Related papers: AWF: Adaptive Weight Fusion for Enhanced Class Inc…

Composed Image Retrieval (CIR) is a cross-modal task that aims to retrieve target images from large-scale databases using a reference image and a modification text. Most existing methods rely on a single model to perform feature fusion and…

Model fusion research aims to aggregate the knowledge of multiple individual models to enhance performance by combining their weights. In this work, we study the inverse problem: investigating whether model fusion can be used to reduce…

Multi-modality image fusion (MMIF) in adverse weather aims to address the loss of visual information caused by weather-related degradations, providing clearer scene representations. Although less studies have attempted to incorporate…

Recent years have witnessed the increasing application of place recognition in various environments, such as city roads, large buildings, and a mix of indoor and outdoor places. This task, however, still remains challenging due to the…

Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. Oftentimes fine-tuned models are readily available but their training data is not, due to data privacy or intellectual property…

Incremental learning remains a critical challenge in machine learning, as models often struggle with catastrophic forgetting -the tendency to lose previously acquired knowledge when learning new information. These challenges are even more…

The ability to learn and retain a wide variety of tasks is a hallmark of human intelligence that has inspired research in artificial general intelligence. Continual learning approaches provide a significant step towards achieving this goal.…

Class-Incremental Learning (CIL) requires a learning system to learn new classes while retaining previously learned knowledge. However, in real-world scenarios such as autonomous driving, a system trained on urban roads in sunny weather may…

Machine learning models trained on imbalanced datasets often exhibit intersectional biases-systematic errors arising from the interaction of multiple attributes such as object class and environmental conditions. This paper presents a…

Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple…

One of the most popular methods for continual learning with deep neural networks is Elastic Weight Consolidation (EWC), which involves computing the Fisher Information. The exact way in which the Fisher Information is computed is however…

We summarize our TRECVID 2022 Ad-hoc Video Search (AVS) experiments. Our solution is built with two new techniques, namely Lightweight Attentional Feature Fusion (LAFF) for combining diverse visual / textual features and Bidirectional…

Computing-in-Memory (CIM) macros have gained popularity for deep learning acceleration due to their highly parallel computation and low power consumption. However, limited macro size and ADC precision introduce throughput and accuracy…

Federated Learning (FL) endeavors to harness decentralized data while preserving privacy, facing challenges of performance, scalability, and collaboration. Asynchronous Federated Learning (AFL) methods have emerged as promising alternatives…

Quantization techniques commonly reduce the inference costs of neural networks by restricting the precision of weights and activations. Recent studies show that also reducing the precision of the accumulator can further improve hardware…

We investigate a failure mode that arises during the training of reasoning models, where the diversity of generations begins to collapse, leading to suboptimal test-time scaling. Notably, the Pass@1 rate reliably improves during supervised…

Learning robotic tasks in the real world is still highly challenging and effective practical solutions remain to be found. Traditional methods used in this area are imitation learning and reinforcement learning, but they both have…

Complex neural networks require substantial memory to store a large number of synaptic weights. This work introduces WINGs (Automatic Weight Generator for Secure and Storage-Efficient Deep Learning Models), a novel framework that…

Federated Learning (FL) faces major challenges in real-world deployments due to statistical heterogeneity across clients and system heterogeneity arising from resource-constrained devices. While clustering-based approaches mitigate…

Deep neural networks have achieved remarkable performance in various applications but are extremely vulnerable to adversarial perturbation. The most representative and promising methods that can enhance model robustness, such as adversarial…