Adaptive ensemble perception tracking

Multiple-instance ensemble for construction of deep heterogeneous committees for high-dimensional low-sample-size data

Deep ensemble learning, where we combine knowledge learned from multiple individual neural networks, has been widely adopted to improve the performance of neural networks in deep learning. This field can be encompassed by committee learning, which includes the construction of neural network cascades. This study focuses on the high-dimensional low-sample-size (HDLS) domain and introduces multiple instance ensemble (MIE) as a novel stacking method for ensembles and cascades. In this study, our proposed approach reformulates the ensemble learning process as a multiple-instance learning problem. We utilise the multiple-instance learning solution of pooling operations to associate feature representations of base neural networks into joint representations as a method of stacking. This study explores various attention mechanisms and proposes two novel committee learning strategies with MIE. In addition, we utilise the capability of MIE to generate pseudo-base neural networks to provide a proof-of-concept for a "growing" neural network cascade that is unbounded by the number of base neural networks. We have shown that our approach provides (1) a class of alternative ensemble methods that performs comparably with various stacking ensemble methods and (2) a novel method for the generation of high-performing "growing" cascades. The approach has also been verified across multiple HDLS datasets, achieving high performance for binary classification tasks in the low-sample size regime.

Learning dynamic spatial-temporal regularized correlation filter tracking with response deviation suppression via multi-feature fusion

Visual object tracking (VOT) for intelligent video surveillance has attracted great attention in the current research community, thanks to advances in computer vision and camera technology. Meanwhile, discriminative correlation filter (DCF) trackers garnered significant interest owing to their high accuracy and low computing cost. Many researchers have introduced spatial and temporal regularization into the DCF framework to achieve a more robust appearance model and further improve tracking performance. However, these algorithms typically set fixed spatial and temporal regularization parameters, which limit flexibility and adaptability under cluttered and challenging scenarios. To overcome these problems, in this work, we propose a new dynamic spatial-temporal regularization for the DCF tracking model that emphasizes the filter to concentrate on more reliable regions during the training stage. Furthermore, we present a response deviation-suppressed regularization term for responses to encourage temporal consistency and avoid model degradation by suppressing relative response changes between two consecutive frames. Moreover, we introduce a multi-memory tracking framework to exploit various features and each memory contributes to tracking the target across all frames. Significant experiments on the OTB-2013, OTB-2015, TC-128, UAV-123, UAVDT, and DTB-70 datasets have revealed that the performance thereof outperformed many state-of-the-art trackers based on DCF and deep-based frameworks in terms of tracking accuracy and tracking success rate.

IASA: An IoU-aware tracker with adaptive sample assignment

Most of existing trackers develop tracking in a tracking head network, which is composed of classification branch and regression branch. However, they lack a meaningful exploration of how to define positive and negative samples during training, which can significantly affect tracking performance. Furthermore, they cannot provide a reliable ranking by using classification scores or a combination of classification and regression scores to obtain candidate locations. To address these issues, we propose an intersection over union (IoU) aware tracker with adaptive sample assignment (IASA). The IASA introduces an IoU-aware classification score to achieve a more accurate ranking for candidate tracking locations. We also propose a new loss function, IoU-focal loss, to train the anchor-free tracker IASA to predict the classification scores and introduce a star-shaped box feature representation to refine classification features. To explore the actual content of the training samples, we develop an adaptive sample assignment (ASA) strategy to divide the positive and negative samples according to the statistical characteristics of the sample IoUs. By combining these two proposed components, the IASA tracker treats the tracking task as a classification and a regression problem. It directly finds the candidate tracking location in the classification branch and then regresses the four distances from the location to the four sides of the tracking box. Experimental results show that the proposed IASA can achieve state-of-the-art performance on seven public datasets.