Related papers: On the Soft-Subnetwork for Few-shot Class Incremen…
Deep learning has shown great success in settings with massive amounts of data but has struggled when data is limited. Few-shot learning algorithms, which seek to address this limitation, are designed to generalize well to new tasks with…
We introduce Mixture-based Feature Space Learning (MixtFSL) for obtaining a rich and robust feature representation in the context of few-shot image classification. Previous works have proposed to model each base class either with a single…
Few-shot class-incremental learning (FSCIL) aims to continuously recognize novel classes under limited data, which suffers from the key stability-plasticity dilemma: balancing the retention of old knowledge with the acquisition of new…
Few-Shot Classification(FSC) aims to generalize from base classes to novel classes given very limited labeled samples, which is an important step on the path toward human-like machine learning. State-of-the-art solutions involve learning to…
We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings. Compared to the well-studied many-class many-shot and few-class few-shot problems, the MCFS problem commonly occurs in practical…
Few-shot learning (FSL) is an important and topical problem in computer vision that has motivated extensive research into numerous methods spanning from sophisticated meta-learning methods to simple transfer learning baselines. We seek to…
Few-shot class-incremental learning is to recognize the new classes given few samples and not forget the old classes. It is a challenging task since representation optimization and prototype reorganization can only be achieved under little…
Machine learning classifiers are often trained to recognize a set of pre-defined classes. However, in many applications, it is often desirable to have the flexibility of learning additional concepts, with limited data and without…
The success of deep learning models is heavily tied to the use of massive amount of labeled data and excessively long training time. With the emergence of intelligent edge applications that use these models, the critical challenge is to…
We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal…
Few-Shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes from a limited set of training samples without forgetting knowledge of previously learned classes. Conventional FSCIL methods typically build a robust…
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…
Novel classes frequently arise in our dynamically changing world, e.g., new users in the authentication system, and a machine learning model should recognize new classes without forgetting old ones. This scenario becomes more challenging…
Learning from a few examples is an important practical aspect of training classifiers. Various works have examined this aspect quite well. However, all existing approaches assume that the few examples provided are always correctly labeled.…
Few-shot class-incremental learning (FSCIL) has recently attracted extensive attention in various areas. Existing FSCIL methods highly depend on the robustness of the feature backbone pre-trained on base classes. In recent years, different…
Low-shot learning methods for image classification support learning from sparse data. We extend these techniques to support dense semantic image segmentation. Specifically, we train a network that, given a small set of annotated images,…
We introduce the integrative task of few-shot classification and segmentation (FS-CS) that aims to both classify and segment target objects in a query image when the target classes are given with a few examples. This task combines two…
Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks not seen during training, given only a few examples. To handle the limited-data problem in few-shot regimes, recent methods tend to…
The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research…
Recent deepfake detection studies often treat unseen sample detection as a ``zero-shot" task, training on images generated by known models but generalizing to unknown ones. A key real-world challenge arises when a model performs poorly on…