With the widespread deployment of dashcams and advancements in computer vision, developing accident prediction models from the dashcam perspective has become critical for proactive safety interventions. However, two key challenges persist: modeling feature-level interactions among traffic participants (often occluded in dashcam views) and capturing complex, asynchronous multi-temporal behavioral cues preceding accidents. To deal with these two challenges, a Multi-scale Feature Interaction Network (MsFIN) is proposed for early-stage accident anticipation from dashcam videos. MsFIN has three layers for multi-scale feature aggregation, temporal feature processing and multi-scale feature post fusion, respectively. For multi-scale feature aggregation, a Multi-scale Module is designed to extract scene representations at short-term, mid-term and long-term temporal scales. Meanwhile, the Transformer architecture is leveraged to facilitate comprehensive feature interactions. Temporal feature processing captures the sequential evolution of scene and object features under causal constraints. In the multi-scale feature post fusion stage, the network fuses scene and object features across multiple temporal scales to generate a comprehensive risk representation. Experiments on DAD and DADA datasets show that MsFIN significantly outperforms state-of-the-art models with single-scale feature extraction in both prediction correctness and earliness. Ablation studies validate the effectiveness of each module in MsFIN, highlighting how the network achieves superior performance through multi-scale feature fusion and contextual interaction modeling.

WSI (bag) while only a slide label is given.

Video object detection has made significant progress in recent years thanks to convolutional neural networks (CNNs) and vision transformers (ViTs). Typically, CNNs excel at capturing local features but struggle to model global representations. Conversely, ViTs are adept at capturing long-range global features but face challenges in representing local feature details. Off-the-shelf video object detection methods solely rely on CNNs or ViTs to conduct feature aggregation, which hampers their capability to simultaneously leverage global and local information, thereby resulting in limited detection performance. In this paper, we propose a Transformer-GraphFormer Blender Network (TGBFormer) for video object detection, with three key technical improvements to fully exploit the advantages of transformers and graph convolutional networks while compensating for their limitations. First, we develop a spatial-temporal transformer module to aggregate global contextual information, constituting global representations with long-range feature dependencies. Second, we introduce a spatial-temporal GraphFormer module that utilizes local spatial and temporal relationships to aggregate features, generating new local representations that are complementary to the transformer outputs. Third, we design a global-local feature blender module to adaptively couple transformer-based global representations and GraphFormer-based local representations. Extensive experiments demonstrate that our TGBFormer establishes new state-of-the-art results on the ImageNet VID dataset. Particularly, our TGBFormer achieves 86.5% mAP while running at around 41.0 FPS on a single Tesla A100 GPU.

Accurate airway anatomical labeling is crucial for clinicians to identify and navigate complex bronchial structures during bronchoscopy. Automatic airway anatomical labeling is challenging due to significant individual variability and anatomical variations. Previous methods are prone to generate inconsistent predictions, which is harmful for preoperative planning and intraoperative navigation. This paper aims to address these challenges by proposing a novel method that enhances topological consistency and improves the detection of abnormal airway branches. We propose a novel approach incorporating two modules: the Soft Subtree Consistency (SSC) and the Abnormal Branch Saliency (ABS). The SSC module constructs a soft subtree to capture clinically relevant topological relationships, allowing for flexible feature aggregation within and across subtrees. The ABS module facilitates the interaction between node features and prototypes to distinguish abnormal branches, preventing the erroneous aggregation of features between normal and abnormal nodes. Evaluated on a challenging dataset characterized by severe airway distortion and atrophy, our method achieves superior performance compared to state-of-the-art approaches. Specifically, it attains a 91.4% accuracy at the segmental level and an 83.7% accuracy at the subsegmental level, representing a 1.4% increase in subsegmental accuracy and a 3.1% increase in topological consistency. Notably, the method demonstrates reliable performance in cases with disease-induced airway deformities, ensuring consistent and accurate labeling.

Enabling efficient and accurate deep neural network (DNN) inference on microcontrollers is non-trivial due to the constrained on-chip resources. Current methodologies primarily focus on compressing larger models yet at the expense of model accuracy. In this paper, we rethink the problem from the inverse perspective by constructing small/weak models directly and improving their accuracy. Thus, we introduce DiTMoS, a novel DNN training and inference framework with a selector-classifiers architecture, where the selector routes each input sample to the appropriate classifier for classification. DiTMoS is grounded on a key insight: a composition of weak models can exhibit high diversity and the union of them can significantly boost the accuracy upper bound. To approach the upper bound, DiTMoS introduces three strategies including diverse training data splitting to increase the classifiers' diversity, adversarial selector-classifiers training to ensure synergistic interactions thereby maximizing their complementarity, and heterogeneous feature aggregation to improve the capacity of classifiers. We further propose a network slicing technique to alleviate the extra memory overhead incurred by feature aggregation. We deploy DiTMoS on the Neucleo STM32F767ZI board and evaluate it based on three time-series datasets for human activity recognition, keywords spotting, and emotion recognition, respectively. The experiment results manifest that: (a) DiTMoS achieves up to 13.4% accuracy improvement compared to the best baseline; (b) network slicing almost completely eliminates the memory overhead incurred by feature aggregation with a marginal increase of latency.

