Related papers: Read-Write Memory and k-Set Consensus as an Affine…

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…

Pre-trained foundation models, due to their enormous capacity and exposure to vast amounts of data during pre-training, are known to have learned plenty of real-world concepts. An important step in making these pre-trained models effective…

This paper investigates an under-explored but important problem: given a collection of pre-trained neural networks, predicting their performance on each multi-modal task without fine-tuning them, such as image recognition, referring,…

Task incremental learning aims to enable a system to maintain its performance on previously learned tasks while learning new tasks, solving the problem of catastrophic forgetting. One promising approach is to build an individual network or…

Scribble-guided image editing allows users to combine simple scribble annotations with text prompts to specify both where and how an image should be edited, enabling flexible interaction with precise spatial control. However, existing…

Are (set)-consensus objects necessary? This paper answer is negative. We show that the availability of consensus objects can be replaced by restricting the set of runs we consider. In particular we concentrate of the set of runs of the…

Continual learning refers to the ability to acquire and transfer knowledge without catastrophically forgetting what was previously learned. In this work, we consider \emph{few-shot} continual learning in classification tasks, and we propose…

Catastrophic forgetting - the tendency of neural networks to forget previously learned data when learning new information - remains a central challenge in continual learning. In this work, we adopt a behavioral approach, observing a…

Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems. These two tasks are closely-related and can flourish each other. Since only a few utterances can be utilized for identifying…

Many real-world applications require making multiple predictions from the same text. Fine-tuning a large pre-trained language model for each downstream task causes computational burdens in the inference time due to several times of forward…

Deep learning models generally display catastrophic forgetting when learning new data continuously. Many incremental learning approaches address this problem by reusing data from previous tasks while learning new tasks. However, the direct…

Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask. SIS has mostly been addressed as a supervised problem. However, state-of-the-art methods depend…

Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge. Motivated by the characteristics of neural networks, in which information is stored in weights on connections, we investigated…

Class incremental learning aims to solve a problem that arises when continuously adding unseen class instances to an existing model This approach has been extensively studied in the context of image classification; however its applicability…

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

Contemporary neural networks are limited in their ability to learn from evolving streams of training data. When trained sequentially on new or evolving tasks, their accuracy drops sharply, making them unsuitable for many real-world…

We present an approach for efficiently taking snapshots of the state of a collection of CAS objects. Taking a snapshot allows later operations to read the value that each CAS object had at the time the snapshot was taken. Taking a snapshot…

Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While the problem of…

Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). To date, no empirical study has systematically examined the effectiveness of existing methods, nor investigated the…

In this paper, we consider a type of image quality assessment as a task-specific measurement, which can be used to select images that are more amenable to a given target task, such as image classification or segmentation. We propose to…