Abstract Object Re-identification (Re-ID) aims to identify specific objects across different
times and scenes, which is a widely researched task in computer vision. For a prolonged …

Recent advances in large-scale pretraining have yielded visual foundation models with
strong capabilities. Not only can recent models generalize to arbitrary images for their …

Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs
more efficient by removing redundant information in the processed tokens. While different …

While many unsupervised learning models focus on one family of tasks, either generative or
discriminative, we explore the possibility of a unified representation learner: a model which …

The popular CLIP model displays impressive zero-shot capabilities thanks to its seamless
interaction with arbitrary text prompts. However, its lack of spatial awareness makes it …

Modern computer vision offers a great variety of models to practitioners, and selecting a
model from multiple options for specific applications can be challenging. Conventionally …

Recent self-supervised models produce visual features that are not only effective at
encoding image-level but also pixel-level semantics. They have been reported to obtain …

This paper studies the problem of concept-based interpretability of transformer
representations for videos. Concretely we seek to explain the decision-making process of …

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 …

We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-
trained MIM models. The motivation behind MIM-Refiner is rooted in the insight that optimal …