Related papers: CST: Calibration Side-Tuning for Parameter and Mem…

In this paper, we propose to exploit the side-tuning framework for multimodal document classification. Side-tuning is a methodology for network adaptation recently introduced to solve some of the problems related to previous approaches.…

Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. Yet, the demand for individualized and comprehensive fine-tuning processes for each task entails substantial…

Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of domains recently. However, it is costly to update the entire parameter set of large pre-trained models. Although recently proposed parameter-efficient…

When training a neural network for a desired task, one may prefer to adapt a pre-trained network rather than starting from randomly initialized weights. Adaptation can be useful in cases when training data is scarce, when a single learner…

Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually…

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…

Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pre-trained…

Multi-modal object detection in autonomous driving has achieved great breakthroughs due to the usage of fusing complementary information from different sensors. The calibration in fusion between sensors such as LiDAR and camera was always…

The impressive performance of deep learning architectures is associated with a massive increase in model complexity. Millions of parameters need to be tuned, with training and inference time scaling accordingly, together with energy…

Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…

Lane detection models are often evaluated in a closed-world setting, where training and testing occur on the same dataset. We observe that, even within the same domain, cross-dataset distribution shifts can cause severe catastrophic…

Benefit from the quick development of deep learning techniques, salient object detection has achieved remarkable progresses recently. However, there still exists following two major challenges that hinder its application in embedded…

Transfer learning is the predominant paradigm for training deep networks on small target datasets. Models are typically pretrained on large ``upstream'' datasets for classification, as such labels are easy to collect, and then finetuned on…

Object detection is one of the most fundamental yet challenging research topics in the domain of computer vision. Recently, the study on this topic in aerial images has made tremendous progress. However, complex background and worse imaging…

Recently, deep learning has been successfully applied to the single-image super-resolution (SISR) with remarkable performance. However, most existing methods focus on building a more complex network with a large number of layers, which can…

We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on instance-discriminative contrastive learning are not as…

Finetuning large language models (LLMs) has been empirically effective on a variety of downstream tasks. Existing approaches to finetuning an LLM either focus on parameter-efficient finetuning, which only updates a small number of trainable…

Object detection is a fundamental task for robots to operate in unstructured environments. Today, there are several deep learning algorithms that solve this task with remarkable performance. Unfortunately, training such systems requires…

In finetuning a large pretrained model to downstream tasks, parameter-efficient fine-tuning (PEFT) methods can effectively finetune pretrained models with few trainable parameters, but suffer from high GPU memory consumption and slow…

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…