Search Results for author:
Found 16 papers, 3 papers with code
An Empirical Study Into What Matters for Calibrating Vision-Language Models
Vision--Language Models (VLMs) have emerged as the dominant approach for zero-shot recognition, adept at handling diverse scenarios and significant distribution changes.
A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
Driven by the above, this work comprehensively investigates the safety objectives of CLIP models, specifically focusing on three key properties: resilience to visual factor variations, calibrated uncertainty estimations, and the ability to detect anomalous inputs.
3D-GPT: Procedural 3D Modeling with Large Language Models
Our work highlights the potential of LLMs in 3D modeling, offering a basic framework for future advancements in scene generation and animation.
A Bag-of-Prototypes Representation for Dataset-Level Applications
The former measures how suitable a training set is for a target domain, while the latter studies how challenging a test set is for a learned model.
Adaptive Calibrator Ensemble for Model Calibration under Distribution Shift
In other words, a calibrator optimal on the calibration set would be suboptimal on the OOD test set and thus has degraded performance.
Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation
This work aims to assess how well a model performs under distribution shifts without using labels.
Adaptive Calibrator Ensemble: Navigating Test Set Difficulty in Out-of-Distribution Scenarios
With this knowledge, we propose a simple and effective method named adaptive calibrator ensemble (ACE) to calibrate OOD datasets whose difficulty is usually higher than the calibration set.
On the Strong Correlation Between Model Invariance and Generalization
Generalization and invariance are two essential properties of any machine learning model.
Ranking Models in Unlabeled New Environments
For this problem, we propose to adopt a proxy dataset that 1) is fully labeled and 2) well reflects the true model rankings in a given target environment, and use the performance rankings on the proxy sets as surrogates.
What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
In this work, we train semantic classification and rotation prediction in a multi-task way.
Fine-grained Classification via Categorical Memory Networks
The memory module stores the prototypical feature representation for each category as a moving average.
Ranked #49 on
Fine-Grained Image Classification
on CUB-200-2011
Are Labels Always Necessary for Classifier Accuracy Evaluation?
As the classification accuracy of the model on each sample (dataset) is known from the original dataset labels, our task can be solved via regression.
Domain Alignment with Triplets
When aligning the distributions in the embedding space, SCA enforces a similarity-preserving constraint to maintain class-level relations among the source and target images, i. e., if a source image and a target image are of the same class label, their corresponding embeddings are supposed to be aligned nearby, and vise versa.
Similarity-preserving Image-image Domain Adaptation for Person Re-identification
It first preserves two types of unsupervised similarity, namely, self-similarity of an image before and after translation, and domain-dissimilarity of a translated source image and a target image.
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
To this end, we propose to preserve two types of unsupervised similarities, 1) self-similarity of an image before and after translation, and 2) domain-dissimilarity of a translated source image and a target image.
SVDNet for Pedestrian Retrieval
This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID).
Ranked #14 on
Person Re-Identification
on CUHK03 detected
