Search Results for author:
Found 32 papers, 11 papers with code
LatentCRF: Continuous CRF for Efficient Latent Diffusion
Latent Diffusion Models (LDMs) produce high-quality, photo-realistic images, however, the latency incurred by multiple costly inference iterations can restrict their applicability.
Efficient Document Ranking with Learnable Late Interactions
Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval.
Rethinking FID: Towards a Better Evaluation Metric for Image Generation
It is an unbiased estimator that does not make any assumptions on the probability distribution of the embeddings and is sample efficient.
MarkovGen: Structured Prediction for Efficient Text-to-Image Generation
Modern text-to-image generation models produce high-quality images that are both photorealistic and faithful to the text prompts.
Large Language Models with Controllable Working Memory
By contrast, when the context is irrelevant to the task, the model should ignore it and fall back on its internal knowledge.
When does mixup promote local linearity in learned representations?
Towards this, we study two questions: (1) how does the Mixup loss that enforces linearity in the \emph{last} network layer propagate the linearity to the \emph{earlier} layers?
Teacher Guided Training: An Efficient Framework for Knowledge Transfer
In this paper, we propose the teacher-guided training (TGT) framework for training a high-quality compact model that leverages the knowledge acquired by pretrained generative models, while obviating the need to go through a large volume of data.
Leveraging redundancy in attention with Reuse Transformers
Pairwise dot product-based attention allows Transformers to exchange information between tokens in an input-dependent way, and is key to their success across diverse applications in language and vision.
An Empirical Study of Pre-trained Models on Out-of-distribution Generalization
Concretely, we show that larger models and larger datasets need to be simultaneously leveraged to improve OOD performance.
Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation
State-of-the-art transformer models use pairwise dot-product based self-attention, which comes at a computational cost quadratic in the input sequence length.
RankDistil: Knowledge Distillation for Ranking
Knowledge distillation is an approach to improve the performance of a student model by using the knowledge of a complex teacher. Despite its success in several deep learning applications, the study of distillation is mostly confined to classification settings.
Understanding Robustness of Transformers for Image Classification
We find that when pre-trained with a sufficient amount of data, ViT models are at least as robust as the ResNet counterparts on a broad range of perturbations.
On the Reproducibility of Neural Network Predictions
By analyzing the relationship between churn and prediction confidences, we pursue an approach with two components for churn reduction.
Improving Calibration in Deep Metric Learning With Cross-Example Softmax
Triplet-based methods capture top-$k$ relevancy, where all top-$k$ scoring documents are assumed to be relevant to a given query Pairwise contrastive models capture threshold relevancy, where all documents scoring higher than some threshold are assumed to be relevant.
Coping with Label Shift via Distributionally Robust Optimisation
The label shift problem refers to the supervised learning setting where the train and test label distributions do not match.
Long-tail learning via logit adjustment
Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels are associated with only a few samples.
Ranked #53 on
Long-tail Learning
on ImageNet-LT
Doubly-stochastic mining for heterogeneous retrieval
Modern retrieval problems are characterised by training sets with potentially billions of labels, and heterogeneous data distributions across subpopulations (e. g., users of a retrieval system may be from different countries), each of which poses a challenge.
Why are Adaptive Methods Good for Attention Models?
While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models.
Why ADAM Beats SGD for Attention Models
While stochastic gradient descent (SGD) is still the de facto algorithm in deep learning, adaptive methods like Adam have been observed to outperform SGD across important tasks, such as attention models.
How To Backdoor Federated Learning
An attacker selected in a single round of federated learning can cause the global model to immediately reach 100% accuracy on the backdoor task.
Semantic Segmentation with Scarce Data
Semantic segmentation is a challenging vision problem that usually necessitates the collection of large amounts of finely annotated data, which is often quite expensive to obtain.
Learning to Evaluate Image Captioning
To address these two challenges, we propose a novel learning based discriminative evaluation metric that is directly trained to distinguish between human and machine-generated captions.
Convolutional Networks with Adaptive Inference Graphs
In this work, we propose convolutional networks with adaptive inference graphs (ConvNet-AIG) that adaptively define their network topology conditioned on the input image.
Separating Self-Expression and Visual Content in Hashtag Supervision
The variety, abundance, and structured nature of hashtags make them an interesting data source for training vision models.
Deep Learning is Robust to Massive Label Noise
Deep neural networks trained on large supervised datasets have led to impressive results in image classification and other tasks.
Learning From Noisy Large-Scale Datasets With Minimal Supervision
For the small clean set of annotations we use a quarter of the validation set with ~40k images.
Residual Networks Behave Like Ensembles of Relatively Shallow Networks
Moreover, residual networks seem to enable very deep networks by leveraging only the short paths during training.
Conditional Similarity Networks
A main reason for this is that contradicting notions of similarities cannot be captured in a single space.
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
The goal of COCO-Text is to advance state-of-the-art in text detection and recognition in natural images.
Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences
In this paper, we propose a novel learning framework to help answer these types of questions.
On Optimizing Human-Machine Task Assignments
When crowdsourcing systems are used in combination with machine inference systems in the real world, they benefit the most when the machine system is deeply integrated with the crowd workers.
Household Electricity Demand Forecasting -- Benchmarking State-of-the-Art Methods
The increasing use of renewable energy sources with variable output, such as solar photovoltaic and wind power generation, calls for Smart Grids that effectively manage flexible loads and energy storage.
