相关论文: Semantic-Guided Dynamic Sparsification for Pre-Tra…

Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substantial ambiguity across language-conditioned tasks, severely…

Understanding how the collective activity of neural populations relates to computation and ultimately behavior is a key goal in neuroscience. To this end, statistical methods which describe high-dimensional neural time series in terms of…

Few-shot Class Incremental Learning (FSCIL) presents a challenging yet realistic scenario, which requires the model to continually learn new classes with limited labeled data (i.e., incremental sessions) while retaining knowledge of…

In multi-label learning, each sample is associated with several labels. Existing works indicate that exploring correlations between labels improve the prediction performance. However, embedding the label correlations into the training…

In today's connected world, the generation of massive streaming data across diverse domains has become commonplace. In the presence of concept drift, class imbalance, label scarcity, and new class emergence, they jointly degrade…

Many problems in science and engineering require making predictions based on few observations. To build a robust predictive model, these sparse data may need to be augmented with simulated data, especially when the design space is…

Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensions. In this work,…

Linear Dynamical System (LDS) is an elegant mathematical framework for modeling and learning multivariate time series. However, in general, it is difficult to set the dimension of its hidden state space. A small number of hidden states may…

Continual learning (CL) refers to the ability of an intelligent system to sequentially acquire and retain knowledge from a stream of data with as little computational overhead as possible. To this end; regularization, replay, architecture,…

Continual learning (CL) remains a significant challenge for deep neural networks, as it is prone to forgetting previously acquired knowledge. Several approaches have been proposed in the literature, such as experience rehearsal,…

This work addresses the task of completely weakly supervised class-incremental learning for semantic segmentation to learn segmentation for both base and additional novel classes using only image-level labels. While class-incremental…

This study investigates the impact of gradient compression on distributed training performance, focusing on sparsification and quantization techniques, including top-k, DGC, and QSGD. In baseline experiments, random-k compression results in…

Few-Shot Class-Incremental Learning (FSCIL) faces dual challenges of data scarcity and incremental learning in real-world scenarios. While pool-based prompting methods have demonstrated success in traditional incremental learning, their…

In scanning microscopy based imaging techniques, there is a need to develop novel data acquisition schemes that can reduce the time for data acquisition and minimize sample exposure to the probing radiation. Sparse sampling schemes are…

The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for…

The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To avoid catastrophic forgetting, various continual learning…

This paper presents meta-sparsity, a framework for learning model sparsity, basically learning the parameter that controls the degree of sparsity, that allows deep neural networks (DNNs) to inherently generate optimal sparse shared…

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…

3D point cloud semantic segmentation technology has been widely used. However, in real-world scenarios, the environment is evolving. Thus, offline-trained segmentation models may lead to catastrophic forgetting of previously seen classes.…

Sampling-based motion planners rely on incremental densification to discover progressively shorter paths. After computing feasible path $\xi$ between start $x_s$ and goal $x_t$, the Informed Set (IS) prunes the configuration space…