Developing lightweight architectures for optical remote sensing image salient object detection (ORSI-SOD) is essential to enable real-time interpretation of ORSI scenes on resource-constrained satellite platforms. Existing lightweight ORSI-SOD methods leverage lightweight encoders and carefully designed modules to enhance efficiency while maintaining performance. However, these methods often rely on intricate multistage feature aggregation strategies to mitigate background interference and enhance the feature response of salient objects, inevitably compromising the accuracy-efficiency balance. To address this issue, we propose the multiscale difference excitation network (MSDEN), a novel lightweight ORSI-SOD architecture that optimizes the accuracy-efficiency trade-off. Our approach first incorporates the multiscale difference excitation guidance module (MDEGM), which explicitly models local boundary cues and mitigates the suppression of object features caused by redundant backgrounds. Additionally, we employ the compact spatial feature fusion module (CSFM) to capture long-range contextual information, facilitating the refinement of salient object representations across diverse scales. We conduct extensive experiments on three public benchmark datasets, demonstrating that the proposed MSDEN substantially narrows the performance gap between lightweight models and recent state-of-the-art ORSI-SOD methods. It achieves the S-alpha of 0.9303 in the EORSSD dataset, with only 2.7M parameters and 1.0G FLOPs for 288 & times;288 inputs.

This article proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolution. It explores the broad "middle spectrum" area between channel pruning and conventional grouped convolution. Compared with channel pruning, MSGC can retain most of the information from the input feature maps due to the group mechanism; compared with grouped convolution, MSGC benefits from the learnability, the core of channel pruning, for constructing its group topology, leading to better channel division. The middle spectrum area is unfolded along four dimensions: groupwise, layerwise, samplewise, and attentionwise, making it possible to reveal more powerful and interpretable structures. As a result, the proposed module acts as a booster that can reduce the computational cost of the host backbones for general image recognition with even improved predictive accuracy. For example, in the experiments on the ImageNet dataset for image classification, MSGC can reduce the multiply-accumulates (MACs) of ResNet-18 and ResNet-50 by half but still increase the Top-1 accuracy by more than 1%. With a 35% reduction of MACs, MSGC can also increase the Top-1 accuracy of the MobileNetV2 backbone. Results on the MS COCO dataset for object detection show similar observations. Our code and trained models are available at https://github.com/hellozhuo/msgc.

This paper addresses the challenge of deploying salient object detection (SOD) on resource-constrained devices with real-time performance. While recent advances in deep neural networks have improved SOD, existing top-leading models are computationally expensive. We propose an efficient network design that combines traditional wisdom on SOD and the representation power of modern CNNs. Like biologically-inspired classical SOD methods relying on computing contrast cues to determine saliency of image regions, our model leverages Pixel Difference Convolutions (PDCs) to encode the feature contrasts. Differently, PDCs are incorporated in a CNN architecture so that the valuable contrast cues are extracted from rich feature maps. For efficiency, we introduce a difference convolution reparameterization (DCR) strategy that embeds PDCs into standard convolutions, eliminating computation and parameters at inference. Additionally, we introduce SpatioTemporal Difference Convolution (STDC) for video SOD, enhancing the standard 3D convolution with spatiotemporal contrast capture. Our models, SDNet for image SOD and STDNet for video SOD, achieve significant improvements in efficiency-accuracy trade-offs. On a Jetson Orin device, our models with $< $< 1M parameters operate at 46 FPS and 150 FPS on streamed images and videos, surpassing the second-best lightweight models in our experiments by more than $2\times$2× and $3\times$3× in speed with superior accuracy.

