experiments show the prowess of our DiffusionPose, with improvements of 1.6, 1.2, and 1.2 mAP on widely-used COCO, CrowdPose, and AI Challenge datasets, respectively.
Vision Transformer(ViT) is now dominating many vision tasks. The drawback of quadratic complexity of its token-wise multi-head self-attention (MHSA), is extensively addressed via either token sparsification or dimension reduction (in spatial or channel). However, the therein redundancy of MHSA is usually overlooked and so is the feed-forward network (FFN). To this end, we propose attention map hallucination and FFN compaction to fill in the blank. Specifically, we observe similar attention maps exist in vanilla ViT and propose to hallucinate half of the attention maps from the rest with much cheaper operations, which is called hallucinated-MHSA (hMHSA). As for FFN, we factorize its hidden-to-output projection matrix and leverage the re-parameterization technique to strengthen its capability, making it compact-FFN (cFFN). With our proposed modules, a 10$\%$-20$\%$ reduction of floating point operations (FLOPs) and parameters (Params) is achieved for various ViT-based backbones, including straight (DeiT), hybrid (NextViT) and hierarchical (PVT) structures, meanwhile, the performances are quite competitive.
Structured text extraction is one of the most valuable and challenging application directions in the field of Document AI. However, the scenarios of past benchmarks are limited, and the corresponding evaluation protocols usually focus on the submodules of the structured text extraction scheme. In order to eliminate these problems, we organized the ICDAR 2023 competition on Structured text extraction from Visually-Rich Document images (SVRD). We set up two tracks for SVRD including Track 1: HUST-CELL and Track 2: Baidu-FEST, where HUST-CELL aims to evaluate the end-to-end performance of Complex Entity Linking and Labeling, and Baidu-FEST focuses on evaluating the performance and generalization of Zero-shot / Few-shot Structured Text extraction from an end-to-end perspective. Compared to the current document benchmarks, our two tracks of competition benchmark enriches the scenarios greatly and contains more than 50 types of visually-rich document images (mainly from the actual enterprise applications). The competition opened on 30th December, 2022 and closed on 24th March, 2023. There are 35 participants and 91 valid submissions received for Track 1, and 15 participants and 26 valid submissions received for Track 2. In this report we will presents the motivation, competition datasets, task definition, evaluation protocol, and submission summaries. According to the performance of the submissions, we believe there is still a large gap on the expected information extraction performance for complex and zero-shot scenarios. It is hoped that this competition will attract many researchers in the field of CV and NLP, and bring some new thoughts to the field of Document AI.
Modern autonomous driving systems are typically divided into three main tasks: perception, prediction, and planning. The planning task involves predicting the trajectory of the ego vehicle based on inputs from both internal intention and the external environment, and manipulating the vehicle accordingly. Most existing works evaluate their performance on the nuScenes dataset using the L2 error and collision rate between the predicted trajectories and the ground truth. In this paper, we reevaluate these existing evaluation metrics and explore whether they accurately measure the superiority of different methods. Specifically, we design an MLP-based method that takes raw sensor data (e.g., past trajectory, velocity, etc.) as input and directly outputs the future trajectory of the ego vehicle, without using any perception or prediction information such as camera images or LiDAR. Surprisingly, such a simple method achieves state-of-the-art end-to-end planning performance on the nuScenes dataset, reducing the average L2 error by about 30%. We further conduct in-depth analysis and provide new insights into the factors that are critical for the success of the planning task on nuScenes dataset. Our observation also indicates that we need to rethink the current open-loop evaluation scheme of end-to-end autonomous driving in nuScenes. Codes are available at https://github.com/E2E-AD/AD-MLP.
Multi-modal 3D object detection has received growing attention as the information from different sensors like LiDAR and cameras are complementary. Most fusion methods for 3D detection rely on an accurate alignment and calibration between 3D point clouds and RGB images. However, such an assumption is not reliable in a real-world self-driving system, as the alignment between different modalities is easily affected by asynchronous sensors and disturbed sensor placement. We propose a novel {F}usion network by {B}ox {M}atching (FBMNet) for multi-modal 3D detection, which provides an alternative way for cross-modal feature alignment by learning the correspondence at the bounding box level to free up the dependency of calibration during inference. With the learned assignments between 3D and 2D object proposals, the fusion for detection can be effectively performed by combing their ROI features. Extensive experiments on the nuScenes dataset demonstrate that our method is much more stable in dealing with challenging cases such as asynchronous sensors, misaligned sensor placement, and degenerated camera images than existing fusion methods. We hope that our FBMNet could provide an available solution to dealing with these challenging cases for safety in real autonomous driving scenarios. Codes will be publicly available at https://github.com/happinesslz/FBMNet.
