Related papers: ParameterNet: Parameters Are All You Need
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…
Large Language Models (LLMs) have shown remarkable performance across various tasks, but the escalating demands on computational resources pose significant challenges, particularly in the extensive utilization of full fine-tuning for…
Reinforcement learning (RL) yields substantial improvements in large language models (LLMs) downstream task performance and alignment with human values. Surprisingly, such large gains result from updating only a small subnetwork comprising…
With the explosive growth of multimodal content online, pre-trained visual-language models have shown great potential for multimodal recommendation. However, while these models achieve decent performance when applied in a frozen manner,…
We propose to impose symmetry in neural network parameters to improve parameter usage and make use of dedicated convolution and matrix multiplication routines. Due to significant reduction in the number of parameters as a result of the…
While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting. However, forecasters based on Transformers are still suffering…
Applying a pre-trained large model to downstream tasks is prohibitive under resource-constrained conditions. Recent dominant approaches for addressing efficiency issues involve adding a few learnable parameters to the fixed backbone model.…
Self-supervised methods have achieved remarkable success in transfer learning, often achieving the same or better accuracy than supervised pre-training. Most prior work has done so by increasing pre-training computation by adding complex…
Neural network pruning offers a promising prospect to facilitate deploying deep neural networks on resource-limited devices. However, existing methods are still challenged by the training inefficiency and labor cost in pruning designs, due…
State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining. ImageNet classification is the de facto pretraining task for these models. Yet, ImageNet is now nearly ten years old and is by modern…
Parameter-efficient fine-tuning (PEFT) techniques, such as adapter tuning, aim to fine-tune a pre-trained language model (PLM) using a minimal number of parameters for a specific task or profile. Although adapter tuning provides increased…
Object detection has gained great progress driven by the development of deep learning. Compared with a widely studied task -- classification, generally speaking, object detection even need one or two orders of magnitude more FLOPs (floating…
In some supervised learning settings, the practitioner might have additional information on the features used for prediction. We propose a new method which leverages this additional information for better prediction. The method, which we…
Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…
Deep learning models are used to minimize the number of polyps that goes unnoticed by the experts and to accurately segment the detected polyps during interventions. Although state-of-the-art models are proposed, it remains a challenge to…
A lightweight underwater image enhancement network is of great significance for resource-constrained platforms, but balancing model size, computational efficiency, and enhancement performance has proven difficult for previous approaches. In…
Large Language Models (LLMs) have demonstrated remarkable performance in real-world applications. However, adapting LLMs to novel tasks via fine-tuning often requires substantial training data and computational resources that are…
This paper introduces Growing Networks with Autonomous Pruning (GNAP) for image classification. Unlike traditional convolutional neural networks, GNAP change their size, as well as the number of parameters they are using, during training,…
We present Generalized LoRA (GLoRA), an advanced approach for universal parameter-efficient fine-tuning tasks. Enhancing Low-Rank Adaptation (LoRA), GLoRA employs a generalized prompt module to optimize pre-trained model weights and adjust…
Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more effective and efficient method for transferring VLMs to…