Salient object detection in optical remote sensing images (ORSIs-SOD) often relies on leveraging pretrained knowledge from natural images to achieve high accuracy with limited training data. Traditional methods typically employ vision backbones [e.g., convolutional neural networks (CNNs) or vision transformers (ViTs)] pretrained on ImageNet to extract features from ORSI scenes. However, these backbones exhibit limited generalization across diverse scenarios compared to recent vision foundation models. To this end, we propose ORSI-segment anything model (SAM), a novel ORSI-SOD framework based on the SAM, leveraging its superior generalization capabilities to achieve an exceptional efficiency-accuracy tradeoff. Specifically, ORSI-SAM adopts lightweight SAM as the backbone, effectively reducing parameter size and computational overhead to enable efficient deployment on satellite devices while retaining the rich knowledge learned from large-scale natural image datasets. To mitigate the impact of unavailable prompts in ORSI-SOD on the prediction capability of the SAM decoder, we introduce a hierarchical interaction prompt generator (HIPG), which aggregates hierarchical features and generates mask prompts tailored for salient objects to guide the decoder in producing high-quality saliency maps. Furthermore, to address the recognition challenges caused by the inherent characteristics of ORSIs, we propose a semantic-aware refinement decoder (SARD). SARD integrates structural details from low-level features to enrich fine-grained object information while leveraging high-level features to suppress redundant interference in shallow layers, thereby improving the detailed information in the predicted saliency map. ORSI-SAM is the first work to explore the accuracy-efficiency tradeoffs for ORSI-SOD based on SAM architecture. Extensive experiments on benchmark datasets show that ORSI-SAM achieves superior performance compared to recent state-of-the-art methods with 12.2 M parameters and 8.9 G FLOPs.

Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML), as it necessitates the Incremental Learning (IL) of new classes from sparsely labeled training samples without forgetting previous knowledge. While this field has seen recent progress, it remains an active exploration area. This paper aims to provide a comprehensive and systematic review of FSCIL. In our in-depth examination, we delve into various facets of FSCIL, encompassing the problem definition, the discussion of the primary challenges of unreliable empirical risk minimization and the stability-plasticity dilemma, general schemes, and relevant problems of IL and Few-shot Learning (FSL). Besides, we offer an overview of benchmark datasets and evaluation metrics. Furthermore, we introduce the Few-shot Class-incremental Classification (FSCIC) methods from data-based, structure-based, and optimization-based approaches and the Few-shot Class-incremental Object Detection (FSCIOD) methods from anchor-free and anchor-based approaches. Beyond these, we present several promising research directions within FSCIL that merit further investigation.

Moving object detection in satellite videos (SVMOD) is a challenging task due to the extremely dim and small target characteristics. Current learning-based methods extract spatio-temporal information from multi-frame dense representation with labor-intensive manual labels to tackle SVMOD, which needs high annotation costs and contains tremendous computational redundancy due to the severe imbalance between foreground and background regions. In this paper, we propose a highly efficient unsupervised framework for SVMOD. Specifically, we propose a generic unsupervised framework for SVMOD, in which pseudo labels generated by a traditional method can evolve with the training process to promote detection performance. Furthermore, we propose a highly efficient and effective sparse convolutional anchor-free detection network by sampling the dense multi-frame image form into a sparse spatio-temporal point cloud representation and skipping the redundant computation on background regions. Coping these two designs, we can achieve both high efficiency (label and computation efficiency) and effectiveness. Extensive experiments demonstrate that our method can not only process 98.8 frames per second on 1024 ×1024 images but also achieve state-of-the-art performance.

Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment. As a powerful AI strategy, deep learning techniques have extensively promoted the development of visual speech learning. Over the past five years, numerous deep learning based methods have been proposed to address various problems in this area, especially automatic visual speech recognition and generation. To push forward future research on visual speech, this paper will present a comprehensive review of recent progress in deep learning methods on visual speech analysis. We cover different aspects of visual speech, including fundamental problems, challenges, benchmark datasets, a taxonomy of existing methods, and state-of-the-art performance. Besides, we also identify gaps in current research and discuss inspiring future research directions.

