Related papers: High-Level Perceptual Similarity is Enabled by Lea…

We introduce a new multi-modal task for computer systems, posed as a combined vision-language comprehension challenge: identifying the most suitable text describing a scene, given several similar options. Accomplishing the task entails…

Recent trends in the machine learning community show that models with fidelity toward human perceptual measurements perform strongly on vision tasks. Likewise, human behavioral measurements have been used to regularize model performance.…

Deep learning methods have achieved great success in pedestrian detection, owing to its ability to learn features from raw pixels. However, they mainly capture middle-level representations, such as pose of pedestrian, but confuse positive…

Humans make complex inferences on faces, ranging from objective properties (gender, ethnicity, expression, age, identity, etc) to subjective judgments (facial attractiveness, trustworthiness, sociability, friendliness, etc). While the…

Rapid categorization paradigms have a long history in experimental psychology: Characterized by short presentation times and speedy behavioral responses, these tasks highlight the efficiency with which our visual system processes natural…

Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same,…

Representation learning approaches typically rely on images of objects captured from a single perspective that are transformed using affine transformations. Additionally, self-supervised learning, a successful paradigm of representation…

Visual illusions allow researchers to devise and test new models of visual perception. Here we show that artificial neural networks trained for basic visual tasks in natural images are deceived by brightness and color illusions, having a…

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Animals (especially humans) have an amazing ability to learn new tasks quickly, and switch between them flexibly. How brains support this ability is largely unknown, both neuroscientifically and algorithmically. One reasonable supposition…

Inference of correspondences between images from different modalities is an extremely important perceptual ability that enables humans to understand and recognize cross-modal concepts. In this paper, we consider an instance of this problem…

Many learning algorithms such as kernel machines, nearest neighbors, clustering, or anomaly detection, are based on the concept of 'distance' or 'similarity'. Before similarities are used for training an actual machine learning model, we…

Autonomous robots deal with unexpected scenarios in real environments. Given input images, various visual perception tasks can be performed, e.g., semantic segmentation, depth estimation and normal estimation. These different tasks provide…

As humans, we can remember certain visuals in great detail, and sometimes even after viewing them once. What is even more interesting is that humans tend to remember and forget the same things, suggesting that there might be some general…

One of the challenges of full autonomy is to have a robot capable of manipulating its current environment to achieve another environment configuration. This paper is a step towards this challenge, focusing on the visual understanding of the…

The upsurge in pre-trained large models started by ChatGPT has swept across the entire deep learning community. Such powerful models demonstrate advanced generative ability and multimodal understanding capability, which quickly set new…

Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…

Supervised learning methods have been suffering from the fact that a large-scale labeled dataset is mandatory, which is difficult to obtain. This has been a more significant issue for fashion compatibility prediction because compatibility…

We introduce a benchmark to directly evaluate the alignment between human observers and vision models on a 3D shape inference task. We leverage an experimental design from the cognitive sciences which requires zero-shot visual inferences…

Traditionally, multitask learning (MTL) assumes that all the tasks are related. This can lead to negative transfer when tasks are indeed incoherent. Recently, a number of approaches have been proposed that alleviate this problem by…