Search Results for author:
Found 10 papers, 8 papers with code
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for image generation.
Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress
However, with repeated testing, the risk of overfitting grows as algorithms over-exploit benchmark idiosyncrasies.
Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models
This finding points to a blind spot in current frontier VLMs: they excel in recognizing semantic content but fail to acquire an understanding of visual data-types through scaling.
SuS-X: Training-Free Name-Only Transfer of Vision-Language Models
Contrastive Language-Image Pre-training (CLIP) has emerged as a simple yet effective way to train large-scale vision-language models.
It's LeVAsa not LevioSA! Latent Encodings for Valence-Arousal Structure Alignment
We build a novel algorithm for mapping categorical and dimensional model labels using annotation transfer across affective facial image datasets.
On the Inference of Soft Biometrics from Typing Patterns Collected in a Multi-device Environment
On the other hand, for regression tasks, we evaluated three ML and four DL-based regressors.
DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors
Disentangling the underlying feature attributes within an image with no prior supervision is a challenging task.
COBRA: Contrastive Bi-Modal Representation Algorithm
In this paper, we present a novel framework COBRA that aims to train two modalities (image and text) in a joint fashion inspired by the Contrastive Predictive Coding (CPC) and Noise Contrastive Estimation (NCE) paradigms which preserve both inter and intra-class relationships.
EDUQA: Educational Domain Question Answering System using Conceptual Network Mapping
Most of the existing question answering models can be largely compiled into two categories: i) open domain question answering models that answer generic questions and use large-scale knowledge base along with the targeted web-corpus retrieval and ii) closed domain question answering models that address focused questioning area and use complex deep learning models.
Memeify: A Large-Scale Meme Generation System
The dataset consists of 1. 1 million meme captions from 128 classes.
