相关论文: Read-Write Memory and k-Set Consensus as an Affine…

Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest…

In this paper, we propose a way of synthesizing realistic images directly with natural language description, which has many useful applications, e.g. intelligent image manipulation. We attempt to accomplish such synthesis: given a source…

Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples. Typical incremental approaches encounter a…

Session types are widely used as abstractions of asynchronous message passing systems. Refinement for such abstractions is crucial as it allows improvements of a given component without compromising its compatibility with the rest of the…

Intent classification (IC) and slot filling (SF) are core components in most goal-oriented dialogue systems. Current IC/SF models perform poorly when the number of training examples per class is small. We propose a new few-shot learning…

Catastrophic forgetting (CF) happens whenever a neural network overwrites past knowledge while being trained on new tasks. Common techniques to handle CF include regularization of the weights (using, e.g., their importance on past tasks),…

In collaborative filtering (CF) algorithms, the optimal models are usually learned by globally minimizing the empirical risks averaged over all the observed data. However, the global models are often obtained via a performance tradeoff…

Learning feature correspondence is a foundational task in computer vision, holding immense importance for downstream applications such as visual odometry and 3D reconstruction. Despite recent progress in data-driven models, feature…

Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a consequence of implicit multitask learning in language…

Continual learning the ability of a neural network to learn multiple sequential tasks without catastrophic forgetting remains a central challenge in developing adaptive artificial intelligence systems. While deep learning models achieve…

Recent works on instruction tuning (IT) have achieved great performance with zero-shot generalizability to unseen tasks. With additional context (e.g., task definition, examples) provided to models for fine-tuning, they achieved much higher…

This work aims at solving the problems with intractable sparsity-inducing norms that are often encountered in various machine learning tasks, such as multi-task learning, subspace clustering, feature selection, robust principal component…

Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly,…

Research on continual learning has led to a variety of approaches to mitigating catastrophic forgetting in feed-forward classification networks. Until now surprisingly little attention has been focused on continual learning of recurrent…

Automatic cell segmentation in microscopy images works well with the support of deep neural networks trained with full supervision. Collecting and annotating images, though, is not a sustainable solution for every new microscopy database…

Referring Remote Sensing Image Segmentation (RRSIS) is a situated, task-driven cross-modal task related to the embodied perception paradigm, requiring models to align visual-spatial features with linguistic intentions for precise target…

Single-image super-resolution refers to the reconstruction of a high-resolution image from a single low-resolution observation. Although recent deep learning-based methods have demonstrated notable success on simulated datasets -- with…

Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-based methods (e.g., EWC) can overconstrain updates when task optima are weakly overlapping,…

Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the…

Continual learning tries to learn new tasks without forgetting previously learned ones. In reality, most of the existing artificial neural network(ANN) models fail, while humans do the same by remembering previous works throughout their…