Related papers: Hierarchical Dual-Subspace Decoupling for Continua…
Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel…
Hierarchical Multiscale LSTM (Chung et al., 2016a) is a state-of-the-art language model that learns interpretable structure from character-level input. Such models can provide fertile ground for (cognitive) computational linguistics…
Transvaginal ultrasound is a critical imaging modality for evaluating cervical anatomy and detecting physiological changes. However, accurate segmentation of cervical structures remains challenging due to low contrast, shadow artifacts, and…
State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations. However, such 3D annotations are often expensive and time-consuming, which may not be practical for real applications. A…
Real-world object detection is highly desired to be equipped with the learning expandability that can enlarge its detection classes incrementally. Moreover, such learning from only few annotated training samples further adds the flexibility…
Instruction tuning is now a widely adopted approach to aligning large multimodal models (LMMs) to follow human intent. It unifies the data format of vision-language tasks, enabling multi-task joint training. However, vision-language tasks…
The increasing complexity of deep learning recommendation models (DLRM) has led to a growing need for large-scale distributed systems that can efficiently train vast amounts of data. In DLRM, the sparse embedding table is a crucial…
This paper addresses the challenge of incremental learning in growing graphs with increasingly complex tasks. The goal is to continuously train a graph model to handle new tasks while retaining proficiency in previous tasks via memory…
The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categories. Many works have been proposed to alleviate this…
The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only superior compression performance to representative methods…
Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this continual learning paradigm faces the significant challenge…
Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation,…
Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared structure while containing some task-specific properties. We…
This study focuses on the feature extraction problem in multi-modal data regression. To address three core challenges in real-world scenarios: limited and non-IID data, effective extraction and fusion of multi-modal information, and…
Natural Language-Guided Drones (NLGD) provide a novel paradigm for tasks such as target matching and navigation. However, the wide field of view and complex compositional semantics in drone scenarios pose challenges for vision-language…
Accurate brain tumor classification is crucial in medical imaging to ensure reliable diagnosis and effective treatment planning. This study introduces a novel double ensembling framework that synergistically combines pre-trained deep…
Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains. A central challenge in Continual Learning…
Multi-frame methods improve monocular depth estimation over single-frame approaches by aggregating spatial-temporal information via feature matching. However, the spatial-temporal feature leads to accuracy degradation in dynamic scenes. To…
We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in continual learning scenarios, storing network parameters at each…
Large-scale Hierarchical Classification (HC) involves datasets consisting of thousands of classes and millions of training instances with high-dimensional features posing several big data challenges. Feature selection that aims to select…