Related papers: Beyond Weight Adaptation: Feature-Space Domain Inj…
With the advent of large pre-trained transformer models, fine-tuning these models for various downstream tasks is a critical problem. Paucity of training data, the existence of data silos, and stringent privacy constraints exacerbate this…
With the increasing availability of depth sensors, multimodal frameworks that combine color information with depth data are gaining interest. However, ground truth data for semantic segmentation is burdensome to provide, thus making domain…
Parameter-Efficient Fine-Tuning (PEFT) of text-to-image models has become an increasingly popular technique with many applications. Among the various PEFT methods, Low-Rank Adaptation (LoRA) and its variants have gained significant…
Pretrained Foundation Models (PFMs) have transformed numerous applications by enabling efficient adaptation to customized tasks. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a resource-efficient alternative to full fine-tuning,…
Unsupervised domain adaptation methods have been widely explored to bridge domain gaps. However, in real-world remote-sensing scenarios, privacy and transmission constraints often preclude access to source domain data, which limits their…
Adapting vision transformer foundation models through parameter-efficient fine-tuning (PEFT) methods has become increasingly popular. These methods optimize a limited subset of parameters, enabling efficient adaptation without the need to…
Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast…
Recently, we have observed that Large Multi-modal Models (LMMs) are revolutionizing the way machines interact with the world, unlocking new possibilities across various multi-modal applications. To adapt LMMs for downstream tasks,…
Vision Foundation Models (VFMs) have become a de facto choice for many downstream vision tasks, like image classification, image segmentation, and object localization. However, they can also provide significant utility for downstream 3D…
The power of foundation models (FMs) lies in their capacity to learn highly expressive representations that can be adapted to a broad spectrum of tasks. However, these pretrained models require additional training stages to become effective…
Source-Free Object Detection (SFOD) has garnered much attention in recent years by eliminating the need of source-domain data in cross-domain tasks, but existing SFOD methods suffer from the Source Bias problem, i.e. the adapted model…
Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-aware dense prediction tasks. They exhibit different biases in representation: for instance,…
Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities.…
Parameter-efficient fine-tuning (PEFT) methods such as \lora{} adapt large pretrained models by adding small weight-space updates. While effective, weight deltas are hard to interpret mechanistically, and they do not directly expose…
Parameter Efficient Fine-Tuning (PEFT) techniques have drawn significant attention due to their ability to yield competitive results while updating only a small portion of the adjustable parameters. However, existing PEFT methods pose…
Monocular depth estimation under adverse weather conditions (e.g.\ rain, fog, snow, and nighttime) remains highly challenging due to the lack of reliable ground truth and the difficulty of learning from unlabeled real-world data. Existing…
Robotic perception in unstructured environments remains challenging despite the zero-shot capabilities of foundation models such as SAM. This work attributes performance degradation to non-uniform representation shifts across transformer…
Popular PEFT methods reduce trainable parameter count for fine-tuning by parameterizing new low-rank or sparse trainable weights in parallel to the frozen pre-trained weights $W$. However, these weights are trained from scratch, and there…
Real-time object detection has achieved substantial progress through meticulously designed architectures and optimization strategies. However, the pursuit of high-speed inference via lightweight network designs often leads to degraded…
Semantic-rich features from Vision Foundation Models (VFMs) have been leveraged to enhance Latent Diffusion Models (LDMs). However, raw VFM features are typically high-dimensional and redundant, increasing the difficulty of learning and…