This study addresses the application of deep learning techniques in joint sound signal classification and localization networks. Current state-of-the-art sound source localization deep learning networks lack feature aggregation within their architecture. Feature aggregation enhances model performance by enabling the consolidation of information from different feature scales, thereby improving feature robustness and invariance. This is particularly important in SSL networks, which must differentiate direct and indirect acoustic signals. To address this gap, we adapt feature aggregation techniques from computer vision neural networks to signal detection neural networks. Additionally, we propose the Scale Encoding Network (SEN) for feature aggregation to encode features from various scales, compressing the network for more computationally efficient aggregation. To evaluate the efficacy of feature aggregation in SSL networks, we integrated the following computer vision feature aggregation sub-architectures into a SSL control architecture: Path Aggregation Network (PANet), Weighted Bi-directional Feature Pyramid Network (BiFPN), and SEN. These sub-architectures were evaluated using two metrics for signal classification and two metrics for direction-of-arrival regression. PANet and BiFPN are established aggregators in computer vision models, while the proposed SEN is a more compact aggregator. The results suggest that models incorporating feature aggregations outperformed the control model, the Sound Event Localization and Detection network (SELDnet), in both sound signal classification and localization. The feature aggregation techniques enhance the performance of sound detection neural networks, particularly in direction-of-arrival regression.

Despite the advances in the field of Face Recognition (FR), the precision of these methods is not yet sufficient. To improve the FR performance, this paper proposes a technique to aggregate the outputs of two state-of-the-art (SOTA) deep FR models, namely ArcFace and AdaFace. In our approach, we leverage the transformer attention mechanism to exploit the relationship between different parts of two feature maps. By doing so, we aim to enhance the overall discriminative power of the FR system. One of the challenges in feature aggregation is the effective modeling of both local and global dependencies. Conventional transformers are known for their ability to capture long-range dependencies, but they often struggle with modeling local dependencies accurately. To address this limitation, we augment the self-attention mechanism to capture both local and global dependencies effectively. This allows our model to take advantage of the overlapping receptive fields present in corresponding locations of the feature maps. However, fusing two feature maps from different FR models might introduce redundancies to the face embedding. Since these models often share identical backbone architectures, the resulting feature maps may contain overlapping information, which can mislead the training process. To overcome this problem, we leverage the principle of Information Bottleneck to obtain a maximally informative facial representation. This ensures that the aggregated features retain the most relevant and discriminative information while minimizing redundant or misleading details. To evaluate the effectiveness of our proposed method, we conducted experiments on popular benchmarks and compared our results with state-of-the-art algorithms. The consistent improvement we observed in these benchmarks demonstrates the efficacy of our approach in enhancing FR performance.

Camouflaged object detection (COD) is the challenging task of identifying camouflaged objects visually blended into surroundings. Albeit achieving remarkable success, existing COD detectors still struggle to obtain precise results in some challenging cases. To handle this problem, we draw inspiration from the prey-vs-predator game that leads preys to develop better camouflage and predators to acquire more acute vision systems and develop algorithms from both the prey side and the predator side. On the prey side, we propose an adversarial training framework, Camouflageator, which introduces an auxiliary generator to generate more camouflaged objects that are harder for a COD method to detect. Camouflageator trains the generator and detector in an adversarial way such that the enhanced auxiliary generator helps produce a stronger detector. On the predator side, we introduce a novel COD method, called Internal Coherence and Edge Guidance (ICEG), which introduces a camouflaged feature coherence module to excavate the internal coherence of camouflaged objects, striving to obtain more complete segmentation results. Additionally, ICEG proposes a novel edge-guided separated calibration module to remove false predictions to avoid obtaining ambiguous boundaries. Extensive experiments show that ICEG outperforms existing COD detectors and Camouflageator is flexible to improve various COD detectors, including ICEG, which brings state-of-the-art COD performance.

Abstract--Deep models have achieved significant process on single image super-resolution (SISR) tasks, in particular large models with large kernel (3 3 or more). However, the heavy computational footprint of such models prevents their deployment in real-time, resource-constrained environments. Conversely, 1 1 convolutions bring substantial computational efficiency, but struggle with aggregating local spatial representations, an essential capability to SISR models. In response to this dichotomy, we propose to harmonize the merits of both 3 3 and 1 1 kernels, and exploit a great potential for lightweight SISR tasks. Specifically, we propose a simple yet effective fully 1 1 convolutional network, named Shift-Conv-based Network (SCNet). By incorporating a parameter-free spatial-shift operation, it equips the fully 1 1 convolutional network with powerful representation capability while impressive computational efficiency. The 3 3 convolution operation is the most widely used Single image super-resolution (SISR) aims at reconstructing operation in CNN-based models due to its advantageous in a high-resolution (HR) image from its corresponding balancing the model capacity and computational cost.