Related papers: ODIN: On-demand Data Formulation to Mitigate Datas…
State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label dataset-provided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain,…
The large spread of sensors and smart devices in urban infrastructures are motivating research in the area of Internet of Thing (IoT), to develop new services and improve citizens' quality of life. Sensors and smart devices generate large…
Open-Set Object Detection (OSOD) enables recognition of novel categories beyond fixed classes but faces challenges in aligning text representations with complex visual concepts and the scarcity of image-text pairs for rare categories. This…
Recent advances in computer vision have led to a resurgence of interest in visual data analytics. Researchers are developing systems for effectively and efficiently analyzing visual data at scale. A significant challenge that these systems…
Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is…
As an increasing number of businesses becomes powered by machine-learning, inference becomes a core operation, with a growing trend to be offered as a service. In this context, the inference task must meet certain service-level objectives…
As labeling cost for different modules in task-oriented dialog (ToD) systems is high, a major challenge in practice is to learn different tasks with the least amount of labeled data. Recently, prompting methods over pre-trained language…
We present the One Pass ImageNet (OPIN) problem, which aims to study the effectiveness of deep learning in a streaming setting. ImageNet is a widely known benchmark dataset that has helped drive and evaluate recent advancements in deep…
Distributed learning is widely used for training large models on large datasets by distributing parts of the model or dataset across multiple devices and aggregating the computed results for subsequent computations or parameter updates.…
We consider the problem of detecting out-of-distribution images in neural networks. We propose ODIN, a simple and effective method that does not require any change to a pre-trained neural network. Our method is based on the observation that…
We introduce the $\textbf{O}$ne-shot $\textbf{P}$runing $\textbf{T}$echnique for $\textbf{I}$nterchangeable $\textbf{N}$etworks ($\textbf{OPTIN}$) framework as a tool to increase the efficiency of pre-trained transformer architectures…
Open-set recognition and adversarial defense study two key aspects of deep learning that are vital for real-world deployment. The objective of open-set recognition is to identify samples from open-set classes during testing, while…
We introduce ODYN, a novel all-shifted primal-dual non-interior-point quadratic programming (QP) solver designed to efficiently handle challenging dense and sparse QPs. ODYN combines all-shifted nonlinear complementarity problem (NCP)…
Solving constrained nonlinear optimization problems (CNLPs) is a longstanding problem that arises in various fields, e.g., economics, computer science, and engineering. We propose optimization-informed neural networks (OINN), a deep…
Decentralized Intelligence Network (DIN) is a theoretical framework designed to address challenges in AI development, particularly focusing on data fragmentation and siloing issues. It facilitates effective AI training within sovereign data…
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…
Open-set semi-supervised learning (OSSL) has attracted growing interest, which investigates a more practical scenario where out-of-distribution (OOD) samples are only contained in unlabeled data. Existing OSSL methods like OpenMatch learn…
We introduce a challenging training scheme of conditional GANs, called open-set semi-supervised image generation, where the training dataset consists of two parts: (i) labeled data and (ii) unlabeled data with samples belonging to one of…
We introduce Low-Shot Open-Set Domain Generalization (LSOSDG), a novel paradigm unifying low-shot learning with open-set domain generalization (ODG). While prompt-based methods using models like CLIP have advanced DG, they falter in…
Open-set recognition and adversarial defense study two key aspects of deep learning that are vital for real-world deployment. The objective of open-set recognition is to identify samples from open-set classes during testing, while…