Undoubtedly, Deep Neural Networks (DNNs), from AlexNet to ResNet to Transformer, have sparked revolutionary advancements in diverse computer vision tasks. The scale of DNNs has grown exponentially due to the rapid development of computational resources. Despite the tremendous success, DNNs typically depend on massive amounts of training data (especially the recent various foundation models) to achieve high performance and are brittle in that their performance can degrade severely with small changes in their operating environment. Generally, collecting massive-scale training datasets is costly or even infeasible, as for certain fields, only very limited or no examples at all can be gathered. Nevertheless, collecting, labeling, and vetting massive amounts of practical training data is certainly difficult and expensive, as it requires the painstaking efforts of experienced human annotators or experts, and in many cases, prohibitively costly or impossible due to some reason, such as privacy, safety or ethic issues.

The articles in this special issue cover four major subfields in affective computing, namely affect analysis, affect synthesis, applications, and ethics.

Lip reading is the task of decoding text from speakers' mouth movements. Numerous deep learning-based methods have been proposed to address this task. However, these existing deep lip reading models suffer from poor generalization due to overfitting the training data. To resolve this issue, we present a novel learning paradigm that aims to improve the interpretability and generalization of lip reading models. In specific, a Variational Temporal Mask (VTM) module is customized to automatically analyze the importance of frame-level features. Furthermore, the prediction consistency constraints of global information and local temporal important features are introduced to strengthen the model generalization. We evaluate the novel learning paradigm with multiple lip reading baseline models on the LRW and LRW-1000 datasets. Experiments show that the proposed framework significantly improves the generalization performance and interpretability of lip reading models.

LBP is a successful hand-crafted feature descriptor in computer vision. However, in the deep learning era, deep neural networks, especially convolutional neural networks (CNNs) can automatically learn powerful task-aware features that are more discriminative and of higher representational capacity. To some extent, such hand-crafted features can be safely ignored when designing deep computer vision models. Nevertheless, due to LBP's preferable properties in visual representation learning, an interesting topic has arisen to explore the value of LBP in enhancing modern deep models in terms of efficiency, memory consumption, and predictive performance. In this paper, we provide a comprehensive review on such efforts which aims to incorporate the LBP mechanism into the design of CNN modules to make deep models stronger. In retrospect of what has been achieved so far, the paper discusses open challenges and directions for future research.

Recently, there have been tremendous efforts in developing lightweight Deep Neural Networks (DNNs) with satisfactory accuracy, which can enable the ubiquitous deployment of DNNs in edge devices. The core challenge of developing compact and efficient DNNs lies in how to balance the competing goals of achieving high accuracy and high efficiency. In this paper we propose two novel types of convolutions, dubbed Pixel Difference Convolution (PDC) and Binary PDC (Bi-PDC) which enjoy the following benefits: capturing higher-order local differential information, computationally efficient, and able to be integrated with existing DNNs. With PDC and Bi-PDC, we further present two lightweight deep networks named Pixel Difference Networks (PiDiNet) and Binary PiDiNet (Bi-PiDiNet) respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition. Extensive experiments on popular datasets (BSDS500, ImageNet, LFW, YTF, etc.) show that PiDiNet and Bi-PiDiNet achieve the best accuracy-efficiency trade-off. For edge detection, PiDiNet is the first network that can be trained without ImageNet, and can achieve the human-level performance on BSDS500 at 100 FPS and with <1 M parameters. For object recognition, among existing Binary DNNs, Bi-PiDiNet achieves the best accuracy and a nearly 2x reduction of computational cost on ResNet18.

