Current approaches in pose estimation primarily concentrate on enhancing model architectures, often overlooking the importance of comprehensively understanding the rationale behind model decisions. In this paper, we propose XPose, a novel framework that incorporates Explainable AI (XAI) principles into pose estimation. This integration aims to elucidate the individual contribution of each keypoint to final prediction, thereby elevating the model's transparency and interpretability. Conventional XAI techniques have predominantly addressed tasks with single-target tasks like classification. Additionally, the application of Shapley value, a common measure in XAI, to pose estimation has been hindered by prohibitive computational demands. To address these challenges, this work introduces an innovative concept called Group Shapley Value (GSV). This approach strategically organizes keypoints into clusters based on their interdependencies. Within these clusters, GSV meticulously calculates Shapley value for keypoints, while for inter-cluster keypoints, it opts for a more holistic group-level valuation. This dual-level computation framework meticulously assesses keypoint contributions to the final outcome, optimizing computational efficiency. Building on the insights into keypoint interactions, we devise a novel data augmentation technique known as Group-based Keypoint Removal (GKR). This method ingeniously removes individual keypoints during training phases, deliberately preserving those with strong mutual connections, thereby refining the model's predictive prowess for non-visible keypoints. The empirical validation of GKR across a spectrum of standard approaches attests to its efficacy. GKR's success demonstrates how using Explainable AI (XAI) can directly enhance pose estimation models.
Multi-modal large language models (MLLMs) have demonstrated remarkable vision-language capabilities, primarily due to the exceptional in-context understanding and multi-task learning strengths of large language models (LLMs). The advent of visual instruction tuning has further enhanced MLLMs' performance in vision-language understanding. However, while existing MLLMs adeptly recognize \textit{what} objects are in an image, they still face challenges in effectively discerning \textit{where} these objects are, particularly along the distance (scene depth) axis. To overcome this limitation in MLLMs, we introduce Proximity Question Answering (Proximity QA), a novel framework designed to enable MLLMs to infer the proximity relationship between objects in images. The framework operates in two phases: the first phase focuses on guiding the models to understand the relative depth of objects, and the second phase further encourages the models to infer the proximity relationships between objects based on their depth perceptions. We also propose a VQA dataset called Proximity-110K, containing additional instructions that incorporate depth information and the proximity relationships of objects. We have conducted extensive experiments to validate Proximity QA's superior ability in depth perception and proximity analysis, outperforming other state-of-the-art MLLMs. Code and dataset will be released at \textcolor{magenta}{https://github.com/NorthSummer/ProximityQA.git}.
The ResNet architecture has been widely adopted in deep learning due to its significant boost to performance through the use of simple skip connections, yet the underlying mechanisms leading to its success remain largely unknown. In this paper, we conduct a thorough empirical study of the ResNet architecture in classification tasks by linearizing its constituent residual blocks using Residual Jacobians and measuring their singular value decompositions. Our measurements reveal a process called Residual Alignment (RA) characterized by four properties: (RA1) intermediate representations of a given input are equispaced on a line, embedded in high dimensional space, as observed by Gai and Zhang [2021]; (RA2) top left and right singular vectors of Residual Jacobians align with each other and across different depths; (RA3) Residual Jacobians are at most rank C for fully-connected ResNets, where C is the number of classes; and (RA4) top singular values of Residual Jacobians scale inversely with depth. RA consistently occurs in models that generalize well, in both fully-connected and convolutional architectures, across various depths and widths, for varying numbers of classes, on all tested benchmark datasets, but ceases to occur once the skip connections are removed. It also provably occurs in a novel mathematical model we propose. This phenomenon reveals a strong alignment between residual branches of a ResNet (RA2+4), imparting a highly rigid geometric structure to the intermediate representations as they progress linearly through the network (RA1) up to the final layer, where they undergo Neural Collapse.
DAVIS camera, streaming two complementary sensing modalities of asynchronous events and frames, has gradually been used to address major object detection challenges (e.g., fast motion blur and low-light). However, how to effectively leverage rich temporal cues and fuse two heterogeneous visual streams remains a challenging endeavor. To address this challenge, we propose a novel streaming object detector with Transformer, namely SODFormer, which first integrates events and frames to continuously detect objects in an asynchronous manner. Technically, we first build a large-scale multimodal neuromorphic object detection dataset (i.e., PKU-DAVIS-SOD) over 1080.1k manual labels. Then, we design a spatiotemporal Transformer architecture to detect objects via an end-to-end sequence prediction problem, where the novel temporal Transformer module leverages rich temporal cues from two visual streams to improve the detection performance. Finally, an asynchronous attention-based fusion module is proposed to integrate two heterogeneous sensing modalities and take complementary advantages from each end, which can be queried at any time to locate objects and break through the limited output frequency from synchronized frame-based fusion strategies. The results show that the proposed SODFormer outperforms four state-of-the-art methods and our eight baselines by a significant margin. We also show that our unifying framework works well even in cases where the conventional frame-based camera fails, e.g., high-speed motion and low-light conditions. Our dataset and code can be available at https://github.com/dianzl/SODFormer.
