Search Results for author:
Found 13 papers, 6 papers with code
Explaining CLIP's performance disparities on data from blind/low vision users
Testing 25 CLIP variants in a zero-shot classification task, we find that their accuracy is 15 percentage points lower on average for images captured by BLV users than web-crawled images.
EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods
From both the human study and automated evaluation, we find that: (i) Instruct-Pix2Pix, Null-Text and SINE are the top-performing methods averaged across different edit types, however {\it only} Instruct-Pix2Pix and Null-Text are able to preserve original image properties; (ii) Most of the editing methods fail at edits involving spatial operations (e. g., changing the position of an object).
NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation
This is useful in a wide range of real-world applications where collecting pixel-wise labels is not feasible in time or cost.
Augmenting CLIP with Improved Visio-Linguistic Reasoning
On the challenging Winoground compositional reasoning benchmark, our method improves the absolute visio-linguistic performance of different CLIP models by up to 7%, while on the ARO dataset, our method improves the visio-linguistic performance by upto 3%.
Strong Baselines for Parameter Efficient Few-Shot Fine-tuning
Through our controlled empirical study, we have two main findings: (i) Fine-tuning just the LayerNorm parameters (which we call LN-Tune) during few-shot adaptation is an extremely strong baseline across ViTs pre-trained with both self-supervised and supervised objectives, (ii) For self-supervised ViTs, we find that simply learning a set of scaling parameters for each attention matrix (which we call AttnScale) along with a domain-residual adapter (DRA) module leads to state-of-the-art performance (while being $\sim\!$ 9$\times$ more parameter-efficient) on MD.
NP-Match: When Neural Processes meet Semi-Supervised Learning
Semi-supervised learning (SSL) has been widely explored in recent years, and it is an effective way of leveraging unlabeled data to reduce the reliance on labeled data.
Memory Efficient Meta-Learning with Large Images
This limitation arises because a task's entire support set, which can contain up to 1000 images, must be processed before an optimization step can be taken.
ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
To close this gap, we present the ORBIT dataset and benchmark, grounded in the real-world application of teachable object recognizers for people who are blind/low-vision.
A Revised Generative Evaluation of Visual Dialogue
Evaluating Visual Dialogue, the task of answering a sequence of questions relating to a visual input, remains an open research challenge.
Visual Dialogue without Vision or Dialogue
We characterise some of the quirks and shortcomings in the exploration of Visual Dialogue - a sequential question-answering task where the questions and corresponding answers are related through given visual stimuli.
FlipDial: A Generative Model for Two-Way Visual Dialogue
We are the first to extend this paradigm to full two-way visual dialogue, where our model is capable of generating both questions and answers in sequence based on a visual input, for which we propose a set of novel evaluation measures and metrics.
Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation
We focus on the following three aspects of EM: (i) initialization; (ii) latent posterior estimation (E-step) and (iii) the parameter update (M-step).
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Random Forests versus Neural Networks - What's Best for Camera Localization?
This work addresses the task of camera localization in a known 3D scene given a single input RGB image.