Artificial intelligence (AI) has become a part of everyday conversation and our lives. It is considered as the new electricity that is revolutionizing the world. AI is heavily invested in both industry and academy. However, there is also a lot of hype in the current AI debate. AI based on so-called deep learning has achieved impressive results in many problems, but its limits are already visible. AI has been under research since the 1940s, and the industry has seen many ups and downs due to over-expectations and related disappointments that have followed. The purpose of this book is to give a realistic picture of AI, its history, its potential and limitations. We believe that AI is a helper, not a ruler of humans. We begin by describing what AI is and how it has evolved over the decades. After fundamentals, we explain the importance of massive data for the current mainstream of artificial intelligence. The most common representations for AI, methods, and machine learning are covered. In addition, the main application areas are introduced. Computer vision has been central to the development of AI. The book provides a general introduction to computer vision, and includes an exposure to the results and applications of our own research. Emotions are central to human intelligence, but little use has been made in AI. We present the basics of emotional intelligence and our own research on the topic. We discuss super-intelligence that transcends human understanding, explaining why such achievement seems impossible on the basis of present knowledge,and how AI could be improved. Finally, a summary is made of the current state of AI and what to do in the future. In the appendix, we look at the development of AI education, especially from the perspective of contents at our own university.

Binary neural networks (BNNs) constrain weights and activations to +1 or -1 with limited storage and computational cost, which is hardware-friendly for portable devices. Recently, BNNs have achieved remarkable progress and been adopted into various fields. However, the performance of BNNs is sensitive to activation distribution. The existing BNNs utilized the Sign function with predefined or learned static thresholds to binarize activations. This process limits representation capacity of BNNs since different samples may adapt to unequal thresholds. To address this problem, we propose a dynamic BNN (DyBNN) incorporating dynamic learnable channel-wise thresholds of Sign function and shift parameters of PReLU. The method aggregates the global information into the hyper function and effectively increases the feature expression ability. The experimental results prove that our method is an effective and straightforward way to reduce information loss and enhance performance of BNNs. The DyBNN based on two backbones of ReActNet (MobileNetV1 and ResNet18) achieve 71.2% and 67.4% top1-accuracy on ImageNet dataset, outperforming baselines by a large margin (i.e., 1.8% and 1.5% respectively).

Developing lightweight Deep Convolutional Neural Networks (DCNNs) and Vision Transformers (ViTs) has become one of the focuses in vision research since the low computational cost is essential for deploying vision models on edge devices. Recently, researchers have explored highly computational efficient Binary Neural Networks (BNNs) by binarizing weights and activations of Full-precision Neural Networks. However, the binarization process leads to an enormous accuracy gap between BNN and its full-precision version. One of the primary reasons is that the Sign function with predefined or learned static thresholds limits the representation capacity of binarized architectures since single-threshold binarization fails to utilize activation distributions. To overcome this issue, we introduce the statistics of channel information into explicit thresholds learning for the Sign Function dubbed DySign to generate various thresholds based on input distribution. Our DySign is a straightforward method to reduce information loss and boost the representative capacity of BNNs, which can be flexibly applied to both DCNNs and ViTs (i.e., DyBCNN and DyBinaryCCT) to achieve promising performance improvement. As shown in our extensive experiments. For DCNNs, DyBCNNs based on two backbones (MobileNetV1 and ResNet18) achieve 71.2% and 67.4% top1-accuracy on ImageNet dataset, outperforming baselines by a large margin (i.e., 1.8% and 1.5% respectively). For ViTs, DyBinaryCCT presents the superiority of the convolutional embedding layer in fully binarized ViTs and achieves 56.1% on the ImageNet dataset, which is nearly 9% higher than the baseline.

