Related papers: SOLAR: Switchable Output Layer for Accuracy and Ro…

Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing…

The emergence of CNNs in mainstream deployment has necessitated methods to design and train efficient architectures tailored to maximize the accuracy under diverse hardware & latency constraints. To scale these resource-intensive tasks with…

Self-Supervised Learning (SSL) models rely on a pretext task to learn representations. Because this pretext task differs from the downstream tasks used to evaluate the performance of these models, there is an inherent misalignment or…

Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples. While literature has demonstrated great successes via representation learning, in this work, we show that substantial…

Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase -- accounting for 50--80% of total step time -- is bottlenecked by skewed generation: long-tailed trajectories indispensable for model…

Hierarchical reinforcement learning (RL) has the potential to enable effective decision-making over long timescales. Existing approaches, while promising, have yet to realize the benefits of large-scale training. In this work, we identify…

Ultrasound Shear Wave Elastography (USWE) with conventional B-mode imaging demonstrates better performance in lesion segmentation and classification problems. In this article, we propose SHEAR-net, an end-to-end deep neural network, to…

Deep neural networks (DNNs) are vulnerable to adversarial examples, in which DNNs are misled to false outputs due to inputs containing imperceptible perturbations. Adversarial training, a reliable and effective method of defense, may…

Large-scale self-supervised pre-training has paved the way for one foundation model to handle many different vision tasks. Most pre-training methodologies train a single model of a certain size at one time. Nevertheless, various computation…

Parameter-efficient fine-tuning approaches have recently garnered a lot of attention. Having considerably lower number of trainable weights, these methods can bring about scalability and computational effectiveness. In this paper, we look…

Accurate flood water mapping is critical for disaster management, yet current methods struggle to fully exploit the potential of spaceborne imagery. Optical data offers high interpretability but is limited by environmental conditions,…

Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. Many techniques have evolved over the past decade that made models lighter, faster, and…

In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task…

Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Existing acceleration methods usually require extensive training and are not universally applicable. LCM-LoRA, trainable…

Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…

Despite online learning (OL) techniques have boosted the performance of semi-supervised video object segmentation (VOS) methods, the huge time costs of OL greatly restrict their practicality. Matching based and propagation based methods run…

In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it is often required to assemble a large number of CLs, each containing thousands of parameters, in…

Standard softmax self-attention excels in vision tasks but incurs quadratic complexity O(N^2), limiting high-resolution deployment. Linear attention reduces the cost to O(N), yet its compressed state representations can impair modeling…

Micro-expression recognition (MER) has achieved impressive accuracy in controlled laboratory settings. However, its real-world applicability faces a significant generalization cliff, severely hindering practical deployment due to poor…

In cloud-centric recommender system, regular data exchanges between user devices and cloud could potentially elevate bandwidth demands and privacy risks. On-device recommendation emerges as a viable solution by performing reranking locally…