Various architectures (such as GoogLeNets, ResNets, and DenseNets) have been proposed. However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters. To handle these challenging issues, we propose Micro-Dense Nets, a novel architecture with global residual learning and local micro-dense aggregations. Specifically, residual learning aims to efficiently retrieve features from different convolutional blocks, while the micro-dense aggregation is able to enhance each block and avoid redundancy of convolutional layers by lessening residual aggregations. Moreover, the proposed micro-dense architecture has two characteristics: pyramidal multi-level feature learning which can widen the deeper layer in a block progressively, and dimension cardinality adaptive convolution which can balance each layer using linearly increasing dimension cardinality. The experimental results over three datasets (i.e., CIFAR-10, CIFAR-100, and ImageNet-1K) demonstrate that the proposed Micro-Dense Net with only 4M parameters can achieve higher classification accuracy than state-of-the-art networks, while being 12.1$\times$ smaller depends on the number of parameters. In addition, our micro-dense block can be integrated with neural architecture search based models to boost their performance, validating the advantage of our architecture. We believe our design and findings will be beneficial to the DNN community.
Technical University of Munich（慕尼黑工业大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Saliency methods interpret the prediction of a neural network by showing the importance of input elements for that prediction. A popular family of saliency methods utilize gradient information. In this work, we empirically show that two approaches for handling the gradient information, namely positive aggregation, and positive propagation, break these methods. Though these methods reflect visually salient information in the input, they do not explain the model prediction anymore as the generated saliency maps are insensitive to the predicted output and are insensitive to model parameter random…
The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation
Nankai University（南开大学）；South China University of Technology（华南理工大学）；Peking University（北京大学）；Henan Institute of Science and Technology（河南科技学院）；MicroBT Electronics Technology Co., Ltd（深圳比特微电子科技有限公司）
From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification
Department of Electrical and Computer Engineering, University of Washington（华盛顿大学电气与计算机工程系）；Applied Physics Laboratory, University of Washington（华盛顿大学应用物理实验室）
Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network's prediction. Gradient-based methods are generally faster than other branches of vision interpretability and independent of human guidance. The performance of CAM-like studies depends on the governing model's layer response, and the influences of the gradients. Typical gradient-oriented CAM studies rely on weighted aggregation for saliency map estimation by projecting the gradient maps into single weight values, which may lead to over generalized saliency map. To address this issue, we …
BiSeNet has been proved to be a popular two-stream network for real-time segmentation. However, its principle of adding an extra path to encode spatial information is time-consuming, and the backbones borrowed from pretrained tasks, e.g., image classification, may be inefficient for image segmentation due to the deficiency of task-specific design. To handle these problems, we propose a novel and efficient structure named Short-Term Dense Concatenate network (STDC network) by removing structure redundancy. Specifically, we gradually reduce the dimension of feature maps and use the aggregation o…
Megvii Inc. (Face++)（旷视科技（Face++））；Shanghai Jiao Tong University（上海交通大学）；Beihang University（北京航空航天大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good as single-stage methods. This work studies this issue. We argue that the current multi-stage methods' unsatisfactory performance comes from the insufficiency in various design choices. We propose several improvements, including the single-stage module design, cross stage feature aggregation, and coarse-to-fine supervision. The resulting method establishes the new state-of-the-ar…
University of Toronto（多伦多大学）；LG AI Research（LG AI研究院）
As an emerging field in Machine Learning, Explainable AI (XAI) has been offering remarkable performance in interpreting the decisions made by Convolutional Neural Networks (CNNs). To achieve visual explanations for CNNs, methods based on class activation mapping and randomized input sampling have gained great popularity. However, the attribution methods based on these techniques provide lower resolution and blurry explanation maps that limit their explanation power. To circumvent this issue, visualization based on various layers is sought. In this work, we collect visualization maps from multi…
Wuhan University（武汉大学）；The University of Hong Kong（香港大学）；Texas A&M University（德克萨斯农工大学）
This paper presents a neural network for robust normal estimation on point clouds, named AdaFit, that can deal with point clouds with noise and density variations. Existing works use a network to learn point-wise weights for weighted least squares surface fitting to estimate the normals, which has difficulty in finding accurate normals in complex regions or containing noisy points. By analyzing the step of weighted least squares surface fitting, we find that it is hard to determine the polynomial order of the fitting surface and the fitting surface is sensitive to outliers. To address these pr…
The Hong Kong University of Science and Technology（香港科技大学）
This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation. Unlike most existing approaches, we establish correspondences directly between frames without re-encoding the mask features for every object, leading to a highly efficient and robust framework. With the correspondences, every node in the current query frame is inferred by aggregating features from the past in an associative fashion. We cast the aggregation process as a voting problem and find that the existing inner-product affinity leads to poor use of memory…
Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective
School of EEE, Nanyang Technological University（南洋理工大学电子工程系）；Department of Civil Engineering, Tsinghua University（清华大学土木工程系）；Dr. B. R. Ambedkar National Institute of Technology, Jalandhar（B.R.阿姆贝卡尔国家理工学院，贾兰德赫）；KTH Royal Institute of Technology（皇家理工学院）；College of AI, Tsinghua University（清华大学人工智能学院）；CCDS, Nanyang Technological University（南洋理工大学CCDS）
Out-Of-Distribution (OOD) detection has received broad attention over the years, aiming to ensure the reliability and safety of deep neural networks (DNNs) in real-world scenarios by rejecting incorrect predictions. However, we notice a discrepancy between the conventional evaluation vs. the essential purpose of OOD detection. On the one hand, the conventional evaluation exclusively considers risks caused by label-space distribution shifts while ignoring the risks from input-space distribution shifts. On the other hand, the conventional evaluation reward detection methods for not rejecting the…
Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba
MICS Thrust at the Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）MICS分支）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））；School of Microelectronics at Southern University of Science and Technology（南方科技大学微电子学院）
Wuhan University（武汉大学）；University of Central Florida（中佛罗里达大学）；Shenzhen University（深圳大学）；National Tsing Hua University（台湾清华大学）
Convolutional neural network (CNN) and Transformer have achieved great success in multimedia applications. However, little effort has been made to effectively and efficiently harmonize these two architectures to satisfy image deraining. This paper aims to unify these two architectures to take advantage of their learning merits for image deraining. In particular, the local connectivity and translation equivariance of CNN and the global aggregation ability of self-attention (SA) in Transformer are fully exploited for specific local context and global structure representations. Based on the obser…
MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding
National University of Defense Technology（国防科技大学）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；ShanghaiTech University（上海科技大学）
