相关论文: DRIFT: Data Reduction via Informative Feature Tran…

Convolutional Neural Networks (CNNs) inherently encode strong inductive biases, enabling effective generalization on small-scale datasets. In this paper, we propose integrating this inductive bias into ViTs, not through an architectural…

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…

We propose a data-driven approach for intrinsic image decomposition, which is the process of inferring the confounding factors of reflectance and shading in an image. We pose this as a two-stage learning problem. First, we train a model to…

A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches typically treat the…

While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert data or discard valuable negative samples, leading to data inefficiency. To address this, we…

The fine-tuning of pre-trained models has become ubiquitous in generative AI, computer vision, and robotics. Although much attention has been paid to improving the efficiency of fine-tuning model, there has been less scholarship around…

We present a simple self-supervised method to enhance the performance of ViT features for dense downstream tasks. Our Lightweight Feature Transform (LiFT) is a straightforward and compact postprocessing network that can be applied to…

Recent advances in text-to-video generation have demonstrated the utility of powerful diffusion models. Nevertheless, the problem is not trivial when shaping diffusion models to animate static image (i.e., image-to-video generation). The…

Reconstructing physically plausible 3D human-scene interactions (HSI) from a single image currently presents a trade-off: optimization based methods offer accurate contact but are slow (~20s), while feed-forward approaches are fast yet lack…

Recent research towards understanding neural networks probes models in a top-down manner, but is only able to identify model tendencies that are known a priori. We propose Susceptibility Identification through Fine-Tuning (SIFT), a novel…

Vision Transformers (ViTs) is emerging as an alternative to convolutional neural networks (CNNs) for visual recognition. They achieve competitive results with CNNs but the lack of the typical convolutional inductive bias makes them more…

Vision Transformers (ViTs) have shown promising performance compared with Convolutional Neural Networks (CNNs), but the training of ViTs is much harder than CNNs. In this paper, we define several metrics, including Dynamic Data Proportion…

Self-supervised pretrain techniques have been widely used to improve the downstream tasks' performance. However, real-world magnetic resonance (MR) studies usually consist of different sets of contrasts due to different acquisition…

We consider the problem of fine-grained classification on an edge camera device that has limited power. The edge device must sparingly interact with the cloud to minimize communication bits to conserve power, and the cloud upon receiving…

Existing disparity fusion methods based on deep learning achieve state-of-the-art performance, but they require ground truth disparity data to train. As far as I know, this is the first time an unsupervised disparity fusion not using ground…

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…

User data confidentiality protection is becoming a rising challenge in the present deep learning research. Without access to data, conventional data-driven model compression faces a higher risk of performance degradation. Recently, some…

Despite recent advances in text-to-image generation, using synthetically generated data seldom brings a significant boost in performance for supervised learning. Oftentimes, synthetic datasets do not faithfully recreate the data…

Modern deep learning models operating on multi-modal visual signals often rely on inductive biases that are poorly aligned with the physical processes governing signal formation, leading to brittle performance under cross-spectral and…

Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous driving systems. Existing image and video driving datasets, however, fall short of capturing the mutable nature of the real…