Related papers: Dual Memory Networks: A Versatile Adaptation Appro…
Large vision-language representation learning models like CLIP have demonstrated impressive performance for zero-shot transfer to downstream tasks while largely benefiting from inter-modal (image-text) alignment via contrastive objectives.…
Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have been devoted to domain adaptive semantic…
Zero-shot learning (ZSL) aims to recognize novel classes through transferring shared semantic knowledge (e.g., attributes) from seen classes to unseen classes. Recently, attention-based methods have exhibited significant progress which…
We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally…
Despite the surging demands for multilingual task-oriented dialog systems (e.g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios. Hence, we propose a zero-shot adaptation of task-oriented…
Large pre-trained vision-language (VL) models have shown significant promise in adapting to various downstream tasks. However, fine-tuning the entire network is challenging due to the massive number of model parameters. To address this…
Few-shot domain adaptation to multiple domains aims to learn a complex image distribution across multiple domains from a few training images. A na\"ive solution here is to train a separate model for each domain using few-shot domain…
Simulation-to-simulation and simulation-to-real world transfer of neural network models have been a difficult problem. To close the reality gap, prior methods to simulation-to-real world transfer focused on domain adaptation, decoupling…
Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few-shot learning for online adaptation. The recent few-shot…
Multimodal few-shot learning is challenging due to the large domain gap between vision and language modalities. Existing methods are trying to communicate visual concepts as prompts to frozen language models, but rely on hand-engineered…
The increasing complexity, dynamism, and heterogeneity of 6G networks demand management systems that can reason proactively and generalize beyond pre-defined cases. In this paper, we propose a modular, knowledge-defined architecture that…
Vision language foundation models such as CLIP exhibit impressive zero-shot generalization yet remain vulnerable to spurious correlations across visual and textual modalities. Existing debiasing approaches often address a single modality…
While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniques used for video are largely based off those for static…
Humans possess remarkable ability to accurately classify new, unseen images after being exposed to only a few examples. Such ability stems from their capacity to identify common features shared between new and previously seen images while…
In this paper, we introduce variational semantic memory into meta-learning to acquire long-term knowledge for few-shot learning. The variational semantic memory accrues and stores semantic information for the probabilistic inference of…
Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a direct consequence of the huge web-scale datasets used to…
Remote Sensing Vision-Language Models (RSVLMs) have shown remarkable potential thanks to large-scale pretraining, achieving strong zero-shot performance on various tasks. However, their ability to generalize in low-data regimes, such as…
Pre-training image representations from the raw text about images enables zero-shot vision transfer to downstream tasks. Through pre-training on millions of samples collected from the internet, multimodal foundation models, such as CLIP,…
Imagine a smart camera trap selectively clicking pictures to understand animal movement patterns within a particular habitat. These "snapshots", or pieces of data captured from a data stream at adaptively chosen times, provide a glimpse of…
This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text classification. The model utilizes dynamic routing to provide more flexibility to memory-based few-shot learning in order to better adapt the support sets, which…