Despite recent advances in syncing lip movements with any audio waves, current methods still struggle to balance generation quality and the model's generalization ability. Previous studies either require long-term data for training or produce a similar movement pattern on all subjects with low quality. In this paper, we propose StyleSync, an effective framework that enables high-fidelity lip synchronization. We identify that a style-based generator would sufficiently enable such a charming property on both one-shot and few-shot scenarios. Specifically, we design a mask-guided spatial information encoding module that preserves the details of the given face. The mouth shapes are accurately modified by audio through modulated convolutions. Moreover, our design also enables personalized lip-sync by introducing style space and generator refinement on only limited frames. Thus the identity and talking style of a target person could be accurately preserved. Extensive experiments demonstrate the effectiveness of our method in producing high-fidelity results on a variety of scenes. Resources can be found at https://hangz-nju-cuhk.github.io/projects/StyleSync.
The In-Context Learning (ICL) is to understand a new task via a few demonstrations (aka. prompt) and predict new inputs without tuning the models. While it has been widely studied in NLP, it is still a relatively new area of research in computer vision. To reveal the factors influencing the performance of visual in-context learning, this paper shows that prompt selection and prompt fusion are two major factors that have a direct impact on the inference performance of visual context learning. Prompt selection is the process of identifying the most appropriate prompt or example to help the model understand new tasks. This is important because providing the model with relevant prompts can help it learn more effectively and efficiently. Prompt fusion involves combining knowledge from different positions within the large-scale visual model. By doing this, the model can leverage the diverse knowledge stored in different parts of the model to improve its performance on new tasks. Based these findings, we propose a simple framework prompt-SelF for visual in-context learning. Specifically, we first use the pixel-level retrieval method to select a suitable prompt, and then use different prompt fusion methods to activate all the knowledge stored in the large-scale model, and finally ensemble the prediction results obtained from different prompt fusion methods to obtain the final prediction results. And we conduct extensive experiments on single-object segmentation and detection tasks to demonstrate the effectiveness of prompt-SelF. Remarkably, the prompt-SelF has outperformed OSLSM based meta-learning in 1-shot segmentation for the first time. This indicated the great potential of visual in-context learning. The source code and models will be available at \url{https://github.com/syp2ysy/prompt-SelF}.
Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an appropriate prompt for each specific task. Recent CoCoOp further boosts the base-to-new generalization performance via an image-conditional prompt. However, it directly fuses identical image semantics to prompts of different labels and significantly weakens the discrimination among different classes as shown in our experiments. Motivated by this observation, we first propose a class-aware text prompt (CTP) to enrich generated prompts with label-related image information. Unlike CoCoOp, CTP can effectively involve image semantics and avoid introducing extra ambiguities into different prompts. On the other hand, instead of reserving the complete image representations, we propose text-guided feature tuning (TFT) to make the image branch attend to class-related representation. A contrastive loss is employed to align such augmented text and image representations on downstream tasks. In this way, the image-to-text CTP and text-to-image TFT can be mutually promoted to enhance the adaptation of VLMs for downstream tasks. Extensive experiments demonstrate that our method outperforms the existing methods by a significant margin. Especially, compared to CoCoOp, we achieve an average improvement of 4.03% on new classes and 3.19% on harmonic-mean over eleven classification benchmarks.
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects across video frames. Detection boxes serve as the basis of both 2D and 3D MOT. The inevitable changing of detection scores leads to object missing after tracking. We propose a hierarchical data association strategy to mine the true objects in low-score detection boxes, which alleviates the problems of object missing and fragmented trajectories. The simple and generic data association strategy shows effectiveness under both 2D and 3D settings. In 3D scenarios, it is much easier for the tracker to predict object velocities in the world coordinate. We propose a complementary motion prediction strategy that incorporates the detected velocities with a Kalman filter to address the problem of abrupt motion and short-term disappearing. ByteTrackV2 leads the nuScenes 3D MOT leaderboard in both camera (56.4% AMOTA) and LiDAR (70.1% AMOTA) modalities. Furthermore, it is nonparametric and can be integrated with various detectors, making it appealing in real applications. The source code is released at https://github.com/ifzhang/ByteTrack-V2.