相关论文: Substance or Style: What Does Your Image Embedding…

Image embeddings are generally assumed to pose limited privacy risk. We challenge this assumption by formalizing semantic leakage as the ability to recover semantic structures from compressed image embeddings. Surprisingly, we show that…

Are traditional classification approaches irrelevant in this era of AI hype? We show that there are multiclass classification problems where predictive models holistically outperform LLM prompt-based frameworks. Given text and images from…

This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images. Conventional deep metric learning methods focus on learning a discriminative embedding to describe the semantic features…

Concept bottleneck models (CBMs) have emerged as critical tools in domains where interpretability is paramount. These models rely on predefined textual descriptions, referred to as concepts, to inform their decision-making process and offer…

Word embeddings are a key component of high-performing natural language processing (NLP) systems, but it remains a challenge to learn good representations for novel words on the fly, i.e., for words that did not occur in the training data.…

Pre-trained language models have demonstrated powerful capabilities in the field of natural language processing (NLP). Recently, code pre-trained model (PTM), which draw from the experiences of the NLP field, have also achieved…

Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…

Incorporating domain-specific priors in search and navigation tasks has shown promising results in improving generalization and sample complexity over end-to-end trained policies. In this work, we study how object embeddings that capture…

Text embeddings are numerical representations of text data, where words, phrases, or entire documents are converted into vectors of real numbers. These embeddings capture semantic meanings and relationships between text elements in a…

Collaborative filtering (CF) is a core technique for recommender systems. Traditional CF approaches exploit user-item relations (e.g., clicks, likes, and views) only and hence they suffer from the data sparsity issue. Items are usually…

Observing that for certain NLP tasks, such as semantic role prediction or thematic fit estimation, random embeddings perform as well as pretrained embeddings, we explore what settings allow for this and examine where most of the learning is…

A dramatic rise in the flow of manipulated image content on the Internet has led to an aggressive response from the media forensics research community. New efforts have incorporated increased usage of techniques from computer vision and…

Deep Metric Learning trains a neural network to map input images to a lower-dimensional embedding space such that similar images are closer together than dissimilar images. When used for item retrieval, a query image is embedded using the…

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

As the influence of LLMs expands, it is imperative to gain insight into their decisions. One way to do that is to develop probes that detect the presence or absence of a broad set of concepts within the embeddings computed in an LLM - which…

There have been many efforts to try to understand what grammatical knowledge (e.g., ability to understand the part of speech of a token) is encoded in large pre-trained language models (LM). This is done through `Edge Probing' (EP) tests:…

Human languages are full of metaphorical expressions. Metaphors help people understand the world by connecting new concepts and domains to more familiar ones. Large pre-trained language models (PLMs) are therefore assumed to encode…

Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each…

Large-scale pre-trained image-text models demonstrate remarkable versatility across diverse tasks, benefiting from their robust representational capabilities and effective multimodal alignment. We extend the application of these models,…