Unsupervised domain adaptation (UDA) aims at learning a classifier for an unlabeled target domain by transferring knowledge from a labeled source domain with a related but different distribution. Most existing approaches learn domain-invariant features by adapting the entire information of the images. However, forcing adaptation of domain-specific variations undermines the effectiveness of the learned features. To address this problem, we propose a novel, yet elegant module, called the deep ladder-suppression network (DLSN), which is designed to better learn the cross-domain shared content by suppressing domain-specific variations. Our proposed DLSN is an autoencoder with lateral connections from the encoder to the decoder. By this design, the domain-specific details, which are only necessary for reconstructing the unlabeled target data, are directly fed to the decoder to complete the reconstruction task, relieving the pressure of learning domain-specific variations at the later layers of the shared encoder. As a result, DLSN allows the shared encoder to focus on learning cross-domain shared content and ignores the domain-specific variations. Notably, the proposed DLSN can be used as a standard module to be integrated with various existing UDA frameworks to further boost performance. Without whistles and bells, extensive experimental results on four gold-standard domain adaptation datasets, for example: 1) Digits; 2) Office31; 3) Office-Home; and 4) VisDA-C, demonstrate that the proposed DLSN can consistently and significantly improve the performance of various popular UDA frameworks.

Efficiency and robustness are increasingly needed for applications on 3D point clouds, with the ubiquitous use of edge devices in scenarios like autonomous driving and robotics, which often demand real-time and reliable responses. The paper tackles the challenge by designing a general framework to construct 3D learning architectures with SO(3) equivariance and network binarization. However, a naive combination of equivariant networks and binarization either causes sub-optimal computational efficiency or geometric ambiguity. We propose to locate both scalar and vector features in our networks to avoid both cases. Precisely, the presence of scalar features makes the major part of the network binarizable, while vector features serve to retain rich structural information and ensure SO(3) equivariance. The proposed approach can be applied to general backbones like PointNet and DGCNN. Meanwhile, experiments on ModelNet40, ShapeNet, and the real-world dataset ScanObjectNN, demonstrated that the method achieves a great trade-off between efficiency, rotation robustness, and accuracy. The codes are available at https://github.com/zhuoinoulu/svnet.

Recently, deep Convolutional Neural Networks (CNNs) can achieve human-level performance in edge detection with the rich and abstract edge representation capacities. However, the high performance of CNN based edge detection is achieved with a large pretrained CNN backbone, which is memory and energy consuming. In addition, it is surprising that the previous wisdom from the traditional edge detectors, such as Canny, Sobel, and LBP are rarely investigated in the rapid-developing deep learning era. To address these issues, we propose a simple, lightweight yet effective architecture named Pixel Difference Network (PiDiNet) for efficient edge detection. PiDiNet adopts novel pixel difference convolutions that integrate the traditional edge detection operators into the popular convolutional operations in modern CNNs for enhanced performance on the task, which enjoys the best of both worlds. Extensive experiments on BSDS500, NYUD, and Multicue are provided to demonstrate its effectiveness, and its high training and inference efficiency. Surprisingly, when training from scratch with only the BSDS500 and VOC datasets, PiDiNet can surpass the recorded result of human perception (0.807 vs. 0.803 in ODS F-measure) on the BSDS500 dataset with 100 FPS and less than 1M parameters. A faster version of PiDiNet with less than 0.1M parameters can still achieve comparable performance among state of the arts with 200 FPS. Results on the NYUD and Multicue datasets show similar observations. The codes are available at https://github.com/zhuoinoulu/pidinet.

The goal of this work is to learn discriminative visual representations for lip reading without access to manual text annotation. Recent advances in cross-modal self-supervised learning have shown that the corresponding audio can serve as a supervisory signal to learn effective visual representations for lip reading. However, existing methods only exploit the natural synchronization of the video and the corresponding audio. We find that both video and audio are actually composed of speech-related information, identity-related information, and modal information. To make the visual representations (i) more discriminative for lip reading and (ii) indiscriminate with respect to the identities and modals, we propose a novel self-supervised learning framework called Adversarial Dual-Contrast Self-Supervised Learning (ADC-SSL), to go beyond previous methods by explicitly forcing the visual representations disentangled from speech-unrelated information. Experimental results clearly show that the proposed method outperforms state-of-the-art cross-modal self-supervised baselines by a large margin. Besides, ADC-SSL can outperform its supervised counterpart without any finetune.