arXiv subjects

Taigo Sakai

Publications and source records attributed to Taigo Sakai.

5 recordsLinked to original sources

arXiv2026

NeuroGuard: Neural Gradient Update Aware of Representation Damage

Long-tailed class-incremental learning (LT-CIL) must learn new classes from imbalanced streams while retaining old classes. Existing methods mainly change replay, classifiers, or losses. We study a different factor, namely how strongly the feature representation should be updated at each task boundary. We propose NeuroGuard, an update-control method added to DGR, a replay-based LT-CIL baseline, without adding learnable parameters. NeuroGuard preserves DGR's replay memory, classifier, and set of loss terms. Adaptive Gradient Scaling (AGS) converts teacher uncertainty into one task-wise gradient scale. Confidence-Ranked Knowledge Distillation Reweighting (CRK) gives larger knowledge-distillation weights to replay samples that the teacher predicts less decisively. Fragility-Blended Entropy Gate (FBE) adds old-memory leakage to the scale decision. Across five LT-CIL settings, NeuroGuard improves over DGR in every setting. In the four main benchmark comparisons, it achieves the best task-agnostic accuracy among the compared methods. The gains extend to both old- and new-class accuracy, while medium-frequency accuracy improves consistently across all five settings. Controlled comparisons show that the gain does not come from generic gradient suppression: AGS outperforms a matched fixed-scale control in all five settings, demonstrating that boundary-specific scaling is more effective than applying the same average scale throughout learning.

cs.CV↗

arXiv2026

Dynamic Distillation and Gradient Consistency for Robust Long-Tailed Incremental Learning

The task of Long-tailed Class Incremental Learning (LT-CIL) addresses the sequential learning of new classes from datasets with imbalanced class distributions. This scenario intensifies the fundamental problem of catastrophic forgetting, inherent to continual learning, with the dual challenges of under-learning minority classes and overfitting majority classes. To tackle these combined issues, this paper proposes two main techniques. First, we introduce gradient consistency regularization, which leverages the moving average of gradients to suppress abrupt fluctuations and stabilize the training process. Second, we dynamically adjust the weight of the distillation loss by measuring the degree of class imbalance with normalized entropy. This adaptive weighting establishes an optimal balance between retaining old knowledge and acquiring new information. Experiments on the CIFAR-100-LT, ImageNetSubset-LT, and Food101-LT benchmarks show that our method achieves consistent accuracy improvements of up to 5.0\%. Furthermore, we demonstrate dramatic gains in the challenging 'In-ordered' setting, where tasks progress from majority to minority classes, highlighting our method's robustness in mitigating forgetting under unfavorable learning dynamics. This enhanced performance is achieved without a significant increase in computational overhead, demonstrating the practicality of our framework.

cs.CV↗

arXiv2025

ATLASFusion: Aggregation Tracking with Location-Aware Sparse Fusion for Robust Spatio-Temporal Multi-View Pedestrian Tracking

For multimedia spatial intelligence through time, multi-view multi-object tracking (MVMOT) suffers from persistent challenges in maintaining consistent object identities across different camera views, leading to tracking inaccuracies. A key source of these errors in modern methods is the distortion of feature representations when projecting from multiple views into a unified Bird's-Eye-View (BEV) space. This projection often creates non-uniform feature densities, harming the reliability of the fused representation. To address this, we present ATLASFusion, a reliability-aware sparse BEV fusion framework built on three complementary techniques: a sparse perspective transform that projects only valid feature points to prevent interpolation artifacts, density-aware weighted aggregation that assigns higher confidence to spatially reliable regions, and per-view BEV supervision that supervises each camera's BEV features independently before fusion. Experiments on the WildTrack and MultiViewX benchmarks demonstrated improvements in IDF1, MODP, and robustness over the baseline. ATLASFusion achieved a 95.9\% IDF1 tracking score on WildTrack, the highest among the compared methods and improved the localization precision (MODP) from 75.0\% to 89.2\% on MultiViewX. ATLASFusion also exhibited strong robustness under calibration noise. When high-magnitude noise was injected, TrackTacular failed entirely at 0.0\% MODA, whereas ATLASFusion retained 40.1\% MODA. When the input resolution was reduced by half, MVTr failed entirely and TrackTacular degraded by 2.7\% MODA, while ATLASFusion sustained 92.5\% MODA with only a 1.1\% decrease. These gains were achieved with negligible computational overhead.

cs.CV↗

arXiv2025

Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training

In conventional deep learning, the number of neurons typically remains fixed during training. However, insights from biology suggest that the human hippocampus undergoes continuous neuron generation and pruning of neurons over the course of learning, implying that a flexible allocation of capacity can contribute to enhance performance. Real-world datasets often exhibit class imbalance situations where certain classes have far fewer samples than others, leading to significantly reduce recognition accuracy for minority classes when relying on fixed size networks.To address the challenge, we propose a method that periodically adds and removes neurons during training, thereby boosting representational power for minority classes. By retaining critical features learned from majority classes while selectively increasing neurons for underrepresented classes, our approach dynamically adjusts capacity during training. Importantly, while the number of neurons changes throughout training, the final network size and structure remain unchanged, ensuring efficiency and compatibility with deployment.Furthermore, by experiments on three different datasets and five representative models, we demonstrate that the proposed method outperforms fixed size networks and shows even greater accuracy when combined with other imbalance-handling techniques. Our results underscore the effectiveness of dynamic, biologically inspired network designs in improving performance on class-imbalanced data.

cs.LG↗

arXiv2024

Growing Deep Neural Network Considering with Similarity between Neurons

Deep learning has excelled in image recognition tasks through neural networks inspired by the human brain. However, the necessity for large models to improve prediction accuracy introduces significant computational demands and extended training times.Conventional methods such as fine-tuning, knowledge distillation, and pruning have the limitations like potential accuracy drops. Drawing inspiration from human neurogenesis, where neuron formation continues into adulthood, we explore a novel approach of progressively increasing neuron numbers in compact models during training phases, thereby managing computational costs effectively. We propose a method that reduces feature extraction biases and neuronal redundancy by introducing constraints based on neuron similarity distributions. This approach not only fosters efficient learning in new neurons but also enhances feature extraction relevancy for given tasks. Results on CIFAR-10 and CIFAR-100 datasets demonstrated accuracy improvement, and our method pays more attention to whole object to be classified in comparison with conventional method through Grad-CAM visualizations. These results suggest that our method's potential to decision-making processes.

cs.CV↗