Spiking neural networks (SNNs) are brain-inspired energy-efficient models that encode information in spatiotemporal dynamics. Recently, deep SNNs trained directly have shown great success in achieving high performance on classification tasks with very few time steps. However, how to design a directly-trained SNN for the regression task of object detection still remains a challenging problem. To address this problem, we propose EMS-YOLO, a novel directly-trained SNN framework for object detection, which is the first trial to train a deep SNN with surrogate gradients for object detection rather than ANN-SNN conversion strategies. Specifically, we design a full-spike residual block, EMS-ResNet, which can effectively extend the depth of the directly-trained SNN with low power consumption. Furthermore, we theoretically analyze and prove the EMS-ResNet could avoid gradient vanishing or exploding. The results demonstrate that our approach outperforms the state-of-the-art ANN-SNN conversion methods (at least 500 time steps) in extremely fewer time steps (only 4 time steps). It is shown that our model could achieve comparable performance to the ANN with the same architecture while consuming 5.83 times less energy on the frame-based COCO Dataset and the event-based Gen1 Dataset.
Given an untrimmed video, repetitive actions counting aims to estimate the number of repetitions of class-agnostic actions. To handle the various length of videos and repetitive actions, also optimization challenges in end-to-end video model training, down-sampling is commonly utilized in recent state-of-the-art methods, leading to ignorance of several repetitive samples. In this paper, we attempt to understand repetitive actions from a full temporal resolution view, by combining offline feature extraction and temporal convolution networks. The former step enables us to train repetition counting network without down-sampling while preserving all repetition regardless of the video length and action frequency, and the later network models all frames in a flexible and dynamically expanding temporal receptive field to retrieve all repetitions with a global aspect. We experimentally demonstrate that our method achieves better or comparable performance in three public datasets, i.e., TransRAC, UCFRep and QUVA. We expect this work will encourage our community to think about the importance of full temporal resolution.
Uncertainty estimation is critical for numerous applications of deep neural networks and draws growing attention from researchers. Here, we demonstrate an uncertainty quantification approach for deep neural networks used in inverse problems based on cycle consistency. We build forward-backward cycles using the physical forward model available and a trained deep neural network solving the inverse problem at hand, and accordingly derive uncertainty estimators through regression analysis on the consistency of these forward-backward cycles. We theoretically analyze cycle consistency metrics and derive their relationship with respect to uncertainty, bias, and robustness of the neural network inference. To demonstrate the effectiveness of these cycle consistency-based uncertainty estimators, we classified corrupted and out-of-distribution input image data using some of the widely used image deblurring and super-resolution neural networks as testbeds. The blind testing of our method outperformed other models in identifying unseen input data corruption and distribution shifts. This work provides a simple-to-implement and rapid uncertainty quantification method that can be universally applied to various neural networks used for solving inverse problems.
Event cameras, offering high temporal resolutions and high dynamic ranges, have brought a new perspective to address common challenges (e.g., motion blur and low light) in monocular depth estimation. However, how to effectively exploit the sparse spatial information and rich temporal cues from asynchronous events remains a challenging endeavor. To this end, we propose a novel event-based monocular depth estimator with recurrent transformers, namely EReFormer, which is the first pure transformer with a recursive mechanism to process continuous event streams. Technically, for spatial modeling, a novel transformer-based encoder-decoder with a spatial transformer fusion module is presented, having better global context information modeling capabilities than CNN-based methods. For temporal modeling, we design a gate recurrent vision transformer unit that introduces a recursive mechanism into transformers, improving temporal modeling capabilities while alleviating the expensive GPU memory cost. The experimental results show that our EReFormer outperforms state-of-the-art methods by a margin on both synthetic and real-world datasets. We hope that our work will attract further research to develop stunning transformers in the event-based vision community. Our open-source code can be found in the supplemental material.
Recently, Bird's-Eye-View (BEV) representation has gained increasing attention in multi-view 3D object detection, which has demonstrated promising applications in autonomous driving. Although multi-view camera systems can be deployed at low cost, the lack of depth information makes current approaches adopt large models for good performance. Therefore, it is essential to improve the efficiency of BEV 3D object detection. Knowledge Distillation (KD) is one of the most practical techniques to train efficient yet accurate models. However, BEV KD is still under-explored to the best of our knowledge. Different from image classification tasks, BEV 3D object detection approaches are more complicated and consist of several components. In this paper, we propose a unified framework named BEV-LGKD to transfer the knowledge in the teacher-student manner. However, directly applying the teacher-student paradigm to BEV features fails to achieve satisfying results due to heavy background information in RGB cameras. To solve this problem, we propose to leverage the localization advantage of LiDAR points. Specifically, we transform the LiDAR points to BEV space and generate the foreground mask and view-dependent mask for the teacher-student paradigm. It is to be noted that our method only uses LiDAR points to guide the KD between RGB models. As the quality of depth estimation is crucial for BEV perception, we further introduce depth distillation to our framework. Our unified framework is simple yet effective and achieves a significant performance boost. Code will be released.