7 accepted papers
Recent work shows that vision encoders capture ordinal attributes along linear axes, which can be recovered from as few as two labeled images. However, in the zero-shot setting, the text-driven rank axis for Vision-Language Models (VLMs) like CLIP remains suboptimal. In this work, we study the embed…
Automated model discovery is the process of automatically searching and identifying the most appropriate model for a given dataset over a large combinatorial search space. Existing approaches, however, often face challenges in balancing the capture of fine-grained details with ensuring generalizabil…
Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts containing multiple attribute-object pairs. This challenge prima…
"Vision language models (VLMs) perceive the world through a combination of a visual encoder and a large language model (LLM). The visual encoder, pre-trained on large-scale vision-text datasets, provides zero-shot generalization to visual data, and the LLM endows its high reasoning ability to VLMs.…
Comprehensive studies of synthetic optical flow datasets have attempted to reveal what properties lead to accuracy improvement in learning-based optical flow estimation. However, manually identifying and verifying the properties that contribute to accurate optical flow estimation require large-scale…
The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA), which enables global interactions at each layer of a ViT model. Previous works acknowledge the property of long-range dependency for the effectiveness in MSA. In this work, we study t…
In this work, we propose a communication-efficient parameterization, $\texttt{FedPara}$, for federated learning (FL) to overcome the burdens on frequent model uploads and downloads. Our method re-parameterizes weight parameters of layers using low-rank weights followed by the Hadamard product. Compa…